binutils-gdb/libctf/ctf-hash.c

811 lines
20 KiB
C
Raw Normal View History

/* Interface to hashtable implementations.
Copyright (C) 2006-2024 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 <string.h>
#include "libiberty.h"
#include "hashtab.h"
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
/* We have two hashtable implementations:
libctf, hash: introduce the ctf_dynset There are many places in the deduplicator which use hashtables as tiny sets: keys with no value (and usually, but not always, no freeing function) often with only one or a few members. For each of these, even after the last change to not store the freeing functions, we are storing a little malloced block for each item just to track the key/value pair, and a little malloced block for the hash table itself just to track the freeing function because we can't use libiberty hashtab's freeing function because we are using that to free the little malloced per-item block. If we only have a key, we don't need any of that: we can ditch the per-malloced block because we don't have a value, and we can ditch the per-hashtab structure because we don't need to independently track the freeing functions since libiberty hashtab is doing it for us. That means we don't need an owner field in the (now nonexistent) item block either. Roughly speaking, this datatype saves about 25% in time and 20% in peak memory usage for normal links, even fairly big ones. So this might seem redundant, but it's really worth it. Instead of a _lookup function, a dynset has two distinct functions: ctf_dynset_exists, which returns true or false and an optional pointer to the set member, and ctf_dynhash_lookup_any, which is used if all members of the set are expected to be equivalent and we just want *any* member and we don't care which one. There is no iterator in this set of functions, not because we don't iterate over dynset members -- we do, a lot -- but because the iterator here is a member of an entirely new family of much more convenient iteration functions, introduced in the next commit. libctf/ * ctf-hash.c (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (DYNSET_EMPTY_ENTRY_REPLACEMENT): New. (DYNSET_DELETED_ENTRY_REPLACEMENT): New. (key_to_internal): New. (internal_to_key): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. (ctf_hash_insert_type): Coding style. (ctf_hash_define_type): Likewise. * ctf-impl.h (ctf_dynset_t): New. (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. * ctf-inlines.h (ctf_dynset_cinsert): New.
2020-06-03 05:26:38 +08:00
- ctf_dynhash_* is an interface to a dynamically-expanding hash with
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
unknown size that should support addition of large numbers of items,
and removal as well, and is used only at type-insertion time and during
linking. It can be constructed with an expected initial number of
elements, but need not be.
libctf, hash: introduce the ctf_dynset There are many places in the deduplicator which use hashtables as tiny sets: keys with no value (and usually, but not always, no freeing function) often with only one or a few members. For each of these, even after the last change to not store the freeing functions, we are storing a little malloced block for each item just to track the key/value pair, and a little malloced block for the hash table itself just to track the freeing function because we can't use libiberty hashtab's freeing function because we are using that to free the little malloced per-item block. If we only have a key, we don't need any of that: we can ditch the per-malloced block because we don't have a value, and we can ditch the per-hashtab structure because we don't need to independently track the freeing functions since libiberty hashtab is doing it for us. That means we don't need an owner field in the (now nonexistent) item block either. Roughly speaking, this datatype saves about 25% in time and 20% in peak memory usage for normal links, even fairly big ones. So this might seem redundant, but it's really worth it. Instead of a _lookup function, a dynset has two distinct functions: ctf_dynset_exists, which returns true or false and an optional pointer to the set member, and ctf_dynhash_lookup_any, which is used if all members of the set are expected to be equivalent and we just want *any* member and we don't care which one. There is no iterator in this set of functions, not because we don't iterate over dynset members -- we do, a lot -- but because the iterator here is a member of an entirely new family of much more convenient iteration functions, introduced in the next commit. libctf/ * ctf-hash.c (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (DYNSET_EMPTY_ENTRY_REPLACEMENT): New. (DYNSET_DELETED_ENTRY_REPLACEMENT): New. (key_to_internal): New. (internal_to_key): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. (ctf_hash_insert_type): Coding style. (ctf_hash_define_type): Likewise. * ctf-impl.h (ctf_dynset_t): New. (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. * ctf-inlines.h (ctf_dynset_cinsert): New.
2020-06-03 05:26:38 +08:00
- ctf_dynset_* is an interface to a dynamically-expanding hash that contains
only keys: no values.
These can be implemented by the same underlying hashmap if you wish. */
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
/* The helem is used for general key/value mappings in the ctf_dynhash: the
owner may not have space allocated for it, and will be garbage (not
NULL!) in that case. */
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
typedef struct ctf_helem
{
void *key; /* Either a pointer, or a coerced ctf_id_t. */
void *value; /* The value (possibly a coerced int). */
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
ctf_dynhash_t *owner; /* The hash that owns us. */
} ctf_helem_t;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
/* Equally, the key_free and value_free may not exist. */
struct ctf_dynhash
{
struct htab *htab;
ctf_hash_free_fun key_free;
ctf_hash_free_fun value_free;
};
libctf, hash: introduce the ctf_dynset There are many places in the deduplicator which use hashtables as tiny sets: keys with no value (and usually, but not always, no freeing function) often with only one or a few members. For each of these, even after the last change to not store the freeing functions, we are storing a little malloced block for each item just to track the key/value pair, and a little malloced block for the hash table itself just to track the freeing function because we can't use libiberty hashtab's freeing function because we are using that to free the little malloced per-item block. If we only have a key, we don't need any of that: we can ditch the per-malloced block because we don't have a value, and we can ditch the per-hashtab structure because we don't need to independently track the freeing functions since libiberty hashtab is doing it for us. That means we don't need an owner field in the (now nonexistent) item block either. Roughly speaking, this datatype saves about 25% in time and 20% in peak memory usage for normal links, even fairly big ones. So this might seem redundant, but it's really worth it. Instead of a _lookup function, a dynset has two distinct functions: ctf_dynset_exists, which returns true or false and an optional pointer to the set member, and ctf_dynhash_lookup_any, which is used if all members of the set are expected to be equivalent and we just want *any* member and we don't care which one. There is no iterator in this set of functions, not because we don't iterate over dynset members -- we do, a lot -- but because the iterator here is a member of an entirely new family of much more convenient iteration functions, introduced in the next commit. libctf/ * ctf-hash.c (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (DYNSET_EMPTY_ENTRY_REPLACEMENT): New. (DYNSET_DELETED_ENTRY_REPLACEMENT): New. (key_to_internal): New. (internal_to_key): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. (ctf_hash_insert_type): Coding style. (ctf_hash_define_type): Likewise. * ctf-impl.h (ctf_dynset_t): New. (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. * ctf-inlines.h (ctf_dynset_cinsert): New.
