@@ -200,6 +200,11 @@ will be used, and CFLAGS sets optimizati
libnss_nisplus are not built at all. Use this option to enable
libnsl with all depending NSS modules and header files.
+'--disable-experimental-malloc'
+ By default, a per-thread cache is enabled in 'malloc'. While this
+ cache can be disabled on a per-application basis using tunables,
+ this option can be used to remove it from the build completely.
+
'--build=BUILD-SYSTEM'
'--host=HOST-SYSTEM'
These options are for cross-compiling. If you specify both options
@@ -7,6 +7,8 @@ using `glibc' in the "product" field.
Version 2.26
+* A per-thread cache has been added to malloc.
+
* Unicode 10.0.0 Support: Character encoding, character type info, and
transliteration tables are all updated to Unicode 10.0.0, using
generator scripts contributed by Mike FABIAN (Red Hat).
@@ -78,6 +78,8 @@ multi-arch = @multi_arch@
mach-interface-list = @mach_interface_list@
+experimental-malloc = @experimental_malloc@
+
nss-crypt = @libc_cv_nss_crypt@
static-nss-crypt = @libc_cv_static_nss_crypt@
@@ -674,6 +674,7 @@ build_obsolete_nsl
link_obsolete_rpc
libc_cv_static_nss_crypt
libc_cv_nss_crypt
+experimental_malloc
enable_werror
all_warnings
force_install
@@ -779,6 +780,7 @@ enable_kernel
enable_all_warnings
enable_werror
enable_multi_arch
+enable_experimental_malloc
enable_nss_crypt
enable_obsolete_rpc
enable_obsolete_nsl
@@ -1450,6 +1452,8 @@ Optional Features:
--disable-werror do not build with -Werror
--enable-multi-arch enable single DSO with optimizations for multiple
architectures
+ --disable-experimental-malloc
+ disable experimental malloc features
--enable-nss-crypt enable libcrypt to use nss
--enable-obsolete-rpc build and install the obsolete RPC code for
link-time usage
@@ -3522,6 +3526,15 @@ else
fi
+# Check whether --enable-experimental-malloc was given.
+if test "${enable_experimental_malloc+set}" = set; then :
+ enableval=$enable_experimental_malloc; experimental_malloc=$enableval
+else
+ experimental_malloc=yes
+fi
+
+
+
# Check whether --enable-nss-crypt was given.
if test "${enable_nss_crypt+set}" = set; then :
enableval=$enable_nss_crypt; nss_crypt=$enableval
@@ -313,6 +313,13 @@ AC_ARG_ENABLE([multi-arch],
[multi_arch=$enableval],
[multi_arch=default])
+AC_ARG_ENABLE([experimental-malloc],
+ AC_HELP_STRING([--disable-experimental-malloc],
+ [disable experimental malloc features]),
+ [experimental_malloc=$enableval],
+ [experimental_malloc=yes])
+AC_SUBST(experimental_malloc)
+
AC_ARG_ENABLE([nss-crypt],
AC_HELP_STRING([--enable-nss-crypt],
[enable libcrypt to use nss]),
@@ -76,6 +76,18 @@ glibc {
minval: 1
security_level: SXID_IGNORE
}
+ tcache_max {
+ type: SIZE_T
+ security_level: SXID_ERASE
+ }
+ tcache_count {
+ type: SIZE_T
+ security_level: SXID_ERASE
+ }
+ tcache_unsorted_limit {
+ type: SIZE_T
+ security_level: SXID_ERASE
+ }
}
tune {
hwcap_mask {
@@ -189,6 +189,11 @@ tst-malloc-usable-static-ENV = $(tst-mal
tst-malloc-usable-tunables-ENV = GLIBC_TUNABLES=glibc.malloc.check=3
tst-malloc-usable-static-tunables-ENV = $(tst-malloc-usable-tunables-ENV)
+ifeq ($(experimental-malloc),yes)
