qemu-e2k/accel/tcg/cpu-exec.c
Emilio G. Cota f6bb84d531 tcg: consolidate TB lookups in tb_lookup__cpu_state
This avoids duplicating code. cpu_exec_step will also use the
new common function once we integrate parallel_cpus into tb->cflags.

Note that in this commit we also fix a race, described by Richard Henderson
during review. Think of this scenario with threads A and B:

   (A) Lookup succeeds for TB in hash without tb_lock
        (B) Sets the TB's tb->invalid flag
        (B) Removes the TB from tb_htable
        (B) Clears all CPU's tb_jmp_cache
   (A) Store TB into local tb_jmp_cache

Given that order of events, (A) will keep executing that invalid TB until
another flush of its tb_jmp_cache happens, which in theory might never happen.
We can fix this by checking the tb->invalid flag every time we look up a TB
from tb_jmp_cache, so that in the above scenario, next time we try to find
that TB in tb_jmp_cache, we won't, and will therefore be forced to look it
up in tb_htable.

Performance-wise, I measured a small improvement when booting debian-arm.
Note that inlining pays off:

 Performance counter stats for 'taskset -c 0 qemu-system-arm \
	-machine type=virt -nographic -smp 1 -m 4096 \
	-netdev user,id=unet,hostfwd=tcp::2222-:22 \
	-device virtio-net-device,netdev=unet \
	-drive file=jessie.qcow2,id=myblock,index=0,if=none \
	-device virtio-blk-device,drive=myblock \
	-kernel kernel.img -append console=ttyAMA0 root=/dev/vda1 \
	-name arm,debug-threads=on -smp 1' (10 runs):

Before:
      18714.917392 task-clock                #    0.952 CPUs utilized            ( +-  0.95% )
            23,142 context-switches          #    0.001 M/sec                    ( +-  0.50% )
                 1 CPU-migrations            #    0.000 M/sec
            10,558 page-faults               #    0.001 M/sec                    ( +-  0.95% )
    53,957,727,252 cycles                    #    2.883 GHz                      ( +-  0.91% ) [83.33%]
    24,440,599,852 stalled-cycles-frontend   #   45.30% frontend cycles idle     ( +-  1.20% ) [83.33%]
    16,495,714,424 stalled-cycles-backend    #   30.57% backend  cycles idle     ( +-  0.95% ) [66.66%]
    76,267,572,582 instructions              #    1.41  insns per cycle
                                             #    0.32  stalled cycles per insn  ( +-  0.87% ) [83.34%]
    12,692,186,323 branches                  #  678.186 M/sec                    ( +-  0.92% ) [83.35%]
       263,486,879 branch-misses             #    2.08% of all branches          ( +-  0.73% ) [83.34%]

      19.648474449 seconds time elapsed                                          ( +-  0.82% )

After, w/ inline (this patch):
      18471.376627 task-clock                #    0.955 CPUs utilized            ( +-  0.96% )
            23,048 context-switches          #    0.001 M/sec                    ( +-  0.48% )
                 1 CPU-migrations            #    0.000 M/sec
            10,708 page-faults               #    0.001 M/sec                    ( +-  0.81% )
    53,208,990,796 cycles                    #    2.881 GHz                      ( +-  0.98% ) [83.34%]
    23,941,071,673 stalled-cycles-frontend   #   44.99% frontend cycles idle     ( +-  0.95% ) [83.34%]
    16,161,773,848 stalled-cycles-backend    #   30.37% backend  cycles idle     ( +-  0.76% ) [66.67%]
    75,786,269,766 instructions              #    1.42  insns per cycle
                                             #    0.32  stalled cycles per insn  ( +-  1.24% ) [83.34%]
    12,573,617,143 branches                  #  680.708 M/sec                    ( +-  1.34% ) [83.33%]
       260,235,550 branch-misses             #    2.07% of all branches          ( +-  0.66% ) [83.33%]

      19.340502161 seconds time elapsed                                          ( +-  0.56% )

