From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: Sergey Fedorov <serge.fdrv@gmail.com>,
Sergey Fedorov <sergey.fedorov@linaro.org>
Subject: [Qemu-devel] [PULL 06/58] tcg: Prepare safe access to tb_flushed out of tb_lock
Date: Tue, 13 Sep 2016 19:15:37 +0200 [thread overview]
Message-ID: <1473786989-54823-7-git-send-email-pbonzini@redhat.com> (raw)
In-Reply-To: <1473786989-54823-1-git-send-email-pbonzini@redhat.com>
From: Sergey Fedorov <serge.fdrv@gmail.com>
Ensure atomicity and ordering of CPU's 'tb_flushed' access for future
translation block lookup out of 'tb_lock'.
This field can only be touched from another thread by tb_flush() in user
mode emulation. So the only access to be sequential atomic is:
* a single write in tb_flush();
* reads/writes out of 'tb_lock'.
In future, before enabling MTTCG in system mode, tb_flush() must be safe
and this field becomes unnecessary.
Signed-off-by: Sergey Fedorov <serge.fdrv@gmail.com>
Signed-off-by: Sergey Fedorov <sergey.fedorov@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20160715175852.30749-5-sergey.fedorov@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
cpu-exec.c | 16 +++++++---------
translate-all.c | 4 ++--
2 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/cpu-exec.c b/cpu-exec.c
index 32b58ed..877ff8e 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -338,13 +338,6 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
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;
- }
#ifndef CONFIG_USER_ONLY
/* We don't take care of direct jumps when address mapping changes in
* system emulation. So it's not safe to make a direct jump to a TB
@@ -356,7 +349,12 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
#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);
+ /* Check if translation buffer has been flushed */
+ if (cpu->tb_flushed) {
+ cpu->tb_flushed = false;
+ } else {
+ tb_add_jump(last_tb, tb_exit, tb);
+ }
}
tb_unlock();
return tb;
@@ -617,7 +615,7 @@ 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);
diff --git a/translate-all.c b/translate-all.c
index 77ae59d..e753a50 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -848,7 +848,6 @@ void tb_flush(CPUState *cpu)
> tcg_ctx.code_gen_buffer_size) {
cpu_abort(cpu, "Internal error: code buffer overflow\n");
}
- tcg_ctx.tb_ctx.nb_tbs = 0;
CPU_FOREACH(cpu) {
int i;
@@ -856,9 +855,10 @@ void tb_flush(CPUState *cpu)
for (i = 0; i < TB_JMP_CACHE_SIZE; ++i) {
atomic_set(&cpu->tb_jmp_cache[i], NULL);
}
- cpu->tb_flushed = true;
+ atomic_mb_set(&cpu->tb_flushed, true);
}
+ tcg_ctx.tb_ctx.nb_tbs = 0;
qht_reset_size(&tcg_ctx.tb_ctx.htable, CODE_GEN_HTABLE_SIZE);
page_flush_tb();
--
1.8.3.1
next prev parent reply other threads:[~2016-09-13 17:17 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-13 17:15 [Qemu-devel] [PULL 00/58] First round of misc patches for QEMU 2.8 Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 01/58] qtail: clean up direct access to tqe_prev field Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 02/58] util/qemu-sockets: revert Yoda Conditions to normal Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 03/58] util: fix some coding style issue Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 04/58] tcg: Pass last_tb by value to tb_find_fast() Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 05/58] tcg: Prepare safe tb_jmp_cache lookup out of tb_lock Paolo Bonzini
2016-09-13 17:15 ` Paolo Bonzini [this message]
2016-09-13 17:15 ` [Qemu-devel] [PULL 07/58] tcg: Prepare TB invalidation for lockless TB lookup Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 08/58] tcg: set up tb->page_addr before insertion Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 09/58] tcg: cpu-exec: remove tb_lock from the hot-path Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 10/58] tcg: Avoid bouncing tb_lock between tb_gen_code() and tb_add_jump() Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 11/58] tcg: Merge tb_find_slow() and tb_find_fast() Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 12/58] tcg: rename tb_find_physical() Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 13/58] rules.mak: Don't extract libs from .mo-libs in link command Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 14/58] timer: update comments Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 15/58] cpus: rename local variable to meaningful one Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 16/58] cpus: update comments Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 17/58] help: Update help to remove misleading display information Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 18/58] lsi: print register names in debug prints Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 19/58] lsi: do not exit QEMU if reading invalid register Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 20/58] lsi: implement I/O memory space for Memory Move instructions Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 21/58] lsi: never set DMA FIFO Empty (DFE) bit in DSTAT register Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 22/58] MAINTAINERS: add myself as stubs maintainers Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 23/58] scsi-disk: change disk serial length from 20 to 36 Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 24/58] vmw_pvscsi: check page count while initialising descriptor rings Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 25/58] scsi: mptconfig: fix an assert expression Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 26/58] scsi: mptconfig: fix misuse of MPTSAS_CONFIG_PACK Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 27/58] vmxcap: Show raw MSR value Paolo Bonzini
2016-09-13 17:15 ` [Qemu-devel] [PULL 28/58] vmxcap: Add TSC scaling bit Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 29/58] doc/rcu: fix typo Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 30/58] chardev: Add 'help' option to print all available chardev backend types Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 31/58] MAINTAINERS: Fix wildcard for scsi headers Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 32/58] MAINTAINERS: Add some header files to the PC chipset section Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 33/58] scsi: pvscsi: limit loop to fetch SG list Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 34/58] default-configs: remove CONFIG_PAM Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 35/58] default-configs: removed obsolete CONFIG_ISA_MMIO Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 36/58] default-configs: remove CONFIG_PIIX_PCI Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 37/58] ipmi: check return of qemu_chr_fe_write() for errors Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 38/58] sclpconsolelm: remove bogus check for -EAGAIN Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 39/58] hw: replace most use of qemu_chr_fe_write with qemu_chr_fe_write_all Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 40/58] char: convert qemu_chr_fe_write to qemu_chr_fe_write_all Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 41/58] Revert "megasas: remove useless check for cmd->frame" Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 42/58] i8257: Make device "i8257" unavailable with -device Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 43/58] kvm-all: drop kvm_setup_guest_memory Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 44/58] atomics: Remove redundant barrier()'s Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 45/58] atomics: Use __atomic_*_n() variant primitives Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 46/58] checkpatch: Fix whitespace checks for documentation code blocks Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 47/58] optionrom: do not rely on compiler's bswap optimization Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 49/58] ppc: do not redefine CPUPPCState Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 50/58] cutils: Move buffer_is_zero and subroutines to a new file Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 51/58] cutils: Remove SPLAT macro Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 52/58] cutils: Export only buffer_is_zero Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 53/58] cutils: Rearrange buffer_is_zero acceleration Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 54/58] cutils: Remove aarch64 buffer zero checking Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 55/58] cutils: Remove ppc " Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 56/58] cutils: Add test for buffer_is_zero Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 57/58] cutils: Add SSE4 version Paolo Bonzini
2016-09-13 17:16 ` [Qemu-devel] [PULL 58/58] cutils: Add generic prefetch Paolo Bonzini
2016-09-13 17:49 ` [Qemu-devel] [PULL 00/58] First round of misc patches for QEMU 2.8 Peter Maydell
2016-09-13 19:08 ` Paolo Bonzini
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=1473786989-54823-7-git-send-email-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--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 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).