+CPPFLAGS-malloc.c += -DUSE_TCACHE=1
+else
+CPPFLAGS-malloc.c += -DUSE_TCACHE=0
+endif
# Uncomment this for test releases. For public releases it is too expensive.
#CPPFLAGS-malloc.o += -DMALLOC_DEBUG=1
@@ -236,6 +236,11 @@ TUNABLE_CALLBACK_FNDECL (set_perturb_byt
TUNABLE_CALLBACK_FNDECL (set_trim_threshold, size_t)
TUNABLE_CALLBACK_FNDECL (set_arena_max, size_t)
TUNABLE_CALLBACK_FNDECL (set_arena_test, size_t)
+#if USE_TCACHE
+TUNABLE_CALLBACK_FNDECL (set_tcache_max, size_t)
+TUNABLE_CALLBACK_FNDECL (set_tcache_count, size_t)
+TUNABLE_CALLBACK_FNDECL (set_tcache_unsorted_limit, size_t)
+#endif
#else
/* Initialization routine. */
#include <string.h>
@@ -322,6 +327,12 @@ ptmalloc_init (void)
TUNABLE_GET (mmap_max, int32_t, TUNABLE_CALLBACK (set_mmaps_max));
TUNABLE_GET (arena_max, size_t, TUNABLE_CALLBACK (set_arena_max));
TUNABLE_GET (arena_test, size_t, TUNABLE_CALLBACK (set_arena_test));
+#if USE_TCACHE
+ TUNABLE_GET (tcache_max, size_t, TUNABLE_CALLBACK (set_tcache_max));
+ TUNABLE_GET (tcache_count, size_t, TUNABLE_CALLBACK (set_tcache_count));
+ TUNABLE_GET (tcache_unsorted_limit, size_t,
+ TUNABLE_CALLBACK (set_tcache_unsorted_limit));
+#endif
__libc_lock_unlock (main_arena.mutex);
#else
const char *s = NULL;
@@ -238,6 +238,9 @@
/* For ALIGN_UP et. al. */
#include <libc-pointer-arith.h>
+/* For DIAG_PUSH/POP_NEEDS_COMMENT et al. */
+#include <libc-diag.h>
+
#include <malloc/malloc-internal.h>
/*
@@ -296,6 +299,30 @@ __malloc_assert (const char *assertion,
}
#endif
+#if USE_TCACHE
+/* We want 64 entries. This is an arbitrary limit, which tunables can reduce. */
+# define TCACHE_MAX_BINS 64
+# define MAX_TCACHE_SIZE tidx2usize (TCACHE_MAX_BINS-1)
+
+/* Only used to pre-fill the tunables. */
+# define tidx2usize(idx) (((size_t) idx) * MALLOC_ALIGNMENT + MINSIZE - SIZE_SZ)
+
+/* When "x" is from chunksize(). */
+# define csize2tidx(x) (((x) - MINSIZE + MALLOC_ALIGNMENT - 1) / MALLOC_ALIGNMENT)
+/* When "x" is a user-provided size. */
+# define usize2tidx(x) csize2tidx (request2size (x))
+
+/* With rounding and alignment, the bins are...
+ idx 0 bytes 0..24 (64-bit) or 0..12 (32-bit)
+ idx 1 bytes 25..40 or 13..20
+ idx 2 bytes 41..56 or 21..28
+ etc. */
+
+/* This is another arbitrary limit, which tunables can change. Each
+ tcache bin will hold at most this number of chunks. */
+# define TCACHE_FILL_COUNT 7
+#endif
+
/*
REALLOC_ZERO_BYTES_FREES should be set if a call to
@@ -1712,6 +1739,17 @@ struct malloc_par
/* First address handed out by MORECORE/sbrk. */
char *sbrk_base;
+
+#if USE_TCACHE
+ /* Maximum number of buckets to use. */
+ size_t tcache_bins;
+ size_t tcache_max_bytes;
+ /* Maximum number of chunks in each bucket. */
+ size_t tcache_count;
+ /* Maximum number of chunks to remove from the unsorted list, which
+ aren't used to prefill the cache. */
+ size_t tcache_unsorted_limit;
+#endif
};
/* There are several instances of this struct ("arenas") in this
@@ -1750,6 +1788,13 @@ static struct malloc_par mp_ =
.trim_threshold = DEFAULT_TRIM_THRESHOLD,
#define NARENAS_FROM_NCORES(n) ((n) * (sizeof (long) == 4 ? 2 : 8))
.arena_test = NARENAS_FROM_NCORES (1)