After, w/o inline:
      18791.253967 task-clock                #    0.954 CPUs utilized            ( +-  0.78% )
            23,230 context-switches          #    0.001 M/sec                    ( +-  0.42% )
                 1 CPU-migrations            #    0.000 M/sec
            10,563 page-faults               #    0.001 M/sec                    ( +-  1.27% )
    54,168,674,622 cycles                    #    2.883 GHz                      ( +-  0.80% ) [83.34%]
    24,244,712,629 stalled-cycles-frontend   #   44.76% frontend cycles idle     ( +-  1.37% ) [83.33%]
    16,288,648,572 stalled-cycles-backend    #   30.07% backend  cycles idle     ( +-  0.95% ) [66.66%]
    77,659,755,503 instructions              #    1.43  insns per cycle
                                             #    0.31  stalled cycles per insn  ( +-  0.97% ) [83.34%]
    12,922,780,045 branches                  #  687.702 M/sec                    ( +-  1.06% ) [83.34%]
       261,962,386 branch-misses             #    2.03% of all branches          ( +-  0.71% ) [83.35%]

      19.700174670 seconds time elapsed                                          ( +-  0.56% )

Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
2017-10-10 07:37:10 -07:00

712 lines
22 KiB
C

/*
* emulator main execution loop
*
* Copyright (c) 2003-2005 Fabrice Bellard
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "cpu.h"
#include "trace.h"
#include "disas/disas.h"
#include "exec/exec-all.h"
#include "tcg.h"
#include "qemu/atomic.h"
#include "sysemu/qtest.h"
#include "qemu/timer.h"
#include "exec/address-spaces.h"
#include "qemu/rcu.h"
#include "exec/tb-hash.h"
#include "exec/tb-lookup.h"
#include "exec/log.h"
#include "qemu/main-loop.h"
#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
#include "hw/i386/apic.h"
#endif
#include "sysemu/cpus.h"
#include "sysemu/replay.h"
/* -icount align implementation. */
typedef struct SyncClocks {
int64_t diff_clk;
int64_t last_cpu_icount;
int64_t realtime_clock;
} SyncClocks;
#if !defined(CONFIG_USER_ONLY)
/* Allow the guest to have a max 3ms advance.
* The difference between the 2 clocks could therefore
* oscillate around 0.
*/
#define VM_CLOCK_ADVANCE 3000000
#define THRESHOLD_REDUCE 1.5
#define MAX_DELAY_PRINT_RATE 2000000000LL
#define MAX_NB_PRINTS 100
static void align_clocks(SyncClocks *sc, const CPUState *cpu)
{
int64_t cpu_icount;
if (!icount_align_option) {
return;
}
cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
sc->diff_clk += cpu_icount_to_ns(sc->last_cpu_icount - cpu_icount);
sc->last_cpu_icount = cpu_icount;
if (sc->diff_clk > VM_CLOCK_ADVANCE) {
#ifndef _WIN32
struct timespec sleep_delay, rem_delay;
sleep_delay.tv_sec = sc->diff_clk / 1000000000LL;
sleep_delay.tv_nsec = sc->diff_clk % 1000000000LL;
if (nanosleep(&sleep_delay, &rem_delay) < 0) {
sc->diff_clk = rem_delay.tv_sec * 1000000000LL + rem_delay.tv_nsec;
} else {
sc->diff_clk = 0;
}
#else
Sleep(sc->diff_clk / SCALE_MS);
sc->diff_clk = 0;
#endif
}
}
static void print_delay(const SyncClocks *sc)
{
static float threshold_delay;
static int64_t last_realtime_clock;
static int nb_prints;
if (icount_align_option &&
sc->realtime_clock - last_realtime_clock >= MAX_DELAY_PRINT_RATE &&
nb_prints < MAX_NB_PRINTS) {
if ((-sc->diff_clk / (float)1000000000LL > threshold_delay) ||
(-sc->diff_clk / (float)1000000000LL <
(threshold_delay - THRESHOLD_REDUCE))) {
threshold_delay = (-sc->diff_clk / 1000000000LL) + 1;
printf("Warning: The guest is now late by %.1f to %.1f seconds\n",
threshold_delay - 1,
threshold_delay);
nb_prints++;
last_realtime_clock = sc->realtime_clock;
}
}
}
static void init_delay_params(SyncClocks *sc,
const CPUState *cpu)
{
if (!icount_align_option) {
