qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Emilio G. Cota" <cota@braap.org>
To: Richard Henderson <rth@twiddle.net>
Cc: qemu-devel@nongnu.org, alex.bennee@linaro.org, pbonzini@redhat.com
Subject: [Qemu-devel] [PATCH] tcg-runtime: increase hit rate of lookup_tb_ptr
Date: Wed, 14 Jun 2017 16:27:33 -0400	[thread overview]
Message-ID: <20170614202733.GA8420@flamenco> (raw)
In-Reply-To: <20170614194821.8754-2-rth@twiddle.net>

On Wed, Jun 14, 2017 at 12:48:17 -0700, Richard Henderson wrote:
> We can call tb_htable_lookup even when the tb_jmp_cache
> is completely empty.  Therefore, un-nest most of the code
> dependent on tb != NULL from the read from the cache.
> 
> Signed-off-by: Richard Henderson <rth@twiddle.net>

I just wrote this alternative patch, which does the same thing
as yours. I also measured what the effect of this change
has on the hit rate of lookup_tb_ptr. Feel free to reuse parts
of the patch and/or the commit message!

Thanks,

		E.

--- 8< ---

Strangely, we do not look up the tb in the global hash table
when we get NULL from tb_jmp_cache.

Fix it, which improves the hit rate of lookup_tb_ptr; for instance,
when booting and immediately shutting down debian-arm, the hit
rate improves from
	93.150742% (before this patch)
to
	99.451323 % (after).

While at it, use a variable for the tb_jmp_cache hash and get rid
of the goto's.

Suggested-by: Richard Henderson <rth@twiddle.net>
Suggested-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
---
 tcg-runtime.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/tcg-runtime.c b/tcg-runtime.c
index 7fa90ce..09324b9 100644
--- a/tcg-runtime.c
+++ b/tcg-runtime.c
@@ -149,23 +149,19 @@ void *HELPER(lookup_tb_ptr)(CPUArchState *env, target_ulong addr)
     CPUState *cpu = ENV_GET_CPU(env);
     TranslationBlock *tb;
     target_ulong cs_base, pc;
+    unsigned int hash = tb_jmp_cache_hash_func(addr);
     uint32_t flags;
 
-    tb = atomic_rcu_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(addr)]);
-    if (likely(tb)) {
-        cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
-        if (likely(tb->pc == addr && tb->cs_base == cs_base &&
-                   tb->flags == flags)) {
-            goto found;
-        }
+    tb = atomic_rcu_read(&cpu->tb_jmp_cache[hash]);
+    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
+    if (unlikely(tb == NULL || tb->pc != addr || tb->cs_base != cs_base ||
+               tb->flags != flags)) {
         tb = tb_htable_lookup(cpu, addr, cs_base, flags);
-        if (likely(tb)) {
-            atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(addr)], tb);
-            goto found;
+        if (unlikely(tb == NULL)) {
+            return tcg_ctx.code_gen_epilogue;
         }
+        atomic_set(&cpu->tb_jmp_cache[hash], tb);
     }
-    return tcg_ctx.code_gen_epilogue;
- found:
     qemu_log_mask_and_addr(CPU_LOG_EXEC, addr,
                            "Chain %p [%d: " TARGET_FMT_lx "] %s\n",
                            tb->tc_ptr, cpu->cpu_index, addr,
-- 
2.7.4

  reply	other threads:[~2017-06-14 20:27 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-14 19:48 [Qemu-devel] [PATCH v2 0/5] Fixes for TCG hangs Richard Henderson
2017-06-14 19:48 ` [Qemu-devel] [PATCH v2 1/5] tcg: Refactor helper_lookup_tb_ptr Richard Henderson
2017-06-14 20:27   ` Emilio G. Cota [this message]
2017-06-15  1:21     ` [Qemu-devel] [PATCH] tcg-runtime: increase hit rate of lookup_tb_ptr Richard Henderson
2017-06-15  8:35   ` [Qemu-devel] [PATCH v2 1/5] tcg: Refactor helper_lookup_tb_ptr Alex Bennée
2017-06-16 20:19   ` Emilio G. Cota
2017-06-16 20:46     ` Richard Henderson
2017-06-14 19:48 ` [Qemu-devel] [PATCH v2 2/5] target/alpha: Use tcg_gen_lookup_and_goto_ptr Richard Henderson
2017-06-14 20:37   ` Emilio G. Cota
2017-06-15  1:21     ` Richard Henderson
2017-06-15  8:48   ` Alex Bennée
2017-06-15 20:55     ` Richard Henderson
2017-06-15 21:57       ` Philippe Mathieu-Daudé
2017-06-16  2:56         ` Richard Henderson
2017-06-14 19:48 ` [Qemu-devel] [PATCH v2 3/5] target/mips: Exit after enabling interrupts Richard Henderson
2017-06-15  8:57   ` Alex Bennée
2017-06-15 14:16     ` Paolo Bonzini
2017-06-15 21:19   ` Aurelien Jarno
2017-06-15 21:29     ` Richard Henderson
2017-06-14 19:48 ` [Qemu-devel] [PATCH v2 4/5] target/s390x: Exit after changing PSW mask Richard Henderson
2017-06-15  9:00   ` Alex Bennée
2017-06-14 19:48 ` [Qemu-devel] [PATCH v2 5/5] target/arm: Exit after clearing interrupt mask Richard Henderson
2017-06-14 20:33   ` [Qemu-devel] [PATCH] target/aarch64: exit to main loop after 'msr daifclr' Emilio G. Cota
2017-06-14 21:13     ` no-reply
2017-06-15  1:20     ` Richard Henderson
2017-06-15  5:19       ` Emilio G. Cota
2017-06-15  8:30   ` [Qemu-devel] [PATCH v2 5/5] target/arm: Exit after clearing interrupt mask Alex Bennée
2017-06-14 20:22 ` [Qemu-devel] [PATCH v2 0/5] Fixes for TCG hangs no-reply
2017-06-14 20:26 ` no-reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170614202733.GA8420@flamenco \
    --to=cota@braap.org \
    --cc=alex.bennee@linaro.org \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).