Lines Matching refs:memory

30 Ulrich Drepper's ELF TLS document specifies two ways of organizing memory pointed at by the
106 A simple approach is to allocate memory lazily:
112    memory.
116 musl, on the other, preallocates TLS memory in `pthread_create` and in `dlopen`, and each can report
117 out-of-memory.
212 memory in the static TLS block. glibc reserves a kilobyte or two (`TLS_STATIC_SURPLUS`) with the
218 Neither musl nor the Bionic TLS prototype currently allocate any surplus TLS memory.
220 In general, supporting surplus TLS memory probably requires maintaining a thread list so that
221 `dlopen` can initialize the new static TLS memory in all existing threads. A thread list could be
222 omitted if the loader only allowed zero-initialized TLS segments and didn't reclaim memory on
378 gdb provides APIs for looking up symbols, reading or writing memory, and retrieving the current
470 rather than experience memory corruption at run-time.
483 marks, so running it on an older platform would result in memory corruption. Should we add something
519 region, along with a thread's stack if it needs one allocated. It doesn't place TLS memory on a
531 The loader's entry points need to call `__tls_get_addr`, which needs to allocate memory. Currently,
553 The prototype lazily allocates TLS memory for dlopen'ed modules (see `__tls_get_addr`), and an
554 out-of-memory error on a TLS access aborts the process. musl, on the other hand, preallocates TLS
555 memory on `pthread_create` and `dlopen`, so either function can return out-of-memory. Both functions
567 > up the process. It would be a waste of memory and time to allocate the storage for all threads. A
573 FWIW: emutls also aborts on out-of-memory.
589 2 allocates everything before the TP. Bionic currently allocates memory before and after the TP to
607 There are issues with rearranging this memory:
642    `pthread_internal_t` fields) become host accesses. Laying out TLS memory differently across
762  * memory layout is the same on all architectures, avoids native bridge complications
772  * Bionic's existing memory layout doesn't change, and arm32 and 32-bit x86 have the same layout
785 the existing thread-specific memory layout untouched.
826 `/system/bin/app_process{32,64}` limits its use of TLS memory, then the pthread keys could be
830 keys (2 words per key), then `app_process` can use at most 108 words of TLS memory.
845 XXX: Maybe a sanitizer would want to intercept allocations of TLS memory, and that could be hard if