tcg: cpu-exec: remove tb_lock from the hot-path

Lock contention in the hot path of moving between existing patched
TranslationBlocks is the main drag in multithreaded performance. This
patch pushes the tb_lock() usage down to the two places that really need
it:

- code generation (tb_gen_code)
- jump patching (tb_add_jump)

The rest of the code doesn't really need to hold a lock as it is either
using per-CPU structures, atomically updated or designed to be used in
concurrent read situations (qht_lookup).

To keep things simple I removed the #ifdef CONFIG_USER_ONLY stuff as the
locks become NOPs anyway until the MTTCG work is completed.

Backports commit 518615c6503ad78d3bb67ddf1cd848c4a41de02e from qemu
This commit is contained in:
Alex Bennée 2018-02-26 01:58:27 -05:00 committed by Lioncash
parent 62aa0abd02
commit 09c3ef656e
No known key found for this signature in database
GPG Key ID: 4E3C3CC1031BA9C7

View File

@ -145,36 +145,29 @@ static TranslationBlock *tb_find_slow(CPUState *cpu,
TranslationBlock *tb;
tb = tb_find_physical(cpu, pc, cs_base, flags);
if (tb) {
goto found;
}
if (!tb) {
/* mmap_lock is needed by tb_gen_code, and mmap_lock must be
* taken outside tb_lock. As system emulation is currently
* single threaded the locks are NOPs.
*/
mmap_lock();
// Unicorn: commented out
//tb_lock();
#ifdef CONFIG_USER_ONLY
/* mmap_lock is needed by tb_gen_code, and mmap_lock must be
* taken outside tb_lock. Since we're momentarily dropping
* tb_lock, there's a chance that our desired tb has been
* translated.
*/
// Unicorn: commented out
//tb_unlock();
mmap_lock();
//tb_lock();
tb = tb_find_physical(cpu, pc, cs_base, flags);
if (tb) {
/* There's a chance that our desired tb has been translated while
* taking the locks so we check again inside the lock.
*/
tb = tb_find_physical(cpu, pc, cs_base, flags);
if (!tb) {
/* if no translated code available, then translate it now */
tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
}
// Unicorn: commented out
//tb_unlock();
mmap_unlock();
goto found;
}
#endif
/* if no translated code available, then translate it now */
tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
#ifdef CONFIG_USER_ONLY
mmap_unlock();
#endif
found:
/* we add the TB in the virtual pc hash table */
/* We add the TB in the virtual pc hash table for the fast lookup */
atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb);
return tb;
}
@ -192,8 +185,6 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
always be the same before a given translated block
is executed. */
cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
// Unicorn: commented out
//tb_lock();
// Unicorn: atomic_read used instead of atomic_rcu_read
tb = atomic_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]);
if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
@ -211,15 +202,17 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
#endif
/* See if we can patch the calling TB. */
if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
// Unicorn: commented out
//tb_lock();
/* Check if translation buffer has been flushed */
if (cpu->tb_flushed) {
cpu->tb_flushed = false;
} else if (!tb->invalid) {
tb_add_jump(last_tb, tb_exit, tb);
}
// Unicorn: commented out
//tb_unlock();
}
// Unicorn: commented out
//tb_unlock();
return tb;
}