+#if USE_TCACHE
+ ,
+ .tcache_count = TCACHE_FILL_COUNT,
+ .tcache_bins = TCACHE_MAX_BINS,
+ .tcache_max_bytes = tidx2usize (TCACHE_MAX_BINS-1),
+ .tcache_unsorted_limit = 0 /* No limit. */
+#endif
};
/* Maximum size of memory handled in fastbins. */
@@ -2875,6 +2920,124 @@ mremap_chunk (mchunkptr p, size_t new_si
/*------------------------ Public wrappers. --------------------------------*/
+#if USE_TCACHE
+
+/* We overlay this structure on the user-data portion of a chunk when
+ the chunk is stored in the per-thread cache. */
+typedef struct tcache_entry
+{
+ struct tcache_entry *next;
+} tcache_entry;
+
+/* There is one of these for each thread, which contains the
+ per-thread cache (hence "tcache_perthread_struct"). Keeping
+ overall size low is mildly important. Note that COUNTS and ENTRIES
+ are redundant (we could have just counted the linked list each
+ time), this is for performance reasons. */
+typedef struct tcache_perthread_struct
+{
+ char counts[TCACHE_MAX_BINS];
+ tcache_entry *entries[TCACHE_MAX_BINS];
+} tcache_perthread_struct;
+
+static __thread char tcache_shutting_down = 0;
+static __thread tcache_perthread_struct *tcache = NULL;
+
+/* Caller must ensure that we know tc_idx is valid and there's room
+ for more chunks. */
+static void
+tcache_put (mchunkptr chunk, size_t tc_idx)
+{
+ tcache_entry *e = (tcache_entry *) chunk2mem (chunk);
+ assert (tc_idx < TCACHE_MAX_BINS);
+ e->next = tcache->entries[tc_idx];
+ tcache->entries[tc_idx] = e;
+ ++(tcache->counts[tc_idx]);
+}
+
+/* Caller must ensure that we know tc_idx is valid and there's
+ available chunks to remove. */
+static void *
+tcache_get (size_t tc_idx)
+{
+ tcache_entry *e = tcache->entries[tc_idx];
+ assert (tc_idx < TCACHE_MAX_BINS);
+ assert (tcache->entries[tc_idx] > 0);
+ tcache->entries[tc_idx] = e->next;
+ --(tcache->counts[tc_idx]);
+ return (void *) e;
+}
+
+static void __attribute__ ((section ("__libc_thread_freeres_fn")))
+tcache_thread_freeres (void)
+{
+ int i;
+ tcache_perthread_struct *tcache_tmp = tcache;
+
+ if (!tcache)
+ return;
+
+ tcache = NULL;
+
+ for (i = 0; i < TCACHE_MAX_BINS; ++i)
+ {
+ while (tcache_tmp->entries[i])
+ {
+ tcache_entry *e = tcache_tmp->entries[i];
+ tcache_tmp->entries[i] = e->next;
+ __libc_free (e);
+ }
+ }
+
+ __libc_free (tcache_tmp);
+
+ tcache_shutting_down = 1;
+}
+text_set_element (__libc_thread_subfreeres, tcache_thread_freeres);
+
+static void
+tcache_init(void)
+{
+ mstate ar_ptr;
+ void *victim = 0;
+ const size_t bytes = sizeof (tcache_perthread_struct);
+
+ if (tcache_shutting_down)
+ return;
+
+ arena_get (ar_ptr, bytes);
+ victim = _int_malloc (ar_ptr, bytes);
+ if (!victim && ar_ptr != NULL)
+ {
+ ar_ptr = arena_get_retry (ar_ptr, bytes);
+ victim = _int_malloc (ar_ptr, bytes);
+ }
+
+
+ if (ar_ptr != NULL)
+ __libc_lock_unlock (ar_ptr->mutex);
+
+ /* In a low memory situation, we may not be able to allocate memory
+ - in which case, we just keep trying later. However, we
+ typically do this very early, so either there is sufficient
+ memory, or there isn't enough memory to do non-trivial