2020-06-03 05:26:38 +08:00
/* Hash and eq functions for the dynhash and hash. */
unsigned int
ctf_hash_integer (const void *ptr)
{
ctf_helem_t *hep = (ctf_helem_t *) ptr;
return htab_hash_pointer (hep->key);
}
int
ctf_hash_eq_integer (const void *a, const void *b)
{
ctf_helem_t *hep_a = (ctf_helem_t *) a;
ctf_helem_t *hep_b = (ctf_helem_t *) b;
return htab_eq_pointer (hep_a->key, hep_b->key);
}
unsigned int
ctf_hash_string (const void *ptr)
{
ctf_helem_t *hep = (ctf_helem_t *) ptr;
return htab_hash_string (hep->key);
}
int
ctf_hash_eq_string (const void *a, const void *b)
{
ctf_helem_t *hep_a = (ctf_helem_t *) a;
ctf_helem_t *hep_b = (ctf_helem_t *) b;
return !strcmp((const char *) hep_a->key, (const char *) hep_b->key);
}
/* Hash a type_key. */
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
unsigned int
ctf_hash_type_key (const void *ptr)
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
{
ctf_helem_t *hep = (ctf_helem_t *) ptr;
ctf_link_type_key_t *k = (ctf_link_type_key_t *) hep->key;
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
return htab_hash_pointer (k->cltk_fp) + 59
* htab_hash_pointer ((void *) (uintptr_t) k->cltk_idx);
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
}
int
ctf_hash_eq_type_key (const void *a, const void *b)
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
{
ctf_helem_t *hep_a = (ctf_helem_t *) a;
ctf_helem_t *hep_b = (ctf_helem_t *) b;
ctf_link_type_key_t *key_a = (ctf_link_type_key_t *) hep_a->key;
ctf_link_type_key_t *key_b = (ctf_link_type_key_t *) hep_b->key;
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
return (key_a->cltk_fp == key_b->cltk_fp)
&& (key_a->cltk_idx == key_b->cltk_idx);
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
}
/* Hash a type_id_key. */
unsigned int
ctf_hash_type_id_key (const void *ptr)
{
ctf_helem_t *hep = (ctf_helem_t *) ptr;
ctf_type_id_key_t *k = (ctf_type_id_key_t *) hep->key;
return htab_hash_pointer ((void *) (uintptr_t) k->ctii_input_num)
+ 59 * htab_hash_pointer ((void *) (uintptr_t) k->ctii_type);
}
int
ctf_hash_eq_type_id_key (const void *a, const void *b)
{
ctf_helem_t *hep_a = (ctf_helem_t *) a;
ctf_helem_t *hep_b = (ctf_helem_t *) b;
ctf_type_id_key_t *key_a = (ctf_type_id_key_t *) hep_a->key;
ctf_type_id_key_t *key_b = (ctf_type_id_key_t *) hep_b->key;
return (key_a->ctii_input_num == key_b->ctii_input_num)
&& (key_a->ctii_type == key_b->ctii_type);
}
libctf, hash: introduce the ctf_dynset There are many places in the deduplicator which use hashtables as tiny sets: keys with no value (and usually, but not always, no freeing function) often with only one or a few members. For each of these, even after the last change to not store the freeing functions, we are storing a little malloced block for each item just to track the key/value pair, and a little malloced block for the hash table itself just to track the freeing function because we can't use libiberty hashtab's freeing function because we are using that to free the little malloced per-item block. If we only have a key, we don't need any of that: we can ditch the per-malloced block because we don't have a value, and we can ditch the per-hashtab structure because we don't need to independently track the freeing functions since libiberty hashtab is doing it for us. That means we don't need an owner field in the (now nonexistent) item block either. Roughly speaking, this datatype saves about 25% in time and 20% in peak memory usage for normal links, even fairly big ones. So this might seem redundant, but it's really worth it. Instead of a _lookup function, a dynset has two distinct functions: ctf_dynset_exists, which returns true or false and an optional pointer to the set member, and ctf_dynhash_lookup_any, which is used if all members of the set are expected to be equivalent and we just want *any* member and we don't care which one. There is no iterator in this set of functions, not because we don't iterate over dynset members -- we do, a lot -- but because the iterator here is a member of an entirely new family of much more convenient iteration functions, introduced in the next commit. libctf/ * ctf-hash.c (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (DYNSET_EMPTY_ENTRY_REPLACEMENT): New. (DYNSET_DELETED_ENTRY_REPLACEMENT): New. (key_to_internal): New. (internal_to_key): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. (ctf_hash_insert_type): Coding style. (ctf_hash_define_type): Likewise. * ctf-impl.h (ctf_dynset_t): New. (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. * ctf-inlines.h (ctf_dynset_cinsert): New.
2020-06-03 05:26:38 +08:00
/* The dynhash, used for hashes whose size is not known at creation time. */
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
/* Free a single ctf_helem with arbitrary key/value functions. */
static void
ctf_dynhash_item_free (void *item)
{
ctf_helem_t *helem = item;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
if (helem->owner->key_free && helem->key)
helem->owner->key_free (helem->key);
if (helem->owner->value_free && helem->value)
helem->owner->value_free (helem->value);
free (helem);
}
ctf_dynhash_t *
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
ctf_dynhash_create_sized (unsigned long nelems, ctf_hash_fun hash_fun,
ctf_hash_eq_fun eq_fun, ctf_hash_free_fun key_free,
ctf_hash_free_fun value_free)
{
ctf_dynhash_t *dynhash;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
htab_del del = ctf_dynhash_item_free;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
if (key_free || value_free)
dynhash = malloc (sizeof (ctf_dynhash_t));
else
dynhash = malloc (offsetof (ctf_dynhash_t, key_free));
if (!dynhash)
return NULL;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
if (key_free == NULL && value_free == NULL)
del = free;
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
if ((dynhash->htab = htab_create_alloc (nelems, (htab_hash) hash_fun, eq_fun,
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
del, xcalloc, free)) == NULL)
{
free (dynhash);
return NULL;
}
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
if (key_free || value_free)
{
dynhash->key_free = key_free;
dynhash->value_free = value_free;
}
return dynhash;
}
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
ctf_dynhash_t *
ctf_dynhash_create (ctf_hash_fun hash_fun, ctf_hash_eq_fun eq_fun,
ctf_hash_free_fun key_free, ctf_hash_free_fun value_free)
{
/* 7 is arbitrary and not benchmarked yet. */
return ctf_dynhash_create_sized (7, hash_fun, eq_fun, key_free, value_free);
}
static ctf_helem_t **
ctf_hashtab_lookup (struct htab *htab, const void *key, enum insert_option insert)
{
ctf_helem_t tmp = { .key = (void *) key };
return (ctf_helem_t **) htab_find_slot (htab, &tmp, insert);
}
static ctf_helem_t *
ctf_hashtab_insert (struct htab *htab, void *key, void *value,
ctf_hash_free_fun key_free,
ctf_hash_free_fun value_free)
{
ctf_helem_t **slot;
slot = ctf_hashtab_lookup (htab, key, INSERT);
if (!slot)
{
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
errno = ENOMEM;
return NULL;
}
if (!*slot)
{
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
/* Only spend space on the owner if we're going to use it: if there is a
