From: "Alex Bennée" <alex.bennee@linaro.org>
To: Sergey Fedorov <sergey.fedorov@linaro.org>
Cc: qemu-devel@nongnu.org, mttcg@listserver.greensocs.com,
fred.konrad@greensocs.com, a.rigo@virtualopensystems.com,
serge.fdrv@gmail.com, cota@braap.org, bobby.prani@gmail.com,
rth@twiddle.net, patches@linaro.org, mark.burton@greensocs.com,
pbonzini@redhat.com, jan.kiszka@siemens.com,
peter.maydell@linaro.org, claudio.fontana@huawei.com,
Peter Crosthwaite <crosthwaite.peter@gmail.com>
Subject: Re: [Qemu-devel] [PATCH v3 07/11] tcg: Prepare TB invalidation for lockless TB lookup
Date: Thu, 14 Jul 2016 13:59:20 +0100 [thread overview]
Message-ID: <87mvlk4bpz.fsf@linaro.org> (raw)
In-Reply-To: <1468354426-837-8-git-send-email-sergey.fedorov@linaro.org>
Sergey Fedorov <sergey.fedorov@linaro.org> writes:
> From: Sergey Fedorov <serge.fdrv@gmail.com>
>
> When invalidating a translation block, set an invalid CPU state into the
> TranslationBlock structure first. All subsequent changes are ordered
> after it with smp_wmb(). This pairs with implied smp_rmb() of
> qht_lookup() in tb_find_physical().
>
> As soon as the TB is marked with an invalid CPU state, there is no need
> to remove it from CPU's 'tb_jmp_cache'. However it will be necessary to
> recheck 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' since
> it is safe to patch an already invalidated TB since it will not be
> executed anyway.
This looks fine. So I guess it's possible for the block to have been
looked up just before it gets invalidated and get one final run but not
get patched?
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
>
> Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
> Signed-off-by: Sergey Fedorov <serge.fdrv@gmail.com>
> Signed-off-by: Sergey Fedorov <sergey.fedorov@linaro.org>
> ---
> cpu-exec.c | 2 +-
> translate-all.c | 12 +++---------
> 2 files changed, 4 insertions(+), 10 deletions(-)
>
> diff --git a/cpu-exec.c b/cpu-exec.c
> index c973e3b85922..07dc50c56e8d 100644
> --- a/cpu-exec.c
> +++ b/cpu-exec.c
> @@ -352,7 +352,7 @@ 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_is_invalid(tb)) {
> tb_add_jump(last_tb, tb_exit, tb);
> }
> }
> diff --git a/translate-all.c b/translate-all.c
> index 788fed1e0765..ee8308209350 100644
> --- a/translate-all.c
> +++ b/translate-all.c
> @@ -986,11 +986,13 @@ static inline void tb_jmp_unlink(TranslationBlock *tb)
> /* invalidate one TB */
> void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
> {
> - CPUState *cpu;
> PageDesc *p;
> uint32_t h;
> tb_page_addr_t phys_pc;
>
> + tb_mark_invalid(tb);
> + smp_wmb();
> +
> /* 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);
> @@ -1008,14 +1010,6 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
> invalidate_page_bitmap(p);
> }
>
> - /* remove the TB from the hash list */
> - h = tb_jmp_cache_hash_func(tb->pc);
> - CPU_FOREACH(cpu) {
> - if (atomic_read(&cpu->tb_jmp_cache[h]) == tb) {
> - atomic_set(&cpu->tb_jmp_cache[h], NULL);
> - }
> - }
> -
> /* suppress this TB from the two jump lists */
> tb_remove_from_jmp_list(tb, 0);
> tb_remove_from_jmp_list(tb, 1);
--
Alex Bennée
next prev parent reply other threads:[~2016-07-14 12:59 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-12 20:13 [Qemu-devel] [PATCH v3 00/11] Reduce lock contention on TCG hot-path Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 01/11] util/qht: Document memory ordering assumptions Sergey Fedorov