+ allocations anyway. */
+ if (victim)
+ {
+ tcache = (tcache_perthread_struct *) victim;
+ memset (tcache, 0, sizeof (tcache_perthread_struct));
+ }
+
+}
+
+#define MAYBE_INIT_TCACHE() \
+ if (__glibc_unlikely (tcache == NULL)) \
+ tcache_init();
+
+#else
+#define MAYBE_INIT_TCACHE()
+#endif
+
void *
__libc_malloc (size_t bytes)
{
@@ -2885,6 +3048,23 @@ __libc_malloc (size_t bytes)
= atomic_forced_read (__malloc_hook);
if (__builtin_expect (hook != NULL, 0))
return (*hook)(bytes, RETURN_ADDRESS (0));
+#if USE_TCACHE
+ /* int_free also calls request2size, be careful to not pad twice. */
+ size_t tbytes = request2size (bytes);
+ size_t tc_idx = csize2tidx (tbytes);
+
+ MAYBE_INIT_TCACHE ();
+
+ DIAG_PUSH_NEEDS_COMMENT;
+ if (tc_idx < mp_.tcache_bins
+ /*&& tc_idx < TCACHE_MAX_BINS*/ /* to appease gcc */
+ && tcache
+ && tcache->entries[tc_idx] != NULL)
+ {
+ return tcache_get (tc_idx);
+ }
+ DIAG_POP_NEEDS_COMMENT;
+#endif
arena_get (ar_ptr, bytes);
@@ -2944,6 +3124,8 @@ __libc_free (void *mem)
return;
}
+ MAYBE_INIT_TCACHE ();
+
ar_ptr = arena_for_chunk (p);
_int_free (ar_ptr, p, 0);
}
@@ -2981,7 +3163,10 @@ __libc_realloc (void *oldmem, size_t byt
if (chunk_is_mmapped (oldp))
ar_ptr = NULL;
else
- ar_ptr = arena_for_chunk (oldp);
+ {
+ MAYBE_INIT_TCACHE ();
+ ar_ptr = arena_for_chunk (oldp);
+ }
/* Little security check which won't hurt performance: the allocator
never wrapps around at the end of the address space. Therefore
@@ -3206,6 +3391,8 @@ __libc_calloc (size_t n, size_t elem_siz
sz = bytes;
+ MAYBE_INIT_TCACHE ();
+
arena_get (av, sz);
if (av)
{
@@ -3336,6 +3523,10 @@ _int_malloc (mstate av, size_t bytes)
mchunkptr fwd; /* misc temp for linking */
mchunkptr bck; /* misc temp for linking */
+#if USE_TCACHE
+ size_t tcache_unsorted_count; /* count of unsorted chunks processed */
+#endif
+
const char *errstr = NULL;
/*
@@ -3365,19 +3556,22 @@ _int_malloc (mstate av, size_t bytes)
can try it without checking, which saves some time on this fast path.
*/
+#define REMOVE_FB(fb, victim, pp) \
+ do \
+ { \
+ victim = pp; \
+ if (victim == NULL) \
+ break; \
+ } \
+ while ((pp = catomic_compare_and_exchange_val_acq (fb, victim->fd, victim)) \
+ != victim); \
+
if ((unsigned long) (nb) <= (unsigned long) (get_max_fast ()))
{
idx = fastbin_index (nb);
mfastbinptr *fb = &fastbin (av, idx);
mchunkptr pp = *fb;
- do
- {
- victim = pp;
- if (victim == NULL)
- break;
- }
- while ((pp = catomic_compare_and_exchange_val_acq (fb, victim->fd, victim))
- != victim);
+ REMOVE_FB (fb, victim, pp);
if (victim != 0)
{
if (__builtin_expect (fastbin_index (chunksize (victim)) != idx, 0))
@@ -3388,6 +3582,26 @@ _int_malloc (mstate av, size_t bytes)
return NULL;
}
check_remalloced_chunk (av, victim, nb);
+#if USE_TCACHE
+ /* While we're here, if we see other chunks of the same size,
+ stash them in the tcache. */
+ size_t tc_idx = csize2tidx (nb);
+ if (tcache && tc_idx < mp_.tcache_bins)
+ {
+ mchunkptr tc_victim;
+
+ /* While bin not empty and tcache not full, copy chunks over. */
+ while (tcache->counts[tc_idx] < mp_.tcache_count
+ && (pp = *fb) != NULL)
+ {
