#include "sysemu/qtest.h"
#include "qemu/timer.h"
#include "exec/address-spaces.h"
-#include "exec/memory-internal.h"
+#include "qemu/rcu.h"
+#include "exec/tb-hash.h"
/* -icount align implementation. */
}
#endif /* CONFIG USER ONLY */
-void cpu_loop_exit(CPUState *cpu)
-{
- cpu->current_tb = NULL;
- siglongjmp(cpu->jmp_env, 1);
-}
-
-/* exit the current TB from a signal handler. The host registers are
- restored in a state compatible with the CPU emulator
- */
-#if defined(CONFIG_SOFTMMU)
-void cpu_resume_from_signal(CPUState *cpu, void *puc)
-{
- /* XXX: restore cpu registers saved in host registers */
-
- cpu->exception_index = -1;
- siglongjmp(cpu->jmp_env, 1);
-}
-
-void cpu_reload_memory_map(CPUState *cpu)
-{
- /* The CPU and TLB are protected by the iothread lock. */
- AddressSpaceDispatch *d = cpu->as->dispatch;
- cpu->memory_dispatch = d;
- tlb_flush(cpu, 1);
-}
-#endif
-
/* Execute a TB, and fix up the CPU state afterwards if necessary */
static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, uint8_t *tb_ptr)
{
}
#endif /* DEBUG_DISAS */
- cpu->can_do_io = 0;
+ cpu->can_do_io = !use_icount;
next_tb = tcg_qemu_tb_exec(env, tb_ptr);
cpu->can_do_io = 1;
trace_exec_tb_exit((void *) (next_tb & ~TB_EXIT_MASK),
/* Execute the code without caching the generated code. An interpreter
could be used if available. */
-static void cpu_exec_nocache(CPUArchState *env, int max_cycles,
+static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
TranslationBlock *orig_tb)
{
- CPUState *cpu = ENV_GET_CPU(env);
TranslationBlock *tb;
- target_ulong pc = orig_tb->pc;
- target_ulong cs_base = orig_tb->cs_base;
- uint64_t flags = orig_tb->flags;
/* Should never happen.
We only end up here when an existing TB is too long. */
if (max_cycles > CF_COUNT_MASK)
max_cycles = CF_COUNT_MASK;
- /* tb_gen_code can flush our orig_tb, invalidate it now */
- tb_phys_invalidate(orig_tb, -1);
- tb = tb_gen_code(cpu, pc, cs_base, flags,
+ tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
max_cycles | CF_NOCACHE);
+ tb->orig_tb = tcg_ctx.tb_ctx.tb_invalidated_flag ? NULL : orig_tb;
cpu->current_tb = tb;
/* execute the generated code */
trace_exec_tb_nocache(tb, tb->pc);
tb_free(tb);
}
-static TranslationBlock *tb_find_slow(CPUArchState *env,
- target_ulong pc,
- target_ulong cs_base,
- uint64_t flags)
+static TranslationBlock *tb_find_physical(CPUState *cpu,
+ target_ulong pc,
+ target_ulong cs_base,
+ uint64_t flags)
{
- CPUState *cpu = ENV_GET_CPU(env);
+ CPUArchState *env = (CPUArchState *)cpu->env_ptr;
TranslationBlock *tb, **ptb1;
unsigned int h;
tb_page_addr_t phys_pc, phys_page1;
ptb1 = &tcg_ctx.tb_ctx.tb_phys_hash[h];
for(;;) {
tb = *ptb1;
- if (!tb)
- goto not_found;
+ if (!tb) {
+ return NULL;
+ }
if (tb->pc == pc &&
tb->page_addr[0] == phys_page1 &&
tb->cs_base == cs_base &&
virt_page2 = (pc & TARGET_PAGE_MASK) +
TARGET_PAGE_SIZE;
phys_page2 = get_page_addr_code(env, virt_page2);
- if (tb->page_addr[1] == phys_page2)
- goto found;
+ if (tb->page_addr[1] == phys_page2) {
+ break;
+ }
} else {
- goto found;
+ break;
}
}
ptb1 = &tb->phys_hash_next;
}
- not_found:
- /* if no translated code available, then translate it now */
- tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
- found:
- /* Move the last found TB to the head of the list */
- if (likely(*ptb1)) {
- *ptb1 = tb->phys_hash_next;
- tb->phys_hash_next = tcg_ctx.tb_ctx.tb_phys_hash[h];
- tcg_ctx.tb_ctx.tb_phys_hash[h] = tb;
+ /* Move the TB to the head of the list */
+ *ptb1 = tb->phys_hash_next;
+ tb->phys_hash_next = tcg_ctx.tb_ctx.tb_phys_hash[h];
+ tcg_ctx.tb_ctx.tb_phys_hash[h] = tb;
+ return tb;
+}
+
+static TranslationBlock *tb_find_slow(CPUState *cpu,
+ target_ulong pc,
+ target_ulong cs_base,
+ uint64_t flags)
+{
+ TranslationBlock *tb;
+
+ tb = tb_find_physical(cpu, pc, cs_base, flags);
+ if (tb) {
+ goto found;
}
+
+#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.
+ */
+ tb_unlock();
+ mmap_lock();
+ tb_lock();
+ tb = tb_find_physical(cpu, pc, cs_base, flags);
+ if (tb) {
+ 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 */
cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)] = tb;
return tb;
}
-static inline TranslationBlock *tb_find_fast(CPUArchState *env)
+static inline TranslationBlock *tb_find_fast(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
+ CPUArchState *env = (CPUArchState *)cpu->env_ptr;
TranslationBlock *tb;
target_ulong cs_base, pc;
int flags;
tb = cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)];
if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
tb->flags != flags)) {
- tb = tb_find_slow(env, pc, cs_base, flags);
+ tb = tb_find_slow(cpu, pc, cs_base, flags);
}
return tb;
}
-static void cpu_handle_debug_exception(CPUArchState *env)
+static void cpu_handle_debug_exception(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
CPUClass *cc = CPU_GET_CLASS(cpu);
CPUWatchpoint *wp;
/* main execution loop */
-volatile sig_atomic_t exit_request;
-
-int cpu_exec(CPUArchState *env)
+int cpu_exec(CPUState *cpu)
{
- CPUState *cpu = ENV_GET_CPU(env);
CPUClass *cc = CPU_GET_CLASS(cpu);
#ifdef TARGET_I386
X86CPU *x86_cpu = X86_CPU(cpu);
+ CPUArchState *env = &x86_cpu->env;
#endif
int ret, interrupt_request;
TranslationBlock *tb;
uintptr_t next_tb;
SyncClocks sc;
- /* This must be volatile so it is not trashed by longjmp() */
- volatile bool have_tb_lock = false;
-
if (cpu->halted) {
if (!cpu_has_work(cpu)) {
return EXCP_HALTED;
}
current_cpu = cpu;
+ atomic_mb_set(&tcg_current_cpu, cpu);
+ rcu_read_lock();
- /* As long as current_cpu is null, up to the assignment just above,
- * requests by other threads to exit the execution loop are expected to
- * be issued using the exit_request global. We must make sure that our
- * evaluation of the global value is performed past the current_cpu
- * value transition point, which requires a memory barrier as well as
- * an instruction scheduling constraint on modern architectures. */
- smp_mb();
-
- if (unlikely(exit_request)) {
+ if (unlikely(atomic_mb_read(&exit_request))) {
cpu->exit_request = 1;
}
/* exit request from the cpu execution loop */
ret = cpu->exception_index;
if (ret == EXCP_DEBUG) {
- cpu_handle_debug_exception(env);
+ cpu_handle_debug_exception(cpu);
}
cpu->exception_index = -1;
break;
cpu->exception_index = EXCP_INTERRUPT;