key or value freeing function. */
if (key_free || value_free)
*slot = malloc (sizeof (ctf_helem_t));
else
*slot = malloc (offsetof (ctf_helem_t, owner));
if (!*slot)
return NULL;
(*slot)->key = key;
}
else
{
if (key_free)
key_free (key);
if (value_free)
value_free ((*slot)->value);
}
(*slot)->value = value;
return *slot;
}
int
ctf_dynhash_insert (ctf_dynhash_t *hp, void *key, void *value)
{
ctf_helem_t *slot;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
ctf_hash_free_fun key_free = NULL, value_free = NULL;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
if (hp->htab->del_f == ctf_dynhash_item_free)
{
key_free = hp->key_free;
value_free = hp->value_free;
}
slot = ctf_hashtab_insert (hp->htab, key, value,
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
key_free, value_free);
if (!slot)
return errno;
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
/* Keep track of the owner, so that the del function can get at the key_free
and value_free functions. Only do this if one of those functions is set:
if not, the owner is not even present in the helem. */
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
if (key_free || value_free)
slot->owner = hp;
return 0;
}
void
ctf_dynhash_remove (ctf_dynhash_t *hp, const void *key)
{
libctf, hash: save per-item space when no key/item freeing function The libctf dynhash hashtab abstraction supports per-hashtab arbitrary key/item freeing functions -- but it also has a constant slot type that holds both key and value requested by the user, so it needs to use its own freeing function to free that -- and it has nowhere to store the freeing functions the caller requested. So it copies them into every hash item, bloating every slot, even though all items in a given hash table must have the same key and value freeing functions. So point back to the owner using a back-pointer, but don't even spend space in the item or the hashtab allocating those freeing functions unless necessary: if none are needed, we can simply arrange to not pass in ctf_dynhash_item_free as a del_f to hashtab_create_alloc, and none of those fields will ever be accessed. The only downside is that this makes the code sensitive to the order of fields in the ctf_helem_t and ctf_hashtab_t: but the deduplicator allocates so many hash tables that doing this alone cuts memory usage during deduplication by about 10%. (libiberty hashtab itself has a lot of per-hashtab bloat: in the future we might trim that down, or make a trimmer version.) libctf/ * ctf-hash.c (ctf_helem_t) <key_free>: Remove. <value_free>: Likewise. <owner>: New. (ctf_dynhash_item_free): Indirect through the owner. (ctf_dynhash_create): Only pass in ctf_dynhash_item_free and allocate space for the key_free and value_free fields fields if necessary. (ctf_hashtab_insert): Likewise. Fix OOM errno value. (ctf_dynhash_insert): Only access ctf_hashtab's key_free and value_free if they will exist. Set the slot's owner, but only if it exists. (ctf_dynhash_remove): Adjust.
2020-06-03 05:00:14 +08:00
ctf_helem_t hep = { (void *) key, NULL, NULL };
htab_remove_elt (hp->htab, &hep);
}
libctf: map from old to corresponding newly-added types in ctf_add_type This lets you call ctf_type_mapping (dest_fp, src_fp, src_type_id) and get told what type ID the corresponding type has in the target ctf_file_t. This works even if it was added by a recursive call, and because it is stored in the target ctf_file_t it works even if we had to add one type to multiple ctf_file_t's as part of conflicting type handling. We empty out this mapping after every archive is linked: because it maps input to output fps, and we only visit each input fp once, its contents are rendered entirely useless every time the source fp changes. v3: add several missing mapping additions. Add ctf_dynhash_empty, and empty after every input archive. v5: fix tabdamage. libctf/ * ctf-impl.h (ctf_file_t): New field ctf_link_type_mapping. (struct ctf_link_type_mapping_key): New. (ctf_hash_type_mapping_key): Likewise. (ctf_hash_eq_type_mapping_key): Likewise. (ctf_add_type_mapping): Likewise. (ctf_type_mapping): Likewise. (ctf_dynhash_empty): Likewise. * ctf-open.c (ctf_file_close): Update accordingly. * ctf-create.c (ctf_update): Likewise. (ctf_add_type): Populate the mapping. * ctf-hash.c (ctf_hash_type_mapping_key): Hash a type mapping key. (ctf_hash_eq_type_mapping_key): Check the key for equality. (ctf_dynhash_insert): Fix comment typo. (ctf_dynhash_empty): New. * ctf-link.c (ctf_add_type_mapping): New. (ctf_type_mapping): Likewise. (empty_link_type_mapping): New. (ctf_link_one_input_archive): Call it.
2019-07-14 04:31:26 +08:00
void
ctf_dynhash_empty (ctf_dynhash_t *hp)
{
htab_empty (hp->htab);
}
size_t
ctf_dynhash_elements (ctf_dynhash_t *hp)
{
return htab_elements (hp->htab);
}
void *
ctf_dynhash_lookup (ctf_dynhash_t *hp, const void *key)
{
ctf_helem_t **slot;
slot = ctf_hashtab_lookup (hp->htab, key, NO_INSERT);
if (slot)
return (*slot)->value;
return NULL;
}
/* TRUE/FALSE return. */
int
ctf_dynhash_lookup_kv (ctf_dynhash_t *hp, const void *key,
const void **orig_key, void **value)
{
ctf_helem_t **slot;
slot = ctf_hashtab_lookup (hp->htab, key, NO_INSERT);
if (slot)
{
if (orig_key)
*orig_key = (*slot)->key;
if (value)
*value = (*slot)->value;
return 1;
}
return 0;
}
typedef struct ctf_traverse_cb_arg
{
ctf_hash_iter_f fun;
void *arg;
} ctf_traverse_cb_arg_t;
static int
ctf_hashtab_traverse (void **slot, void *arg_)
{
ctf_helem_t *helem = *((ctf_helem_t **) slot);
ctf_traverse_cb_arg_t *arg = (ctf_traverse_cb_arg_t *) arg_;
arg->fun (helem->key, helem->value, arg->arg);
return 1;
}
void
ctf_dynhash_iter (ctf_dynhash_t *hp, ctf_hash_iter_f fun, void *arg_)
{
ctf_traverse_cb_arg_t arg = { fun, arg_ };
htab_traverse (hp->htab, ctf_hashtab_traverse, &arg);
}
typedef struct ctf_traverse_find_cb_arg
{
ctf_hash_iter_find_f fun;
void *arg;
void *found_key;
} ctf_traverse_find_cb_arg_t;
static int
ctf_hashtab_traverse_find (void **slot, void *arg_)
{
ctf_helem_t *helem = *((ctf_helem_t **) slot);
ctf_traverse_find_cb_arg_t *arg = (ctf_traverse_find_cb_arg_t *) arg_;
if (arg->fun (helem->key, helem->value, arg->arg))
{
arg->found_key = helem->key;
return 0;
}
return 1;
}
void *
ctf_dynhash_iter_find (ctf_dynhash_t *hp, ctf_hash_iter_find_f fun, void *arg_)
{
ctf_traverse_find_cb_arg_t arg = { fun, arg_, NULL };
htab_traverse (hp->htab, ctf_hashtab_traverse_find, &arg);
return arg.found_key;
}
typedef struct ctf_traverse_remove_cb_arg
{
struct htab *htab;
ctf_hash_iter_remove_f fun;
void *arg;
} ctf_traverse_remove_cb_arg_t;
static int
ctf_hashtab_traverse_remove (void **slot, void *arg_)
{
ctf_helem_t *helem = *((ctf_helem_t **) slot);
ctf_traverse_remove_cb_arg_t *arg = (ctf_traverse_remove_cb_arg_t *) arg_;
if (arg->fun (helem->key, helem->value, arg->arg))
htab_clear_slot (arg->htab, slot);
return 1;
}
void
ctf_dynhash_iter_remove (ctf_dynhash_t *hp, ctf_hash_iter_remove_f fun,
void *arg_)
{
ctf_traverse_remove_cb_arg_t arg = { hp->htab, fun, arg_ };
htab_traverse (hp->htab, ctf_hashtab_traverse_remove, &arg);
}
/* Traverse a dynhash in arbitrary order, in _next iterator form.