+ REMOVE_FB (fb, tc_victim, pp);
+ if (tc_victim != 0)
+ {
+ tcache_put (tc_victim, tc_idx);
+ }
+ }
+ }
+#endif
void *p = chunk2mem (victim);
alloc_perturb (p, bytes);
return p;
@@ -3426,6 +3640,32 @@ _int_malloc (mstate av, size_t bytes)
if (av != &main_arena)
set_non_main_arena (victim);
check_malloced_chunk (av, victim, nb);
+#if USE_TCACHE
+ /* While we're here, if we see other chunks of the same size,
+ stash them in the tcache. */
+ size_t tc_idx = csize2tidx (nb);
+ if (tcache && tc_idx < mp_.tcache_bins)
+ {
+ mchunkptr tc_victim;
+
+ /* While bin not empty and tcache not full, copy chunks over. */
+ while (tcache->counts[tc_idx] < mp_.tcache_count
+ && (tc_victim = last (bin)) != bin)
+ {
+ if (tc_victim != 0)
+ {
+ bck = tc_victim->bk;
+ set_inuse_bit_at_offset (tc_victim, nb);
+ if (av != &main_arena)
+ set_non_main_arena (tc_victim);
+ bin->bk = bck;
+ bck->fd = bin;
+
+ tcache_put (tc_victim, tc_idx);
+ }
+ }
+ }
+#endif
void *p = chunk2mem (victim);
alloc_perturb (p, bytes);
return p;
@@ -3464,6 +3704,16 @@ _int_malloc (mstate av, size_t bytes)
otherwise need to expand memory to service a "small" request.
*/
+#if USE_TCACHE
+ INTERNAL_SIZE_T tcache_nb = 0;
+ size_t tc_idx = csize2tidx (nb);
+ if (tcache && tc_idx < mp_.tcache_bins)
+ tcache_nb = nb;
+ int return_cached = 0;
+
+ tcache_unsorted_count = 0;
+#endif
+
for (;; )
{
int iters = 0;
@@ -3524,10 +3774,26 @@ _int_malloc (mstate av, size_t bytes)
set_inuse_bit_at_offset (victim, size);
if (av != &main_arena)
set_non_main_arena (victim);
+#if USE_TCACHE
+ /* Fill cache first, return to user only if cache fills.
+ We may return one of these chunks later. */
+ if (tcache_nb
+ && tcache->counts[tc_idx] < mp_.tcache_count)
+ {
+ tcache_put (victim, tc_idx);
+ return_cached = 1;
+ continue;
+ }
+ else
+ {
+#endif
check_malloced_chunk (av, victim, nb);
void *p = chunk2mem (victim);
alloc_perturb (p, bytes);
return p;
+#if USE_TCACHE
+ }
+#endif
}
/* place chunk in bin */
@@ -3594,11 +3860,31 @@ _int_malloc (mstate av, size_t bytes)
fwd->bk = victim;
bck->fd = victim;
+#if USE_TCACHE
+ /* If we've processed as many chunks as we're allowed while
+ filling the cache, return one of the cached ones. */
+ ++tcache_unsorted_count;
+ if (return_cached
+ && mp_.tcache_unsorted_limit > 0
+ && tcache_unsorted_count > mp_.tcache_unsorted_limit)
+ {
+ return tcache_get (tc_idx);
+ }
+#endif
+
#define MAX_ITERS 10000
if (++iters >= MAX_ITERS)
break;
}
+#if USE_TCACHE
+ /* If all the small chunks we found ended up cached, return one now. */
+ if (return_cached)
+ {
+ return tcache_get (tc_idx);
+ }
+#endif
+
/*
If a large request, scan through the chunks of current bin in
sorted order to find smallest that fits. Use the skip list for this.
@@ -3884,6 +4170,20 @@ _int_free (mstate av, mchunkptr p, int h
check_inuse_chunk(av, p);
+#if USE_TCACHE
+ {
+ size_t tc_idx = csize2tidx (size);
+
+ if (tcache
+ && tc_idx < mp_.tcache_bins
+ && tcache->counts[tc_idx] < mp_.tcache_count)
+ {
+ tcache_put (p, tc_idx);
+ return;
+ }
+ }
+#endif
+
/*
If eligible, place chunk on a fastbin so it can be found
and used quickly in malloc.