return;
}
sc->realtime_clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
sc->diff_clk = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - sc->realtime_clock;
sc->last_cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
if (sc->diff_clk < max_delay) {
max_delay = sc->diff_clk;
}
if (sc->diff_clk > max_advance) {
max_advance = sc->diff_clk;
}
/* Print every 2s max if the guest is late. We limit the number
of printed messages to NB_PRINT_MAX(currently 100) */
print_delay(sc);
}
#else
static void align_clocks(SyncClocks *sc, const CPUState *cpu)
{
}
static void init_delay_params(SyncClocks *sc, const CPUState *cpu)
{
}
#endif /* CONFIG USER ONLY */
/* Execute a TB, and fix up the CPU state afterwards if necessary */
static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
{
CPUArchState *env = cpu->env_ptr;
uintptr_t ret;
TranslationBlock *last_tb;
int tb_exit;
uint8_t *tb_ptr = itb->tc_ptr;
qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc,
"Trace %p [%d: " TARGET_FMT_lx "] %s\n",
itb->tc_ptr, cpu->cpu_index, itb->pc,
lookup_symbol(itb->pc));
#if defined(DEBUG_DISAS)
if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
&& qemu_log_in_addr_range(itb->pc)) {
qemu_log_lock();
#if defined(TARGET_I386)
log_cpu_state(cpu, CPU_DUMP_CCOP);
#else
log_cpu_state(cpu, 0);
#endif
qemu_log_unlock();
}
#endif /* DEBUG_DISAS */
cpu->can_do_io = !use_icount;
ret = tcg_qemu_tb_exec(env, tb_ptr);
cpu->can_do_io = 1;
last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
tb_exit = ret & TB_EXIT_MASK;
trace_exec_tb_exit(last_tb, tb_exit);
if (tb_exit > TB_EXIT_IDX1) {
/* We didn't start executing this TB (eg because the instruction
* counter hit zero); we must restore the guest PC to the address
* of the start of the TB.
*/
CPUClass *cc = CPU_GET_CLASS(cpu);
qemu_log_mask_and_addr(CPU_LOG_EXEC, last_tb->pc,
"Stopped execution of TB chain before %p ["
TARGET_FMT_lx "] %s\n",
last_tb->tc_ptr, last_tb->pc,
lookup_symbol(last_tb->pc));
if (cc->synchronize_from_tb) {
cc->synchronize_from_tb(cpu, last_tb);
} else {
assert(cc->set_pc);
cc->set_pc(cpu, last_tb->pc);
}
}
return ret;
}
#ifndef CONFIG_USER_ONLY
/* Execute the code without caching the generated code. An interpreter
could be used if available. */
static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
TranslationBlock *orig_tb, bool ignore_icount)
{
TranslationBlock *tb;
/* 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_lock();
tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
max_cycles | CF_NOCACHE
| (ignore_icount ? CF_IGNORE_ICOUNT : 0));
tb->orig_tb = orig_tb;
tb_unlock();
/* execute the generated code */
trace_exec_tb_nocache(tb, tb->pc);
cpu_tb_exec(cpu, tb);
tb_lock();
tb_phys_invalidate(tb, -1);
tb_free(tb);
tb_unlock();
}
#endif
static void cpu_exec_step(CPUState *cpu)
{
CPUClass *cc = CPU_GET_CLASS(cpu);
CPUArchState *env = (CPUArchState *)cpu->env_ptr;
TranslationBlock *tb;
target_ulong cs_base, pc;
uint32_t flags;
cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
if (sigsetjmp(cpu->jmp_env, 0) == 0) {
mmap_lock();
tb_lock();
tb = tb_gen_code(cpu, pc, cs_base, flags,
1 | CF_NOCACHE | CF_IGNORE_ICOUNT);
tb->orig_tb = NULL;
tb_unlock();
mmap_unlock();
cc->cpu_exec_enter(cpu);
/* execute the generated code */
trace_exec_tb_nocache(tb, pc);
cpu_tb_exec(cpu, tb);
cc->cpu_exec_exit(cpu);
tb_lock();
tb_phys_invalidate(tb, -1);
tb_free(tb);
tb_unlock();
} else {
/* We may have exited due to another problem here, so we need
* to reset any tb_locks we may have taken but didn't release.
* The mmap_lock is dropped by tb_gen_code if it runs out of
* memory.
*/
#ifndef CONFIG_SOFTMMU
tcg_debug_assert(!have_mmap_lock());
#endif