2016-07-12 23:19 ` Emilio G. Cota
2016-07-13 7:36 ` Paolo Bonzini
2016-07-13 17:50 ` Sergey Fedorov
2016-07-14 13:56 ` Paolo Bonzini
2016-07-14 14:08 ` Sergey Fedorov
2016-07-13 11:13 ` Paolo Bonzini
2016-07-13 18:03 ` Sergey Fedorov
2016-07-14 8:05 ` Paolo Bonzini
2016-07-15 12:37 ` Sergey Fedorov
2016-07-15 12:51 ` Paolo Bonzini
2016-07-15 13:18 ` Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 02/11] cpu-exec: Pass last_tb by value to tb_find_fast() Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 03/11] tcg: Prepare safe tb_jmp_cache lookup out of tb_lock Sergey Fedorov
2016-07-14 12:14 ` Alex Bennée
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 04/11] tcg: Prepare safe access to tb_flushed " Sergey Fedorov
2016-07-14 12:45 ` Alex Bennée
2016-07-14 12:55 ` Sergey Fedorov
2016-07-14 13:12 ` Alex Bennée
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 05/11] target-i386: Remove redundant HF_SOFTMMU_MASK Sergey Fedorov
2016-07-14 12:19 ` Alex Bennée
2016-07-12 20:13 ` [PATCH v3 06/11] tcg: Introduce tb_mark_invalid() and tb_is_invalid() Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] " Sergey Fedorov
2016-07-14 10:25 ` Alex Bennée
2016-07-14 10:25 ` [Qemu-devel] " Alex Bennée
2016-07-14 11:10 ` Sergey Fedorov
2016-07-14 11:10 ` [Qemu-devel] " Sergey Fedorov
2016-07-14 11:48 ` Paolo Bonzini
2016-07-14 11:48 ` [Qemu-devel] " Paolo Bonzini
2016-07-14 12:04 ` Alex Bennée
2016-07-14 12:04 ` [Qemu-devel] " Alex Bennée
2016-07-14 12:53 ` Alex Bennée
2016-07-14 12:53 ` [Qemu-devel] " Alex Bennée
2016-07-14 13:00 ` Sergey Fedorov
2016-07-14 13:00 ` [Qemu-devel] " Sergey Fedorov
2016-07-14 13:12 ` Paolo Bonzini
2016-07-14 13:12 ` [Qemu-devel] " Paolo Bonzini
2016-07-14 13:15 ` Alex Bennée
2016-07-14 13:15 ` [Qemu-devel] " Alex Bennée
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 07/11] tcg: Prepare TB invalidation for lockless TB lookup Sergey Fedorov
2016-07-14 12:59 ` Alex Bennée [this message]
2016-07-14 13:11 ` Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 08/11] tcg: set up tb->page_addr before insertion Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 09/11] tcg: cpu-exec: remove tb_lock from the hot-path Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 10/11] tcg: Avoid bouncing tb_lock between tb_gen_code() and tb_add_jump() Sergey Fedorov
2016-07-14 13:01 ` Alex Bennée
2016-07-14 13:13 ` Sergey Fedorov
2016-07-12 20:13 ` [Qemu-devel] [PATCH v3 11/11] tcg: Merge tb_find_slow() and tb_find_fast() Sergey Fedorov
2016-07-14 13:02 ` Alex Bennée
2016-07-13 7:39 ` [Qemu-devel] [PATCH v3 00/11] Reduce lock contention on TCG hot-path Paolo Bonzini
2016-07-13 17:00 ` Sergey Fedorov
2016-07-14 9:55 ` Alex Bennée
2016-07-14 11:13 ` Sergey Fedorov
2016-07-13 18:06 ` Sergey Fedorov
2016-07-14 12:02 ` Alex Bennée
2016-07-14 12:10 ` Paolo Bonzini
2016-07-14 13:13 ` 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=87mvlk4bpz.fsf@linaro.org \
--to=alex.bennee@linaro.org \
--cc=a.rigo@virtualopensystems.com \
--cc=bobby.prani@gmail.com \
--cc=claudio.fontana@huawei.com \
--cc=cota@braap.org \
--cc=crosthwaite.peter@gmail.com \
--cc=fred.konrad@greensocs.com \
--cc=jan.kiszka@siemens.com \
--cc=mark.burton@greensocs.com \
--cc=mttcg@listserver.greensocs.com \
--cc=patches@linaro.org \
--cc=pbonzini@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=rth@twiddle.net \
--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.