@@ -4845,6 +5145,38 @@ do_set_arena_max (size_t value)
return 1;
}
+#if USE_TCACHE
+static inline int
+__always_inline
+do_set_tcache_max (size_t value)
+{
+ if (value >= 0 && value <= MAX_TCACHE_SIZE)
+ {
+ LIBC_PROBE (memory_tunable_tcache_max_bytes, 2, value, mp_.tcache_max_bytes);
+ mp_.tcache_max_bytes = value;
+ mp_.tcache_bins = csize2tidx (request2size(value)) + 1;
+ }
+ return 1;
+}
+
+static inline int
+__always_inline
+do_set_tcache_count (size_t value)
+{
+ LIBC_PROBE (memory_tunable_tcache_count, 2, value, mp_.tcache_count);
+ mp_.tcache_count = value;
+ return 1;
+}
+
+static inline int
+__always_inline
+do_set_tcache_unsorted_limit (size_t value)
+{
+ LIBC_PROBE (memory_tunable_tcache_unsorted_limit, 2, value, mp_.tcache_unsorted_limit);
+ mp_.tcache_unsorted_limit = value;
+ return 1;
+}
+#endif
int
__libc_mallopt (int param_number, int value)
@@ -232,6 +232,11 @@ libnss_nisplus are not built at all.
Use this option to enable libnsl with all depending NSS modules and
header files.
+@item --disable-experimental-malloc
+By default, a per-thread cache is enabled in @code{malloc}. While
+this cache can be disabled on a per-application basis using tunables,
+this option can be used to remove it from the build completely.
+
@item --build=@var{build-system}
@itemx --host=@var{host-system}
These options are for cross-compiling. If you specify both options and
@@ -231,6 +231,25 @@ dynamic brk/mmap thresholds. Argument @
the adjusted mmap and trim thresholds, respectively.
@end deftp
+@deftp Probe memory_tunable_tcache_max_bytes (int @var{$arg1}, int @var{$arg2})
+This probe is triggered when the @code{glibc.malloc.tcache_max}
+tunable is set. Argument @var{$arg1} is the requested value, and
+@var{$arg2} is the previous value of this tunable.
+@end deftp
+
+@deftp Probe memory_tunable_tcache_count (int @var{$arg1}, int @var{$arg2})
+This probe is triggered when the @code{glibc.malloc.tcache_count}
+tunable is set. Argument @var{$arg1} is the requested value, and
+@var{$arg2} is the previous value of this tunable.
+@end deftp
+
+@deftp Probe memory_tunable_tcache_unsorted_limit (int @var{$arg1}, int @var{$arg2})
+This probe is triggered when the
+@code{glibc.malloc.tcache_unsorted_limit} tunable is set. Argument
+@var{$arg1} is the requested value, and @var{$arg2} is the previous
+value of this tunable.
+@end deftp
+
@node Mathematical Function Probes
@section Mathematical Function Probes
@@ -193,6 +193,37 @@ systems the limit is twice the number of
is 8 times the number of cores online.
@end deftp
+@deftp Tunable glibc.malloc.tcache_max
+The maximum size of a request (in bytes) which may be met via the
+per-thread cache. The default (and maximum) value is 1032 bytes on
+64-bit systems and 516 bytes on 32-bit systems.
+@end deftp
+
+@deftp Tunable glibc.malloc.tcache_count
+The maximum number of chunks of each size to cache. The default is 7.
+There is no upper limit, other than available system memory.
+
+The approximate maximum overhead of the per-thread cache is thus equal
+to the number of bins times the chunk count in each bin times the size
+of each chunk. With defaults, the approximate maximum overhead of the
+per-thread cache is approximately 236 KB on 64-bit systems and 118 KB
+on 32-bit systems.
+@end deftp
+
+@deftp Tunable glibc.malloc.tcache_unsorted_limit
+When the user requests memory and the request cannot be met via the
+per-thread cache, the arenas are used to meet the request. At this
+time, additional chunks will be moved from existing arena lists to
+pre-fill the corresponding cache. While copies from the fastbins,
+smallbins, and regular bins are bounded and predictable due to the bin
+sizes, copies from the unsorted bin are not bounded, and incur
+additional time penalties as they need to be sorted as they're
+scanned. To make scanning the unsorted list more predictable and
+bounded, the user may set this tunable to limit the number of chunks
+that are scanned from the unsorted list while searching for chunks to
+pre-fill the per-thread cache with. The default, or when set to zero,
+is no limit.
+
@node Hardware Capability Tunables
@section Hardware Capability Tunables
@cindex hardware capability tunables