cpu_loop_exit(cpu);
}
- spin_lock(&tcg_ctx.tb_ctx.tb_lock);
- have_tb_lock = true;
- tb = tb_find_fast(env);
+ tb_lock();
+ tb = tb_find_fast(cpu);
/* Note: we do it here to avoid a gcc bug on Mac OS X when
doing it in tb_find_slow */
if (tcg_ctx.tb_ctx.tb_invalidated_flag) {
tb_add_jump((TranslationBlock *)(next_tb & ~TB_EXIT_MASK),
next_tb & TB_EXIT_MASK, tb);
}
- have_tb_lock = false;
- spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
-
- /* cpu_interrupt might be called while translating the
- TB, but before it is linked into a potentially
- infinite loop and becomes env->current_tb. Avoid
- starting execution if there is a pending interrupt. */
- cpu->current_tb = tb;
- barrier();
+ tb_unlock();
if (likely(!cpu->exit_request)) {
trace_exec_tb(tb, tb->pc);
tc_ptr = tb->tc_ptr;
/* execute the generated code */
+ cpu->current_tb = tb;
next_tb = cpu_tb_exec(cpu, tc_ptr);
+ cpu->current_tb = NULL;
switch (next_tb & TB_EXIT_MASK) {
case TB_EXIT_REQUESTED:
/* Something asked us to stop executing
* loop. Whatever requested the exit will also
* have set something else (eg exit_request or
* interrupt_request) which we will handle
- * next time around the loop.
+ * next time around the loop. But we need to
+ * ensure the tcg_exit_req read in generated code
+ * comes before the next read of cpu->exit_request
+ * or cpu->interrupt_request.
*/
- tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
+ smp_rmb();
next_tb = 0;
break;
case TB_EXIT_ICOUNT_EXPIRED:
{
/* Instruction counter expired. */
- int insns_left;
- tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
- insns_left = cpu->icount_decr.u32;
+ int insns_left = cpu->icount_decr.u32;
if (cpu->icount_extra && insns_left >= 0) {
/* Refill decrementer and continue execution. */
cpu->icount_extra += insns_left;
- if (cpu->icount_extra > 0xffff) {
- insns_left = 0xffff;
- } else {
- insns_left = cpu->icount_extra;
- }
+ insns_left = MIN(0xffff, cpu->icount_extra);
cpu->icount_extra -= insns_left;
cpu->icount_decr.u16.low = insns_left;
} else {
if (insns_left > 0) {
/* Execute remaining instructions. */
- cpu_exec_nocache(env, insns_left, tb);
+ tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
+ cpu_exec_nocache(cpu, insns_left, tb);
align_clocks(&sc, cpu);
}
cpu->exception_index = EXCP_INTERRUPT;
break;
}
}
- cpu->current_tb = NULL;
/* Try to align the host and virtual clocks
if the guest is in advance */
align_clocks(&sc, cpu);
/* Reload env after longjmp - the compiler may have smashed all
* local variables as longjmp is marked 'noreturn'. */
cpu = current_cpu;
- env = cpu->env_ptr;
cc = CPU_GET_CLASS(cpu);
cpu->can_do_io = 1;
#ifdef TARGET_I386
x86_cpu = X86_CPU(cpu);
+ env = &x86_cpu->env;
#endif
- if (have_tb_lock) {
- spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
- have_tb_lock = false;
- }
+ tb_lock_reset();
}
} /* for(;;) */
cc->cpu_exec_exit(cpu);
+ rcu_read_unlock();
/* fail safe : never use current_cpu outside cpu_exec() */
current_cpu = NULL;
+
+ /* Does not need atomic_mb_set because a spurious wakeup is okay. */
+ atomic_set(&tcg_current_cpu, NULL);
return ret;
}
projects / mirror_qemu.git / blobdiff