Mutating the dynhash while iterating is not supported (just as it isn't for
htab_traverse).
Note: unusually, this returns zero on success and a *positive* value on
error, because it does not take an fp, taking an error pointer would be
incredibly clunky, and nearly all error-handling ends up stuffing the result
of this into some sort of errno or ctf_errno, which is invariably
positive. So doing this simplifies essentially all callers. */
int
ctf_dynhash_next (ctf_dynhash_t *h, ctf_next_t **it, void **key, void **value)
{
ctf_next_t *i = *it;
ctf_helem_t *slot;
if (!i)
{
size_t size = htab_size (h->htab);
/* If the table has too many entries to fit in an ssize_t, just give up.
This might be spurious, but if any type-related hashtable has ever been
nearly as large as that then something very odd is going on. */
if (((ssize_t) size) < 0)
return EDOM;
if ((i = ctf_next_create ()) == NULL)
return ENOMEM;
i->u.ctn_hash_slot = h->htab->entries;
i->cu.ctn_h = h;
i->ctn_n = 0;
i->ctn_size = (ssize_t) size;
i->ctn_iter_fun = (void (*) (void)) ctf_dynhash_next;
*it = i;
}
if ((void (*) (void)) ctf_dynhash_next != i->ctn_iter_fun)
return ECTF_NEXT_WRONGFUN;
if (h != i->cu.ctn_h)
return ECTF_NEXT_WRONGFP;
if ((ssize_t) i->ctn_n == i->ctn_size)
goto hash_end;
while ((ssize_t) i->ctn_n < i->ctn_size
&& (*i->u.ctn_hash_slot == HTAB_EMPTY_ENTRY
|| *i->u.ctn_hash_slot == HTAB_DELETED_ENTRY))
{
i->u.ctn_hash_slot++;
i->ctn_n++;
}
if ((ssize_t) i->ctn_n == i->ctn_size)
goto hash_end;
slot = *i->u.ctn_hash_slot;
if (key)
*key = slot->key;
if (value)
*value = slot->value;
i->u.ctn_hash_slot++;
i->ctn_n++;
return 0;
hash_end:
ctf_next_destroy (i);
*it = NULL;
return ECTF_NEXT_END;
}
libctf: symbol type linking support This adds facilities to write out the function info and data object sections, which efficiently map from entries in the symbol table to types. The write-side code is entirely new: the read-side code was merely significantly changed and support for indexed tables added (pointed to by the no-longer-unused cth_objtidxoff and cth_funcidxoff header fields). With this in place, you can use ctf_lookup_by_symbol to look up the types of symbols of function and object type (and, as before, you can use ctf_lookup_variable to look up types of file-scope variables not present in the symbol table, as long as you know their name: but variables that are also data objects are now found in the data object section instead.) (Compatible) file format change: The CTF spec has always said that the function info section looks much like the CTF_K_FUNCTIONs in the type section: an info word (including an argument count) followed by a return type and N argument types. This format is suboptimal: it means function symbols cannot be deduplicated and it causes a lot of ugly code duplication in libctf. But conveniently the compiler has never emitted this! Because it has always emitted a rather different format that libctf has never accepted, we can be sure that there are no instances of this function info section in the wild, and can freely change its format without compatibility concerns or a file format version bump. (And since it has never been emitted in any code that generated any older file format version, either, we need keep no code to read the format as specified at all!) So the function info section is now specified as an array of uint32_t, exactly like the object data section: each entry is a type ID in the type section which must be of kind CTF_K_FUNCTION, the prototype of this function. This allows function types to be deduplicated and also correctly encodes the fact that all functions declared in C really are types available to the program: so they should be stored in the type section like all other types. (In format v4, we will be able to represent the types of static functions as well, but that really does require a file format change.) We introduce a new header flag, CTF_F_NEWFUNCINFO, which is set if the new function info format is in use. A sufficiently new compiler will always set this flag. New libctf will always set this flag: old libctf will refuse to open any CTF dicts that have this flag set. If the flag is not set on a dict being read in, new libctf will disregard the function info section. Format v4 will remove this flag (or, rather, the flag has no meaning there and the bit position may be recycled for some other purpose). New API: Symbol addition: ctf_add_func_sym: Add a symbol with a given name and type. The type must be of kind CTF_K_FUNCTION (a function pointer). Internally this adds a name -> type mapping to the ctf_funchash in the ctf_dict. ctf_add_objt_sym: Add a symbol with a given name and type. The type kind can be anything, including function pointers. This adds to ctf_objthash. These both treat symbols as name -> type mappings: the linker associates symbol names with symbol indexes via the ctf_link_shuffle_syms callback, which sets up the ctf_dynsyms/ctf_dynsymidx/ctf_dynsymmax fields in the ctf_dict. Repeated relinks can add more symbols. Variables that are also exposed as symbols are removed from the variable section at serialization time. CTF symbol type sections which have enough pads, defined by CTF_INDEX_PAD_THRESHOLD (whether because they are in dicts with symbols where most types are unknown, or in archive where most types are defined in some child or parent dict, not in this specific dict) are sorted by name rather than symidx and accompanied by an index which associates each symbol type entry with a name: the existing ctf_lookup_by_symbol will map symbol indexes to symbol names and look the names up in the index automatically. (This is currently ELF-symbol-table-dependent, but there is almost nothing specific to ELF in here and we can add support for other symbol table formats easily). The compiler also uses index sections to communicate the contents of object file symbol tables without relying on any specific ordering of symbols: it doesn't need to sort them, and libctf will detect an unsorted index section via the absence of the new CTF_F_IDXSORTED header flag, and sort it if needed. Iteration: ctf_symbol_next: Iterator which returns the types and names of symbols one by one, either for function or data symbols. This does not require any sorting: the ctf_link machinery uses it to pull in all the compiler-provided symbols cheaply, but it is not restricted to that use. (Compatible) changes in API: ctf_lookup_by_symbol: can now be called for object and function symbols: never returns ECTF_NOTDATA (which is now not thrown by anything, but is kept for compatibility and because it is a plausible error that we might start throwing again at some later date). Internally we also have changes to the ctf-string functionality so that "external" strings (those where we track a string -> offset mapping, but only write out an offset) can be consulted via the usual means (ctf_strptr) before the strtab is written out. This is important because ctf_link_add_linker_symbol can now be handed symbols named via strtab offsets, and ctf_link_shuffle_syms must figure out their actual names by looking in the external symtab we have just been fed by the ctf_link_add_strtab callback, long before that strtab is written out. include/ChangeLog 2020-11-20 Nick Alcock <nick.alcock@oracle.com> * ctf-api.h (ctf_symbol_next): New. (ctf_add_objt_sym): Likewise. (ctf_add_func_sym): Likewise. * ctf.h: Document new function info section format. (CTF_F_NEWFUNCINFO): New. (CTF_F_IDXSORTED): New. (CTF_F_MAX): Adjust accordingly. libctf/ChangeLog 2020-11-20 Nick Alcock <nick.alcock@oracle.com> * ctf-impl.h (CTF_INDEX_PAD_THRESHOLD): New. (_libctf_nonnull_): Likewise. (ctf_in_flight_dynsym_t): New. (ctf_dict_t) <ctf_funcidx_names>: Likewise. <ctf_objtidx_names>: Likewise. <ctf_nfuncidx>: Likewise. <ctf_nobjtidx>: Likewise. <ctf_funcidx_sxlate>: Likewise. <ctf_objtidx_sxlate>: Likewise. <ctf_objthash>: Likewise. <ctf_funchash>: Likewise. <ctf_dynsyms>: Likewise. <ctf_dynsymidx>: Likewise. <ctf_dynsymmax>: Likewise. <ctf_in_flight_dynsym>: Likewise. (struct ctf_next) <u.ctn_next>: Likewise. (ctf_symtab_skippable): New prototype. (ctf_add_funcobjt_sym): Likewise. (ctf_dynhash_sort_by_name): Likewise. (ctf_sym_to_elf64): Rename to... (ctf_elf32_to_link_sym): ... this, and... (ctf_elf64_to_link_sym): ... this. * ctf-open.c (init_symtab): Check for lack of CTF_F_NEWFUNCINFO flag, and presence of index sections. Refactor out ctf_symtab_skippable and ctf_elf*_to_link_sym, and use them. Use ctf_link_sym_t, not Elf64_Sym. Skip initializing objt or func sxlate sections if corresponding index section is present. Adjust for new func info section format. (ctf_bufopen_internal): Add ctf_err_warn to corrupt-file error handling. Report incorrect-length index sections. Always do an init_symtab, even if there is no symtab section (there may be index sections still). (flip_objts): Adjust comment: func and objt sections are actually identical in structure now, no need to caveat. (ctf_dict_close): Free newly-added data structures. * ctf-create.c (ctf_create): Initialize them. (ctf_symtab_skippable): New, refactored out of init_symtab, with st_nameidx_set check added. (ctf_add_funcobjt_sym): New, add a function or object symbol to the ctf_objthash or ctf_funchash, by name. (ctf_add_objt_sym): Call it. (ctf_add_func_sym): Likewise. (symtypetab_delete_nonstatic_vars): New, delete vars also present as data objects. (CTF_SYMTYPETAB_EMIT_FUNCTION): New flag to symtypetab emitters: this is a function emission, not a data object emission. (CTF_SYMTYPETAB_EMIT_PAD): New flag to symtypetab emitters: emit pads for symbols with no type (only set for unindexed sections). (CTF_SYMTYPETAB_FORCE_INDEXED): New flag to symtypetab emitters: always emit indexed. (symtypetab_density): New, figure out section sizes. (emit_symtypetab): New, emit a symtypetab. (emit_symtypetab_index): New, emit a symtypetab index. (ctf_serialize): Call them, emitting suitably sorted symtypetab sections and indexes. Set suitable header flags. Copy over new fields. * ctf-hash.c (ctf_dynhash_sort_by_name): New, used to impose an order on symtypetab index sections. * ctf-link.c (ctf_add_type_mapping): Delete erroneous comment relating to code that was never committed. (ctf_link_one_variable): Improve variable name. (check_sym): New, symtypetab analogue of check_variable. (ctf_link_deduplicating_one_symtypetab): New. (ctf_link_deduplicating_syms): Likewise. (ctf_link_deduplicating): Call them. (ctf_link_deduplicating_per_cu): Note that we don't call them in this case (yet). (ctf_link_add_strtab): Set the error on the fp correctly. (ctf_link_add_linker_symbol): New (no longer a do-nothing stub), add a linker symbol to the in-flight list. (ctf_link_shuffle_syms): New (no longer a do-nothing stub), turn the in-flight list into a mapping we can use, now its names are resolvable in the external strtab. * ctf-string.c (ctf_str_rollback_atom): Don't roll back atoms with external strtab offsets. (ctf_str_rollback): Adjust comment. (ctf_str_write_strtab): Migrate ctf_syn_ext_strtab population from writeout time... (ctf_str_add_external): ... to string addition time. * ctf-lookup.c (ctf_lookup_var_key_t): Rename to... (ctf_lookup_idx_key_t): ... this, now we use it for syms too. <clik_names>: New member, a name table. (ctf_lookup_var): Adjust accordingly. (ctf_lookup_variable): Likewise. (ctf_lookup_by_id): Shuffle further up in the file. (ctf_symidx_sort_arg_cb): New, callback for... (sort_symidx_by_name): ... this new function to sort a symidx found to be unsorted (likely originating from the compiler). (ctf_symidx_sort): New, sort a symidx. (ctf_lookup_symbol_name): Support dynamic symbols with indexes provided by the linker. Use ctf_link_sym_t, not Elf64_Sym. Check the parent if a child lookup fails. (ctf_lookup_by_symbol): Likewise. Work for function symbols too. (ctf_symbol_next): New, iterate over symbols with types (without sorting). (ctf_lookup_idx_name): New, bsearch for symbol names in indexes. (ctf_try_lookup_indexed): New, attempt an indexed lookup. (ctf_func_info): Reimplement in terms of ctf_lookup_by_symbol. (ctf_func_args): Likewise. (ctf_get_dict): Move... * ctf-types.c (ctf_get_dict): ... here. * ctf-util.c (ctf_sym_to_elf64): Re-express as... (ctf_elf64_to_link_sym): ... this. Add new st_symidx field, and st_nameidx_set (always 0, so st_nameidx can be ignored). Look in the ELF strtab for names. (ctf_elf32_to_link_sym): Likewise, for Elf32_Sym. (ctf_next_destroy): Destroy ctf_next_t.u.ctn_next if need be. * libctf.ver: Add ctf_symbol_next, ctf_add_objt_sym and ctf_add_func_sym.
2020-11-20 21:34:04 +08:00
int
ctf_dynhash_sort_by_name (const ctf_next_hkv_t *one, const ctf_next_hkv_t *two,
void *unused _libctf_unused_)
{
return strcmp ((char *) one->hkv_key, (char *) two->hkv_key);
}
/* Traverse a sorted dynhash, in _next iterator form.
