All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: serge.fdrv@gmail.com, sergey.fedorov@linaro.org, alex.bennee@linaro.org
Subject: [Qemu-devel] [PATCH 05/10] tcg: Prepare TB invalidation for lockless TB lookup
Date: Tue, 19 Jul 2016 10:32:16 +0200	[thread overview]
Message-ID: <1468917141-8155-6-git-send-email-pbonzini@redhat.com> (raw)
In-Reply-To: <1468917141-8155-1-git-send-email-pbonzini@redhat.com>

When invalidating a translation block, set an invalid flag into the
TranslationBlock structure first.  It is also necessary to check whether
the target TB is still valid after acquiring 'tb_lock' but before calling
tb_add_jump() since TB lookup is to be performed out of 'tb_lock' in
future. Note that we don't have to check 'last_tb'; an already invalidated
TB will not be executed anyway and it is thus safe to patch it.

Suggested-by: Sergey Fedorov <serge.fdrv@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 cpu-exec.c              | 5 +++--
 include/exec/exec-all.h | 2 ++
 translate-all.c         | 3 +++
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/cpu-exec.c b/cpu-exec.c
index 877ff8e..cdaab1d 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;
@@ -352,7 +353,7 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
         /* Check if translation buffer has been flushed */
         if (cpu->tb_flushed) {
             cpu->tb_flushed = false;
-        } else {
+        } else if (!tb->invalid) {
             tb_add_jump(last_tb, tb_exit, tb);
         }
     }
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index acda7b6..bc0bcc5 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -213,6 +213,8 @@ struct TranslationBlock {
 #define CF_USE_ICOUNT  0x20000
 #define CF_IGNORE_ICOUNT 0x40000 /* Do not generate icount code */
 
+    uint16_t invalid;
+
     void *tc_ptr;    /* pointer to the translated code */
     uint8_t *tc_search;  /* pointer to search data */
     /* original tb when cflags has CF_NOCACHE */
diff --git a/translate-all.c b/translate-all.c
index 788fed1..eaa1232 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -773,6 +773,7 @@ static TranslationBlock *tb_alloc(target_ulong pc)
     tb = &tcg_ctx.tb_ctx.tbs[tcg_ctx.tb_ctx.nb_tbs++];
     tb->pc = pc;
     tb->cflags = 0;
+    tb->invalid = false;
     return tb;
 }
 
@@ -991,6 +992,8 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
     uint32_t h;
     tb_page_addr_t phys_pc;
 
+    atomic_set(&tb->invalid, true);
+
     /* remove the TB from the hash list */
     phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
     h = tb_hash_func(phys_pc, tb->pc, tb->flags);
-- 
2.7.4

  parent reply	other threads:[~2016-07-19  8:32 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-19  8:32 [Qemu-devel] [PATCH v5 00/10] Reduce lock contention on TCG hot-path Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 01/10] util/qht: Document memory ordering assumptions Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 02/10] tcg: Pass last_tb by value to tb_find_fast() Paolo Bonzini
2016-09-08 12:44   ` Alex Bennée
2016-09-08 13:28     ` Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 03/10] tcg: Prepare safe tb_jmp_cache lookup out of tb_lock Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 04/10] tcg: Prepare safe access to tb_flushed " Paolo Bonzini
2016-07-19  8:32 ` Paolo Bonzini [this message]
2016-07-19 19:56   ` [Qemu-devel] [PATCH 05/10] tcg: Prepare TB invalidation for lockless TB lookup Sergey Fedorov
2016-07-19 22:27     ` Paolo Bonzini
2016-07-21  8:36       ` Sergey Fedorov
2016-07-21  9:04         ` Paolo Bonzini
2016-07-21 11:25         ` Paolo Bonzini
2016-07-21 17:42           ` Sergey Fedorov
2016-07-19  8:32 ` [Qemu-devel] [PATCH 06/10] tcg: set up tb->page_addr before insertion Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 07/10] tcg: cpu-exec: remove tb_lock from the hot-path Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 08/10] tcg: Avoid bouncing tb_lock between tb_gen_code() and tb_add_jump() Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 09/10] tcg: Merge tb_find_slow() and tb_find_fast() Paolo Bonzini
2016-07-19  8:32 ` [Qemu-devel] [PATCH 10/10] tcg: rename tb_find_physical() Paolo Bonzini
2016-09-08 12:39   ` Alex Bennée

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=1468917141-8155-6-git-send-email-pbonzini@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=alex.bennee@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=serge.fdrv@gmail.com \
    --cc=sergey.fedorov@linaro.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.