tb_lock_reset();
}
}
void cpu_exec_step_atomic(CPUState *cpu)
{
start_exclusive();
/* Since we got here, we know that parallel_cpus must be true. */
parallel_cpus = false;
cpu_exec_step(cpu);
parallel_cpus = true;
end_exclusive();
}
struct tb_desc {
target_ulong pc;
target_ulong cs_base;
CPUArchState *env;
tb_page_addr_t phys_page1;
uint32_t flags;
uint32_t trace_vcpu_dstate;
};
static bool tb_cmp(const void *p, const void *d)
{
const TranslationBlock *tb = p;
const struct tb_desc *desc = d;
if (tb->pc == desc->pc &&
tb->page_addr[0] == desc->phys_page1 &&
tb->cs_base == desc->cs_base &&
tb->flags == desc->flags &&
tb->trace_vcpu_dstate == desc->trace_vcpu_dstate &&
!atomic_read(&tb->invalid)) {
/* check next page if needed */
if (tb->page_addr[1] == -1) {
return true;
} else {
tb_page_addr_t phys_page2;
target_ulong virt_page2;
virt_page2 = (desc->pc & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
phys_page2 = get_page_addr_code(desc->env, virt_page2);
if (tb->page_addr[1] == phys_page2) {
return true;
}
}
}
return false;
}
TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
target_ulong cs_base, uint32_t flags)
{
tb_page_addr_t phys_pc;
struct tb_desc desc;
uint32_t h;
desc.env = (CPUArchState *)cpu->env_ptr;
desc.cs_base = cs_base;
desc.flags = flags;
desc.trace_vcpu_dstate = *cpu->trace_dstate;
desc.pc = pc;
phys_pc = get_page_addr_code(desc.env, pc);
desc.phys_page1 = phys_pc & TARGET_PAGE_MASK;
h = tb_hash_func(phys_pc, pc, flags, *cpu->trace_dstate);
return qht_lookup(&tcg_ctx.tb_ctx.htable, tb_cmp, &desc, h);
}
void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)
{
if (TCG_TARGET_HAS_direct_jump) {
uintptr_t offset = tb->jmp_target_arg[n];
uintptr_t tc_ptr = (uintptr_t)tb->tc_ptr;
tb_target_set_jmp_target(tc_ptr, tc_ptr + offset, addr);
} else {
tb->jmp_target_arg[n] = addr;
}
}
/* Called with tb_lock held. */
static inline void tb_add_jump(TranslationBlock *tb, int n,
TranslationBlock *tb_next)
{
assert(n < ARRAY_SIZE(tb->jmp_list_next));
if (tb->jmp_list_next[n]) {
/* Another thread has already done this while we were
* outside of the lock; nothing to do in this case */
return;
}
qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc,
"Linking TBs %p [" TARGET_FMT_lx
"] index %d -> %p [" TARGET_FMT_lx "]\n",
tb->tc_ptr, tb->pc, n,
tb_next->tc_ptr, tb_next->pc);
/* patch the native jump address */
tb_set_jmp_target(tb, n, (uintptr_t)tb_next->tc_ptr);
/* add in TB jmp circular list */
tb->jmp_list_next[n] = tb_next->jmp_list_first;
tb_next->jmp_list_first = (uintptr_t)tb | n;
}
static inline TranslationBlock *tb_find(CPUState *cpu,
TranslationBlock *last_tb,
int tb_exit)
{
TranslationBlock *tb;
target_ulong cs_base, pc;
uint32_t flags;
bool acquired_tb_lock = false;
tb = tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags);
if (tb == NULL) {
/* 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();
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);
if (likely(tb == NULL)) {
/* if no translated code available, then translate it now */
tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
}
mmap_unlock();
/* 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);
}
#ifndef CONFIG_USER_ONLY
/* We don't take care of direct jumps when address mapping changes in
* system emulation. So it's not safe to make a direct jump to a TB
* spanning two pages because the mapping for the second page can change.
*/
if (tb->page_addr[1] != -1) {
last_tb = NULL;
}
#endif
/* See if we can patch the calling TB. */
if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
if (!acquired_tb_lock) {
tb_lock();
acquired_tb_lock = true;
}
if (!tb->invalid) {
tb_add_jump(last_tb, tb_exit, tb);
}
}
if (acquired_tb_lock) {
