diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2016-09-15 10:24:22 +0100 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2016-09-15 10:24:22 +0100 |
commit | 8212ff86f4405b6128d89dd1d97ff2d6cfcf9842 (patch) | |
tree | 50f293d984cbe311cd984cb41989d85eb0fa5076 /cpu-exec.c | |
parent | 507e4ddc3abf67391bcbc9624fd60b969c159b78 (diff) | |
parent | 083d012a388e7e2a8bfd9144c2c9bcceb29a78fc (diff) |
Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging
* minor patches here and there
* MTTCG: lock-free TB lookup
* SCSI: bugfixes for MPTSAS, MegaSAS, LSI53c, vmw_pvscsi
* buffer_is_zero rewrite (except for one patch)
* chardev: qemu_chr_fe_write checks
* checkpatch improvement for markdown preformatted text
* default-configs cleanups
* atomics cleanups
# gpg: Signature made Tue 13 Sep 2016 18:14:30 BST
# gpg: using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg: aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4 E2F7 7E15 100C CD36 69B1
# Subkey fingerprint: F133 3857 4B66 2389 866C 7682 BFFB D25F 78C7 AE83
* remotes/bonzini/tags/for-upstream: (58 commits)
cutils: Add generic prefetch
cutils: Add SSE4 version
cutils: Add test for buffer_is_zero
cutils: Remove ppc buffer zero checking
cutils: Remove aarch64 buffer zero checking
cutils: Rearrange buffer_is_zero acceleration
cutils: Export only buffer_is_zero
cutils: Remove SPLAT macro
cutils: Move buffer_is_zero and subroutines to a new file
ppc: do not redefine CPUPPCState
x86/lapic: Load LAPIC state at post_load
optionrom: do not rely on compiler's bswap optimization
checkpatch: Fix whitespace checks for documentation code blocks
atomics: Use __atomic_*_n() variant primitives
atomics: Remove redundant barrier()'s
kvm-all: drop kvm_setup_guest_memory
i8257: Make device "i8257" unavailable with -device
Revert "megasas: remove useless check for cmd->frame"
char: convert qemu_chr_fe_write to qemu_chr_fe_write_all
hw: replace most use of qemu_chr_fe_write with qemu_chr_fe_write_all
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Conflicts:
cpus.c
tests/Makefile.include
Diffstat (limited to 'cpu-exec.c')
-rw-r--r-- | cpu-exec.c | 115 |
1 files changed, 51 insertions, 64 deletions
diff --git a/cpu-exec.c b/cpu-exec.c index 5d9710a1ea..b240b9fa45 100644 --- a/cpu-exec.c +++ b/cpu-exec.c @@ -241,7 +241,8 @@ static bool tb_cmp(const void *p, const void *d) if (tb->pc == desc->pc && tb->page_addr[0] == desc->phys_page1 && tb->cs_base == desc->cs_base && - tb->flags == desc->flags) { + tb->flags == desc->flags && + !atomic_read(&tb->invalid)) { /* check next page if needed */ if (tb->page_addr[1] == -1) { return true; @@ -259,7 +260,7 @@ static bool tb_cmp(const void *p, const void *d) return false; } -static TranslationBlock *tb_find_physical(CPUState *cpu, +static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, target_ulong cs_base, uint32_t flags) @@ -278,72 +279,48 @@ static TranslationBlock *tb_find_physical(CPUState *cpu, return qht_lookup(&tcg_ctx.tb_ctx.htable, tb_cmp, &desc, h); } -static TranslationBlock *tb_find_slow(CPUState *cpu, - target_ulong pc, - target_ulong cs_base, - uint32_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(CPUState *cpu, - TranslationBlock **last_tb, - int tb_exit) +static inline TranslationBlock *tb_find(CPUState *cpu, + TranslationBlock *last_tb, + int tb_exit) { CPUArchState *env = (CPUArchState *)cpu->env_ptr; TranslationBlock *tb; target_ulong cs_base, pc; uint32_t flags; + bool have_tb_lock = false; /* we record a subset of the CPU state. It will always be the same before a given translated block is executed. */ cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags); - tb_lock(); - tb = cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]; + tb = atomic_rcu_read(&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(cpu, pc, cs_base, flags); - } - if (cpu->tb_flushed) { - /* Ensure that no TB jump will be modified as the - * translation buffer has been flushed. - */ - *last_tb = NULL; - cpu->tb_flushed = false; + tb = tb_htable_lookup(cpu, pc, cs_base, flags); + 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(); + tb_lock(); + have_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 (!tb) { + /* 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 @@ -351,14 +328,25 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu, * spanning two pages because the mapping for the second page can change. */ if (tb->page_addr[1] != -1) { - *last_tb = NULL; + last_tb = NULL; } #endif /* See if we can patch the calling TB. */ - if (*last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) { - tb_add_jump(*last_tb, tb_exit, tb); + if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) { + if (!have_tb_lock) { + tb_lock(); + have_tb_lock = true; + } + /* 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); + } + } + if (have_tb_lock) { + tb_unlock(); } - tb_unlock(); return tb; } @@ -437,8 +425,7 @@ static inline bool cpu_handle_exception(CPUState *cpu, int *ret) } else if (replay_has_exception() && cpu->icount_decr.u16.low + cpu->icount_extra == 0) { /* try to cause an exception pending in the log */ - TranslationBlock *last_tb = NULL; /* Avoid chaining TBs */ - cpu_exec_nocache(cpu, 1, tb_find_fast(cpu, &last_tb, 0), true); + cpu_exec_nocache(cpu, 1, tb_find(cpu, NULL, 0), true); *ret = -1; return true; #endif @@ -618,10 +605,10 @@ int cpu_exec(CPUState *cpu) break; } - cpu->tb_flushed = false; /* reset before first TB lookup */ + atomic_mb_set(&cpu->tb_flushed, false); /* reset before first TB lookup */ for(;;) { cpu_handle_interrupt(cpu, &last_tb); - tb = tb_find_fast(cpu, &last_tb, tb_exit); + tb = tb_find(cpu, last_tb, tb_exit); cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit, &sc); /* Try to align the host and virtual clocks if the guest is in advance */ |