See ctf_dynhash_next for notes on error returns, etc.
Sort keys before iterating over them using the SORT_FUN and SORT_ARG.
If SORT_FUN is null, thunks to ctf_dynhash_next. */
int
ctf_dynhash_next_sorted (ctf_dynhash_t *h, ctf_next_t **it, void **key,
void **value, ctf_hash_sort_f sort_fun, void *sort_arg)
{
ctf_next_t *i = *it;
if (sort_fun == NULL)
return ctf_dynhash_next (h, it, key, value);
if (!i)
{
size_t els = ctf_dynhash_elements (h);
ctf_next_t *accum_i = NULL;
void *key, *value;
int err;
ctf_next_hkv_t *walk;
if (((ssize_t) els) < 0)
return EDOM;
if ((i = ctf_next_create ()) == NULL)
return ENOMEM;
if ((i->u.ctn_sorted_hkv = calloc (els, sizeof (ctf_next_hkv_t))) == NULL)
{
ctf_next_destroy (i);
return ENOMEM;
}
walk = i->u.ctn_sorted_hkv;
i->cu.ctn_h = h;
while ((err = ctf_dynhash_next (h, &accum_i, &key, &value)) == 0)
{
walk->hkv_key = key;
walk->hkv_value = value;
walk++;
}
if (err != ECTF_NEXT_END)
{
ctf_next_destroy (i);
return err;
}
if (sort_fun)
ctf_qsort_r (i->u.ctn_sorted_hkv, els, sizeof (ctf_next_hkv_t),
(int (*) (const void *, const void *, void *)) sort_fun,
sort_arg);
i->ctn_n = 0;
i->ctn_size = (ssize_t) els;
i->ctn_iter_fun = (void (*) (void)) ctf_dynhash_next_sorted;
*it = i;
}
if ((void (*) (void)) ctf_dynhash_next_sorted != i->ctn_iter_fun)
return ECTF_NEXT_WRONGFUN;
if (h != i->cu.ctn_h)
return ECTF_NEXT_WRONGFP;
if ((ssize_t) i->ctn_n == i->ctn_size)
{
ctf_next_destroy (i);
*it = NULL;
return ECTF_NEXT_END;
}
if (key)
*key = i->u.ctn_sorted_hkv[i->ctn_n].hkv_key;
if (value)
*value = i->u.ctn_sorted_hkv[i->ctn_n].hkv_value;
i->ctn_n++;
return 0;
}
void
ctf_dynhash_destroy (ctf_dynhash_t *hp)
{
if (hp != NULL)
htab_delete (hp->htab);
free (hp);
}
libctf, hash: introduce the ctf_dynset There are many places in the deduplicator which use hashtables as tiny sets: keys with no value (and usually, but not always, no freeing function) often with only one or a few members. For each of these, even after the last change to not store the freeing functions, we are storing a little malloced block for each item just to track the key/value pair, and a little malloced block for the hash table itself just to track the freeing function because we can't use libiberty hashtab's freeing function because we are using that to free the little malloced per-item block. If we only have a key, we don't need any of that: we can ditch the per-malloced block because we don't have a value, and we can ditch the per-hashtab structure because we don't need to independently track the freeing functions since libiberty hashtab is doing it for us. That means we don't need an owner field in the (now nonexistent) item block either. Roughly speaking, this datatype saves about 25% in time and 20% in peak memory usage for normal links, even fairly big ones. So this might seem redundant, but it's really worth it. Instead of a _lookup function, a dynset has two distinct functions: ctf_dynset_exists, which returns true or false and an optional pointer to the set member, and ctf_dynhash_lookup_any, which is used if all members of the set are expected to be equivalent and we just want *any* member and we don't care which one. There is no iterator in this set of functions, not because we don't iterate over dynset members -- we do, a lot -- but because the iterator here is a member of an entirely new family of much more convenient iteration functions, introduced in the next commit. libctf/ * ctf-hash.c (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (DYNSET_EMPTY_ENTRY_REPLACEMENT): New. (DYNSET_DELETED_ENTRY_REPLACEMENT): New. (key_to_internal): New. (internal_to_key): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. (ctf_hash_insert_type): Coding style. (ctf_hash_define_type): Likewise. * ctf-impl.h (ctf_dynset_t): New. (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. * ctf-inlines.h (ctf_dynset_cinsert): New.
2020-06-03 05:26:38 +08:00
/* The dynset, used for sets of keys with no value. The implementation of this
can be much simpler, because without a value the slot can simply be the
stored key, which means we don't need to store the freeing functions and the
dynset itself is just a htab. */
ctf_dynset_t *
ctf_dynset_create (htab_hash hash_fun, htab_eq eq_fun,
ctf_hash_free_fun key_free)
{
/* 7 is arbitrary and untested for now. */
return (ctf_dynset_t *) htab_create_alloc (7, (htab_hash) hash_fun, eq_fun,
key_free, xcalloc, free);
}
/* The dynset has one complexity: the underlying implementation reserves two
values for internal hash table implementation details (empty versus deleted
entries). These values are otherwise very useful for pointers cast to ints,
so transform the ctf_dynset_inserted value to allow for it. (This
introduces an ambiguity in that one can no longer store these two values in
the dynset, but if we pick high enough values this is very unlikely to be a
problem.)
We leak this implementation detail to the freeing functions on the grounds
that any use of these functions is overwhelmingly likely to be in sets using
real pointers, which will be unaffected. */
#define DYNSET_EMPTY_ENTRY_REPLACEMENT ((void *) (uintptr_t) -64)
#define DYNSET_DELETED_ENTRY_REPLACEMENT ((void *) (uintptr_t) -63)
static void *
key_to_internal (const void *key)
{
if (key == HTAB_EMPTY_ENTRY)
return DYNSET_EMPTY_ENTRY_REPLACEMENT;
else if (key == HTAB_DELETED_ENTRY)
return DYNSET_DELETED_ENTRY_REPLACEMENT;
return (void *) key;
}
static void *
internal_to_key (const void *internal)
{
if (internal == DYNSET_EMPTY_ENTRY_REPLACEMENT)
return HTAB_EMPTY_ENTRY;
else if (internal == DYNSET_DELETED_ENTRY_REPLACEMENT)
return HTAB_DELETED_ENTRY;
return (void *) internal;
}
int
ctf_dynset_insert (ctf_dynset_t *hp, void *key)
{
struct htab *htab = (struct htab *) hp;
void **slot;
slot = htab_find_slot (htab, key_to_internal (key), INSERT);
libctf, hash: introduce the ctf_dynset There are many places in the deduplicator which use hashtables as tiny sets: keys with no value (and usually, but not always, no freeing function) often with only one or a few members. For each of these, even after the last change to not store the freeing functions, we are storing a little malloced block for each item just to track the key/value pair, and a little malloced block for the hash table itself just to track the freeing function because we can't use libiberty hashtab's freeing function because we are using that to free the little malloced per-item block. If we only have a key, we don't need any of that: we can ditch the per-malloced block because we don't have a value, and we can ditch the per-hashtab structure because we don't need to independently track the freeing functions since libiberty hashtab is doing it for us. That means we don't need an owner field in the (now nonexistent) item block either. Roughly speaking, this datatype saves about 25% in time and 20% in peak memory usage for normal links, even fairly big ones. So this might seem redundant, but it's really worth it. Instead of a _lookup function, a dynset has two distinct functions: ctf_dynset_exists, which returns true or false and an optional pointer to the set member, and ctf_dynhash_lookup_any, which is used if all members of the set are expected to be equivalent and we just want *any* member and we don't care which one. There is no iterator in this set of functions, not because we don't iterate over dynset members -- we do, a lot -- but because the iterator here is a member of an entirely new family of much more convenient iteration functions, introduced in the next commit. libctf/ * ctf-hash.c (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (DYNSET_EMPTY_ENTRY_REPLACEMENT): New. (DYNSET_DELETED_ENTRY_REPLACEMENT): New. (key_to_internal): New. (internal_to_key): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. (ctf_hash_insert_type): Coding style. (ctf_hash_define_type): Likewise. * ctf-impl.h (ctf_dynset_t): New. (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. * ctf-inlines.h (ctf_dynset_cinsert): New.