tb_unlock();
}
return tb;
}
static inline bool cpu_handle_halt(CPUState *cpu)
{
if (cpu->halted) {
#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
if ((cpu->interrupt_request & CPU_INTERRUPT_POLL)
&& replay_interrupt()) {
X86CPU *x86_cpu = X86_CPU(cpu);
qemu_mutex_lock_iothread();
apic_poll_irq(x86_cpu->apic_state);
cpu_reset_interrupt(cpu, CPU_INTERRUPT_POLL);
qemu_mutex_unlock_iothread();
}
#endif
if (!cpu_has_work(cpu)) {
return true;
}
cpu->halted = 0;
}
return false;
}
static inline void cpu_handle_debug_exception(CPUState *cpu)
{
CPUClass *cc = CPU_GET_CLASS(cpu);
CPUWatchpoint *wp;
if (!cpu->watchpoint_hit) {
QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
wp->flags &= ~BP_WATCHPOINT_HIT;
}
}
cc->debug_excp_handler(cpu);
}
static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
{
if (cpu->exception_index >= 0) {
if (cpu->exception_index >= EXCP_INTERRUPT) {
/* exit request from the cpu execution loop */
*ret = cpu->exception_index;
if (*ret == EXCP_DEBUG) {
cpu_handle_debug_exception(cpu);
}
cpu->exception_index = -1;
return true;
} else {
#if defined(CONFIG_USER_ONLY)
/* if user mode only, we simulate a fake exception
which will be handled outside the cpu execution
loop */
#if defined(TARGET_I386)
CPUClass *cc = CPU_GET_CLASS(cpu);
cc->do_interrupt(cpu);
#endif
*ret = cpu->exception_index;
cpu->exception_index = -1;
return true;
#else
if (replay_exception()) {
CPUClass *cc = CPU_GET_CLASS(cpu);
qemu_mutex_lock_iothread();
cc->do_interrupt(cpu);
qemu_mutex_unlock_iothread();
cpu->exception_index = -1;
} else if (!replay_has_interrupt()) {
/* give a chance to iothread in replay mode */
*ret = EXCP_INTERRUPT;
return true;
}
#endif
}
#ifndef CONFIG_USER_ONLY
} else if (replay_has_exception()
&& cpu->icount_decr.u16.low + cpu->icount_extra == 0) {
/* try to cause an exception pending in the log */
cpu_exec_nocache(cpu, 1, tb_find(cpu, NULL, 0), true);
*ret = -1;
return true;
#endif
}
return false;
}
static inline bool cpu_handle_interrupt(CPUState *cpu,
TranslationBlock **last_tb)
{
CPUClass *cc = CPU_GET_CLASS(cpu);
if (unlikely(atomic_read(&cpu->interrupt_request))) {
int interrupt_request;
qemu_mutex_lock_iothread();
interrupt_request = cpu->interrupt_request;
if (unlikely(cpu->singlestep_enabled & SSTEP_NOIRQ)) {
/* Mask out external interrupts for this step. */
interrupt_request &= ~CPU_INTERRUPT_SSTEP_MASK;
}
if (interrupt_request & CPU_INTERRUPT_DEBUG) {
cpu->interrupt_request &= ~CPU_INTERRUPT_DEBUG;
cpu->exception_index = EXCP_DEBUG;
qemu_mutex_unlock_iothread();
return true;
}
if (replay_mode == REPLAY_MODE_PLAY && !replay_has_interrupt()) {
/* Do nothing */
} else if (interrupt_request & CPU_INTERRUPT_HALT) {
replay_interrupt();
cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
cpu->halted = 1;
cpu->exception_index = EXCP_HLT;
qemu_mutex_unlock_iothread();
return true;
}
#if defined(TARGET_I386)
else if (interrupt_request & CPU_INTERRUPT_INIT) {
X86CPU *x86_cpu = X86_CPU(cpu);
CPUArchState *env = &x86_cpu->env;
replay_interrupt();
cpu_svm_check_intercept_param(env, SVM_EXIT_INIT, 0, 0);
do_cpu_init(x86_cpu);
cpu->exception_index = EXCP_HALTED;
qemu_mutex_unlock_iothread();
return true;
}
#else
else if (interrupt_request & CPU_INTERRUPT_RESET) {
replay_interrupt();
cpu_reset(cpu);
qemu_mutex_unlock_iothread();
return true;
}
#endif
/* The target hook has 3 exit conditions:
False when the interrupt isn't processed,
True when it is, and we should restart on a new TB,
and via longjmp via cpu_loop_exit. */
else {
if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
replay_interrupt();
*last_tb = NULL;
}
/* The target hook may have updated the 'cpu->interrupt_request';
