aboutsummaryrefslogtreecommitdiff
path: root/cpu-exec.c
diff options
context:
space:
mode:
authorPeter Maydell <peter.maydell@linaro.org>2015-09-14 16:13:16 +0100
committerPeter Maydell <peter.maydell@linaro.org>2015-09-14 16:13:16 +0100
commita2aa09e18186801931763fbd40a751fa39971b18 (patch)
tree550e6dc13cae6ef93986d69f7fb1d62620f07709 /cpu-exec.c
parent7e4804dafd4689312ef1172b549927a973bb5414 (diff)
parent47d4be12c3997343e436c6cca89aefbbbeb70863 (diff)
downloadqemu-a2aa09e18186801931763fbd40a751fa39971b18.zip
qemu-a2aa09e18186801931763fbd40a751fa39971b18.tar.gz
qemu-a2aa09e18186801931763fbd40a751fa39971b18.tar.bz2
Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging
* Support for jemalloc * qemu_mutex_lock_iothread "No such process" fix * cutils: qemu_strto* wrappers * iohandler.c simplification * Many other fixes and misc patches. And some MTTCG work (with Emilio's fixes squashed): * Signal-free TCG kick * Removing spinlock in favor of QemuMutex * User-mode emulation multi-threading fixes/docs # gpg: Signature made Thu 10 Sep 2015 09:03:07 BST using RSA key ID 78C7AE83 # gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" # gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" * remotes/bonzini/tags/for-upstream: (44 commits) cutils: work around platform differences in strto{l,ul,ll,ull} cpu-exec: fix lock hierarchy for user-mode emulation exec: make mmap_lock/mmap_unlock globally available tcg: comment on which functions have to be called with mmap_lock held tcg: add memory barriers in page_find_alloc accesses remove unused spinlock. replace spinlock by QemuMutex. cpus: remove tcg_halt_cond and tcg_cpu_thread globals cpus: protect work list with work_mutex scripts/dump-guest-memory.py: fix after RAMBlock change configure: Add support for jemalloc add macro file for coccinelle configure: factor out adding disas configure vhost-scsi: fix wrong vhost-scsi firmware path checkpatch: remove tests that are not relevant outside the kernel checkpatch: adapt some tests to QEMU CODING_STYLE: update mixed declaration rules qmp: Add example usage of strto*l() qemu wrapper cutils: Add qemu_strtoull() wrapper cutils: Add qemu_strtoll() wrapper ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'cpu-exec.c')
-rw-r--r--cpu-exec.c119
1 files changed, 70 insertions, 49 deletions
diff --git a/cpu-exec.c b/cpu-exec.c
index 6b6942d..8945533 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -258,10 +258,10 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
tb_free(tb);
}
-static TranslationBlock *tb_find_slow(CPUState *cpu,
- 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)
{
CPUArchState *env = (CPUArchState *)cpu->env_ptr;
TranslationBlock *tb, **ptb1;
@@ -278,8 +278,9 @@ static TranslationBlock *tb_find_slow(CPUState *cpu,
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 &&
@@ -291,25 +292,59 @@ static TranslationBlock *tb_find_slow(CPUState *cpu,
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;
@@ -350,7 +385,8 @@ static void cpu_handle_debug_exception(CPUState *cpu)
/* main execution loop */
-volatile sig_atomic_t exit_request;
+bool exit_request;
+CPUState *tcg_current_cpu;
int cpu_exec(CPUState *cpu)
{
@@ -365,9 +401,6 @@ int cpu_exec(CPUState *cpu)
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;
@@ -377,18 +410,10 @@ int cpu_exec(CPUState *cpu)
}
current_cpu = cpu;
-
- /* 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();
-
+ atomic_mb_set(&tcg_current_cpu, cpu);
rcu_read_lock();
- if (unlikely(exit_request)) {
+ if (unlikely(atomic_mb_read(&exit_request))) {
cpu->exit_request = 1;
}
@@ -484,8 +509,7 @@ int cpu_exec(CPUState *cpu)
cpu->exception_index = EXCP_INTERRUPT;
cpu_loop_exit(cpu);
}
- spin_lock(&tcg_ctx.tb_ctx.tb_lock);
- have_tb_lock = true;
+ 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 */
@@ -507,20 +531,14 @@ int cpu_exec(CPUState *cpu)
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
@@ -528,8 +546,12 @@ int cpu_exec(CPUState *cpu)
* 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.
*/
+ smp_rmb();
next_tb = 0;
break;
case TB_EXIT_ICOUNT_EXPIRED:
@@ -559,7 +581,6 @@ int cpu_exec(CPUState *cpu)
break;
}
}
- cpu->current_tb = NULL;
/* Try to align the host and virtual clocks
if the guest is in advance */
align_clocks(&sc, cpu);
@@ -576,10 +597,7 @@ int cpu_exec(CPUState *cpu)
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(;;) */
@@ -588,5 +606,8 @@ int cpu_exec(CPUState *cpu)
/* 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;
}