2020-06-03 05:26:38 +08:00
if (!slot)
{
errno = ENOMEM;
return -errno;
}
if (*slot)
{
if (htab->del_f)
(*htab->del_f) (*slot);
}
*slot = key_to_internal (key);
return 0;
}
void
ctf_dynset_remove (ctf_dynset_t *hp, const void *key)
{
htab_remove_elt ((struct htab *) hp, key_to_internal (key));
}
libctf: prohibit addition of enums with overlapping enumerator constants libctf has long prohibited addition of enums with overlapping constants in a single enum, but now that we are properly considering enums with overlapping constants to be conflciting types, we can go further and prohibit addition of enumeration constants to a dict if they already exist in any enum in that dict: the same rules as C itself. We do this in a fashion vaguely similar to what we just did in the deduplicator, by considering enumeration constants as identifiers and adding them to the core type/identifier namespace, ctf_dict_t.ctf_names. This is a little fiddly, because we do not want to prohibit opening of existing dicts into which the deduplicator has stuffed enums with overlapping constants! We just want to prohibit the addition of *new* enumerators that violate that rule. Even then, it's fine to add overlapping enumerator constants as long as at least one of them is in a non-root type. (This is essential for proper deduplicator operation in cu-mapped mode, where multiple compilation units can be smashed into one dict, with conflicting types marked as hidden: these types may well contain overlapping enumerators.) So, at open time, keep track of all enums observed, then do a third pass through the enums alone, adding each enumerator either to the ctf_names table as a mapping from the enumerator name to the enum it is part of (if not already present), or to a new ctf_conflicting_enums hashtable that tracks observed duplicates. (The latter is not used yet, but will be soon.) (We need to do a third pass because it's quite possible to have an enum containing an enumerator FOO followed by a type FOO: since they're processed in order, the enumerator would be processed before the type, and at that stage it seems nonconflicting. The easiest fix is to run through the enumerators after all type names are interned.) At ctf_add_enumerator time, if the enumerator to which we are adding a type is root-visible, check for an already-present name and error out if found, then intern the new name in the ctf_names table as is done at open time. (We retain the existing code which scans the enum itself for duplicates because it is still an error to add an enumerator twice to a non-root-visible enum type; but we only need to do this if the enum is non-root-visible, so the cost of enum addition is reduced.) Tested in an upcoming commit. libctf/ * ctf-impl.h (ctf_dict_t) <ctf_names>: Augment comment. <ctf_conflicting_enums>: New. (ctf_dynset_elements): New. * ctf-hash.c (ctf_dynset_elements): Implement it. * ctf-open.c (init_static_types): Split body into... (init_static_types_internal): ... here. Count enumerators; keep track of observed enums in pass 2; populate ctf_names and ctf_conflicting_enums with enumerators in a third pass. (ctf_dict_close): Free ctf_conflicting_enums. * ctf-create.c (ctf_add_enumerator): Prohibit addition of duplicate enumerators in root-visible enum types. include/ * ctf-api.h (CTF_ADD_NONROOT): Describe what non-rootness means for enumeration constants. (ctf_add_enumerator): The name is not a misnomer. We now require that enumerators have unique names. Document the non-rootness of enumerators.
2024-06-12 03:33:03 +08:00
size_t
ctf_dynset_elements (ctf_dynset_t *hp)
{
return htab_elements ((struct htab *) hp);
}
libctf, hash: introduce the ctf_dynset There are many places in the deduplicator which use hashtables as tiny sets: keys with no value (and usually, but not always, no freeing function) often with only one or a few members. For each of these, even after the last change to not store the freeing functions, we are storing a little malloced block for each item just to track the key/value pair, and a little malloced block for the hash table itself just to track the freeing function because we can't use libiberty hashtab's freeing function because we are using that to free the little malloced per-item block. If we only have a key, we don't need any of that: we can ditch the per-malloced block because we don't have a value, and we can ditch the per-hashtab structure because we don't need to independently track the freeing functions since libiberty hashtab is doing it for us. That means we don't need an owner field in the (now nonexistent) item block either. Roughly speaking, this datatype saves about 25% in time and 20% in peak memory usage for normal links, even fairly big ones. So this might seem redundant, but it's really worth it. Instead of a _lookup function, a dynset has two distinct functions: ctf_dynset_exists, which returns true or false and an optional pointer to the set member, and ctf_dynhash_lookup_any, which is used if all members of the set are expected to be equivalent and we just want *any* member and we don't care which one. There is no iterator in this set of functions, not because we don't iterate over dynset members -- we do, a lot -- but because the iterator here is a member of an entirely new family of much more convenient iteration functions, introduced in the next commit. libctf/ * ctf-hash.c (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (DYNSET_EMPTY_ENTRY_REPLACEMENT): New. (DYNSET_DELETED_ENTRY_REPLACEMENT): New. (key_to_internal): New. (internal_to_key): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. (ctf_hash_insert_type): Coding style. (ctf_hash_define_type): Likewise. * ctf-impl.h (ctf_dynset_t): New. (ctf_dynset_eq_string): New. (ctf_dynset_create): New. (ctf_dynset_insert): New. (ctf_dynset_remove): New. (ctf_dynset_destroy): New. (ctf_dynset_lookup): New. (ctf_dynset_exists): New. (ctf_dynset_lookup_any): New. * ctf-inlines.h (ctf_dynset_cinsert): New.
