@@ -237,10 +237,7 @@ void cpu_exec_step_atomic(CPUState *cpu)
if (tb == NULL) {
mmap_lock();
tb_lock();
- tb = tb_htable_lookup(cpu, pc, cs_base, flags, cf_mask);
- if (likely(tb == NULL)) {
- tb = tb_gen_code(cpu, pc, cs_base, flags, cflags);
- }
+ tb = tb_gen_code(cpu, pc, cs_base, flags, cflags);
tb_unlock();
mmap_unlock();
}
@@ -348,14 +345,7 @@ static inline TranslationBlock *tb_find(CPUState *cpu,
tb_lock();
acquired_tb_lock = true;
- /* There's a chance that our desired tb has been translated while
- * taking the locks so we check again inside the lock.
- */
- tb = tb_htable_lookup(cpu, pc, cs_base, flags, cf_mask);
- if (likely(tb == NULL)) {
- /* if no translated code available, then translate it now */
- tb = tb_gen_code(cpu, pc, cs_base, flags, cf_mask);
- }
+ tb = tb_gen_code(cpu, pc, cs_base, flags, cf_mask);
mmap_unlock();
/* We add the TB in the virtual pc hash table for the fast lookup */
@@ -1490,12 +1490,16 @@ static inline void tb_page_add(PageDesc *p, TranslationBlock *tb,
* (-1) to indicate that only one page contains the TB.
*
* Called with mmap_lock held for user-mode emulation.
+ *
+ * Returns @tb or an existing TB that matches @tb.
*/
-static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
- tb_page_addr_t phys_page2)
+static TranslationBlock *
+tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
+ tb_page_addr_t phys_page2)
{
PageDesc *p;
PageDesc *p2 = NULL;
+ void *existing_tb;
uint32_t h;
assert_memory_lock();
@@ -1503,6 +1507,11 @@ static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
/*
* Add the TB to the page list.
* To avoid deadlock, acquire first the lock of the lower-addressed page.
+ * We keep the locks held until after inserting the TB in the hash table,
+ * so that if the insertion fails we know for sure that the TBs are still
+ * in the page descriptors.
+ * Note that inserting into the hash table first isn't an option, since
+ * we can only insert TBs that are fully initialized.
*/
p = page_find_alloc(phys_pc >> TARGET_PAGE_BITS, 1);
if (likely(phys_page2 == -1)) {
@@ -1522,21 +1531,33 @@ static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
tb_page_add(p2, tb, 1, phys_page2);
}
+ /* add in the hash table */
+ h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MASK,
+ tb->trace_vcpu_dstate);
+ existing_tb = qht_insert(&tb_ctx.htable, tb, h);
+
+ /* remove TB from the page(s) if we couldn't insert it */
+ if (existing_tb) {
+ tb_page_remove(p, tb);
+ invalidate_page_bitmap(p);
+ if (p2) {
+ tb_page_remove(p2, tb);
+ invalidate_page_bitmap(p2);
+ }
+ tb = existing_tb;
+ }
+
if (p2) {
page_unlock(p2);
}
page_unlock(p);
- /* add in the hash table */
- h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MASK,
- tb->trace_vcpu_dstate);
- qht_insert(&tb_ctx.htable, tb, h);
-
#ifdef CONFIG_USER_ONLY
if (DEBUG_TB_CHECK_GATE) {
tb_page_check();
}
#endif
+ return tb;
}
/* Called with mmap_lock held for user mode emulation. */
@@ -1545,7 +1566,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
uint32_t flags, int cflags)
{
CPUArchState *env = cpu->env_ptr;
- TranslationBlock *tb;
+ TranslationBlock *tb, *existing_tb;
tb_page_addr_t phys_pc, phys_page2;
target_ulong virt_page2;
tcg_insn_unit *gen_code_buf;
@@ -1676,7 +1697,15 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
* memory barrier is required before tb_link_page() makes the TB visible
* through the physical hash table and physical page list.
*/
- tb_link_page(tb, phys_pc, phys_page2);
+ existing_tb = tb_link_page(tb, phys_pc, phys_page2);
+ /* if the TB already exists, discard what we just translated */
+ if (unlikely(existing_tb != tb)) {
+ uintptr_t orig_aligned = (uintptr_t)gen_code_buf;
+
+ orig_aligned -= ROUND_UP(sizeof(*tb), qemu_icache_linesize);
+ atomic_set(&tcg_ctx->code_gen_ptr, orig_aligned);
+ return existing_tb;
+ }
tcg_tb_insert(tb);
return tb;
}
Use the recently-gained QHT feature of returning the matching TB if it already exists. This allows us to get rid of the lookup we perform right after acquiring tb_lock. Suggested-by: Richard Henderson <rth@twiddle.net> Signed-off-by: Emilio G. Cota <cota@braap.org> --- accel/tcg/cpu-exec.c | 14 ++------------ accel/tcg/translate-all.c | 47 ++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 40 insertions(+), 21 deletions(-)