* reload the 'interrupt_request' value */
interrupt_request = cpu->interrupt_request;
}
if (interrupt_request & CPU_INTERRUPT_EXITTB) {
cpu->interrupt_request &= ~CPU_INTERRUPT_EXITTB;
/* ensure that no TB jump will be modified as
the program flow was changed */
*last_tb = NULL;
}
/* If we exit via cpu_loop_exit/longjmp it is reset in cpu_exec */
qemu_mutex_unlock_iothread();
}
/* Finally, check if we need to exit to the main loop. */
if (unlikely(atomic_read(&cpu->exit_request)
|| (use_icount && cpu->icount_decr.u16.low + cpu->icount_extra == 0))) {
atomic_set(&cpu->exit_request, 0);
cpu->exception_index = EXCP_INTERRUPT;
return true;
}
return false;
}
static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
TranslationBlock **last_tb, int *tb_exit)
{
uintptr_t ret;
int32_t insns_left;
trace_exec_tb(tb, tb->pc);
ret = cpu_tb_exec(cpu, tb);
tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
*tb_exit = ret & TB_EXIT_MASK;
if (*tb_exit != TB_EXIT_REQUESTED) {
*last_tb = tb;
return;
}
*last_tb = NULL;
insns_left = atomic_read(&cpu->icount_decr.u32);
atomic_set(&cpu->icount_decr.u16.high, 0);
if (insns_left < 0) {
/* Something asked us to stop executing chained TBs; just
* continue round the main 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. But we need to ensure the zeroing of icount_decr
* comes before the next read of cpu->exit_request
* or cpu->interrupt_request.
*/
smp_mb();
return;
}
/* Instruction counter expired. */
assert(use_icount);
#ifndef CONFIG_USER_ONLY
/* Ensure global icount has gone forward */
cpu_update_icount(cpu);
/* Refill decrementer and continue execution. */
insns_left = MIN(0xffff, cpu->icount_budget);
cpu->icount_decr.u16.low = insns_left;
cpu->icount_extra = cpu->icount_budget - insns_left;
if (!cpu->icount_extra) {
/* Execute any remaining instructions, then let the main loop
* handle the next event.
*/
if (insns_left > 0) {
cpu_exec_nocache(cpu, insns_left, tb, false);
}
}
#endif
}
/* main execution loop */
int cpu_exec(CPUState *cpu)
{
CPUClass *cc = CPU_GET_CLASS(cpu);
int ret;
SyncClocks sc = { 0 };
/* replay_interrupt may need current_cpu */
current_cpu = cpu;
if (cpu_handle_halt(cpu)) {
return EXCP_HALTED;
}
rcu_read_lock();
cc->cpu_exec_enter(cpu);
/* Calculate difference between guest clock and host clock.
* This delay includes the delay of the last cycle, so
* what we have to do is sleep until it is 0. As for the
* advance/delay we gain here, we try to fix it next time.
*/
init_delay_params(&sc, cpu);
/* prepare setjmp context for exception handling */
if (sigsetjmp(cpu->jmp_env, 0) != 0) {
#if defined(__clang__) || !QEMU_GNUC_PREREQ(4, 6)
/* Some compilers wrongly smash all local variables after
* siglongjmp. There were bug reports for gcc 4.5.0 and clang.
* Reload essential local variables here for those compilers.
* Newer versions of gcc would complain about this code (-Wclobbered). */
cpu = current_cpu;
cc = CPU_GET_CLASS(cpu);
#else /* buggy compiler */
/* Assert that the compiler does not smash local variables. */
g_assert(cpu == current_cpu);
g_assert(cc == CPU_GET_CLASS(cpu));
#endif /* buggy compiler */
cpu->can_do_io = 1;
tb_lock_reset();
if (qemu_mutex_iothread_locked()) {
qemu_mutex_unlock_iothread();
}
}
/* if an exception is pending, we execute it here */
while (!cpu_handle_exception(cpu, &ret)) {
TranslationBlock *last_tb = NULL;
int tb_exit = 0;
while (!cpu_handle_interrupt(cpu, &last_tb)) {
TranslationBlock *tb = tb_find(cpu, last_tb, tb_exit);
cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit);
/* Try to align the host and virtual clocks
if the guest is in advance */
align_clocks(&sc, cpu);
}
}
cc->cpu_exec_exit(cpu);
rcu_read_unlock();
return ret;
}