2020-06-03 05:26:38 +08:00
void
ctf_dynset_destroy (ctf_dynset_t *hp)
{
if (hp != NULL)
htab_delete ((struct htab *) hp);
}
void *
ctf_dynset_lookup (ctf_dynset_t *hp, const void *key)
{
void **slot = htab_find_slot ((struct htab *) hp,
key_to_internal (key), NO_INSERT);
if (slot)
return internal_to_key (*slot);
return NULL;
}
/* TRUE/FALSE return. */
int
ctf_dynset_exists (ctf_dynset_t *hp, const void *key, const void **orig_key)
{
void **slot = htab_find_slot ((struct htab *) hp,
key_to_internal (key), NO_INSERT);
if (orig_key && slot)
*orig_key = internal_to_key (*slot);
return (slot != NULL);
}
/* Look up a completely random value from the set, if any exist.
Keys with value zero cannot be distinguished from a nonexistent key. */
void *
ctf_dynset_lookup_any (ctf_dynset_t *hp)
{
struct htab *htab = (struct htab *) hp;
void **slot = htab->entries;
void **limit = slot + htab_size (htab);
while (slot < limit
&& (*slot == HTAB_EMPTY_ENTRY || *slot == HTAB_DELETED_ENTRY))
slot++;
if (slot < limit)
return internal_to_key (*slot);
return NULL;
}
/* Traverse a dynset in arbitrary order, in _next iterator form.
Otherwise, just like ctf_dynhash_next. */
int
ctf_dynset_next (ctf_dynset_t *hp, ctf_next_t **it, void **key)
{
struct htab *htab = (struct htab *) hp;
ctf_next_t *i = *it;
void *slot;
if (!i)
{
size_t size = htab_size (htab);
/* If the table has too many entries to fit in an ssize_t, just give up.
This might be spurious, but if any type-related hashtable has ever been
nearly as large as that then somthing very odd is going on. */
if (((ssize_t) size) < 0)
return EDOM;
if ((i = ctf_next_create ()) == NULL)
return ENOMEM;
i->u.ctn_hash_slot = htab->entries;
i->cu.ctn_s = hp;
i->ctn_n = 0;
i->ctn_size = (ssize_t) size;
i->ctn_iter_fun = (void (*) (void)) ctf_dynset_next;
*it = i;
}
if ((void (*) (void)) ctf_dynset_next != i->ctn_iter_fun)
return ECTF_NEXT_WRONGFUN;
if (hp != i->cu.ctn_s)
return ECTF_NEXT_WRONGFP;
if ((ssize_t) i->ctn_n == i->ctn_size)
goto set_end;
while ((ssize_t) i->ctn_n < i->ctn_size
&& (*i->u.ctn_hash_slot == HTAB_EMPTY_ENTRY
|| *i->u.ctn_hash_slot == HTAB_DELETED_ENTRY))
{
i->u.ctn_hash_slot++;
i->ctn_n++;
}
if ((ssize_t) i->ctn_n == i->ctn_size)
goto set_end;
slot = *i->u.ctn_hash_slot;
if (key)
*key = internal_to_key (slot);
i->u.ctn_hash_slot++;
i->ctn_n++;
return 0;
set_end:
ctf_next_destroy (i);
*it = NULL;
return ECTF_NEXT_END;
}
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
/* Helper functions for insertion/removal of types. */
int
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
ctf_dynhash_insert_type (ctf_dict_t *fp, ctf_dynhash_t *hp, uint32_t type,
uint32_t name)
{
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
const char *str;
int err;
if (type == 0)
return EINVAL;
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
if ((str = ctf_strptr_validate (fp, name)) == NULL)
return ctf_errno (fp);
if (str[0] == '\0')
return 0; /* Just ignore empty strings on behalf of caller. */
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
if ((err = ctf_dynhash_insert (hp, (char *) str,
(void *) (ptrdiff_t) type)) == 0)
return 0;
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
return err;
}
ctf_id_t
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
ctf_dynhash_lookup_type (ctf_dynhash_t *hp, const char *key)
{
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
void *value;
libctf: remove static/dynamic name lookup distinction libctf internally maintains a set of hash tables for type name lookups, one for each valid C type namespace (struct, union, enum, and everything else). Or, rather, it maintains *two* sets of hash tables: one, a ctf_hash *, is meant for lookups in ctf_(buf)open()ed dicts with fixed content; the other, a ctf_dynhash *, is meant for lookups in ctf_create()d dicts. This distinction was somewhat valuable in the far pre-binutils past when two different hashtable implementations were used (one expanding, the other fixed-size), but those days are long gone: the hash table implementations are almost identical, both wrappers around the libiberty hashtab. The ctf_dynhash has many more capabilities than the ctf_hash (iteration, deletion, etc etc) and has no downsides other than starting at a fixed, arbitrary small size. That limitation is easy to lift (via a new ctf_dynhash_create_sized()), following which we can throw away nearly all the ctf_hash implementation, and all the code to choose between readable and writable hashtabs; the few convenience functions that are still useful (for insertion of name -> type mappings) can also be generalized a bit so that the extra string verification they do is potentially available to other string lookups as well. (libctf still has two hashtable implementations, ctf_dynhash, above, and ctf_dynset, which is a key-only hashtab that can avoid a great many malloc()s, used for high-volume applications in the deduplicator.) libctf/ * ctf-create.c (ctf_create): Eliminate ctn_writable. (ctf_dtd_insert): Likewise. (ctf_dtd_delete): Likewise. (ctf_rollback): Likewise. (ctf_name_table): Eliminate ctf_names_t. * ctf-hash.c (ctf_dynhash_create): Comment update. Reimplement in terms of... (ctf_dynhash_create_sized): ... this new function. (ctf_hash_create): Remove. (ctf_hash_size): Remove. (ctf_hash_define_type): Remove. (ctf_hash_destroy): Remove. (ctf_hash_lookup_type): Rename to... (ctf_dynhash_lookup_type): ... this. (ctf_hash_insert_type): Rename to... (ctf_dynhash_insert_type): ... this, moving validation to... * ctf-string.c (ctf_strptr_validate): ... this new function. * ctf-impl.h (struct ctf_names): Extirpate. (struct ctf_lookup.ctl_hash): Now a ctf_dynhash_t. (struct ctf_dict): All ctf_names_t fields are now ctf_dynhash_t. (ctf_name_table): Now returns a ctf_dynhash_t. (ctf_lookup_by_rawhash): Remove. (ctf_hash_create): Likewise. (ctf_hash_insert_type): Likewise. (ctf_hash_define_type): Likewise. (ctf_hash_lookup_type): Likewise. (ctf_hash_size): Likewise. (ctf_hash_destroy): Likewise. (ctf_dynhash_create_sized): New. (ctf_dynhash_insert_type): New. (ctf_dynhash_lookup_type): New. (ctf_strptr_validate): New. * ctf-lookup.c (ctf_lookup_by_name_internal): Adapt. * ctf-open.c (init_types): Adapt. (ctf_set_ctl_hashes): Adapt. (ctf_dict_close): Adapt. * ctf-serialize.c (ctf_serialize): Adapt. * ctf-types.c (ctf_lookup_by_rawhash): Remove.
2023-12-19 01:47:48 +08:00
if (ctf_dynhash_lookup_kv (hp, key, NULL, &value))
return (ctf_id_t) (uintptr_t) value;
return 0;
}