qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: Richard Henderson <rth@twiddle.net>
Cc: Peter Maydell <peter.maydell@linaro.org>,
	Tom Musta <tommusta@gmail.com>,
	qemu-ppc@nongnu.org, Alexander Graf <agraf@suse.de>,
	qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH 03/14] target-ppc: use separate indices for various translation modes
Date: Wed, 17 Sep 2014 10:53:13 +0200	[thread overview]
Message-ID: <54194BF9.7010102@redhat.com> (raw)
In-Reply-To: <1959651544.50247750.1410934939759.JavaMail.zimbra@redhat.com>

Il 17/09/2014 08:22, Paolo Bonzini ha scritto:
> 
>> What if instead of having a "mmu_index" for the mmu arrays, we have a pointer
>> to the "mmu context".  This does imply an extra memory load on the fast path,
>> but probably not an extra instruction.
>>
>> With this, we can suddenly afford to have a relatively large number of mmu
>> contexts, with which we could implement address space numbers for relevant
>> targets.
>>
>> It is, of course, a much larger change, but perhaps it's of larger benefit.
> 
> Sounds good.  I can give it a shot---in the meanwhile, since I forgot to
> Cc qemu-ppc, Alex can you review/apply patch 1?

Much simpler: let's cut the size of the TLB in half on affected targets.

This does sacrifice some speed, but you still get about two thirds of
the improvement (boot speed of a Debian installation ISO: 30s without
patches, 24s with small TLB, 22s with large TLB) compared to the current
TCG target.

For 32-bit target and 32-bit host we can still use the full TLB size.

The following can be easily squashed in patch 2:

diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index 0ca6f0b..ed78884 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -69,8 +69,6 @@ typedef uint64_t target_ulong;
 #define TB_JMP_PAGE_MASK (TB_JMP_CACHE_SIZE - TB_JMP_PAGE_SIZE)
 
 #if !defined(CONFIG_USER_ONLY)
-#define CPU_TLB_BITS 8
-#define CPU_TLB_SIZE (1 << CPU_TLB_BITS)
 /* use a fully associative victim tlb of 8 entries */
 #define CPU_VTLB_SIZE 8
 
@@ -80,6 +78,16 @@ typedef uint64_t target_ulong;
 #define CPU_TLB_ENTRY_BITS 5
 #endif
 
+/* All the TLBs together must be smaller than 64k on RISC machines  */
+#if !defined(__i386__) && !defined(__x86_64__) && !defined(__aarch64__) \
+    && !defined(__sparc__) && !defined(CONFIG_TCG_INTERPRETER)
+#define CPU_TLB_BITS (NB_MMU_MODES < 8 ? 8 : 12 - CPU_TLB_ENTRY_BITS)
+#else
+#define CPU_TLB_BITS 8
+#endif
+
+#define CPU_TLB_SIZE (1 << CPU_TLB_BITS)
+
 typedef struct CPUTLBEntry {
     /* bit TARGET_LONG_BITS to TARGET_PAGE_BITS : virtual address
        bit TARGET_PAGE_BITS-1..4  : Nonzero for accesses that should not

Tom, can you test this on PPC?

Paolo

  reply	other threads:[~2014-09-17  8:53 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-09-15 15:03 [Qemu-devel] [PATCH v2 00/14] TCG ppc speedups Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 01/14] ppc: do not look at the MMU index to detect PR/HV mode Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 02/14] softmmu: support up to 12 MMU modes Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 03/14] target-ppc: use separate indices for various translation modes Paolo Bonzini
2014-09-16 17:20   ` Tom Musta
2014-09-16 18:02     ` Richard Henderson
2014-09-16 18:27       ` Paolo Bonzini
2014-09-16 18:41         ` Richard Henderson
2014-09-16 22:23           ` Richard Henderson
2014-09-17  6:22             ` Paolo Bonzini
2014-09-17  8:53               ` Paolo Bonzini [this message]
2014-09-17 15:33                 ` Richard Henderson
2014-09-17 15:50                   ` Paolo Bonzini
2014-09-17 15:55                     ` Richard Henderson
2014-09-16 18:49     ` Peter Maydell
2014-09-16 22:13       ` Richard Henderson
2014-09-15 15:03 ` [Qemu-devel] [PATCH 04/14] ppc: introduce ppc_get_cr and ppc_set_cr Paolo Bonzini
2014-09-18 19:24   ` Tom Musta
2014-09-15 15:03 ` [Qemu-devel] [PATCH 05/14] ppc: use CRF_* in fpu_helper.c Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 06/14] ppc: introduce helpers for mfocrf/mtocrf Paolo Bonzini
2014-09-18 19:32   ` Tom Musta
2014-09-18 21:01   ` Richard Henderson
2014-09-15 15:03 ` [Qemu-devel] [PATCH 07/14] ppc: reorganize gen_compute_fprf Paolo Bonzini
2014-09-18 19:48   ` Tom Musta
2014-09-15 15:03 ` [Qemu-devel] [PATCH 08/14] ppc: introduce gen_op_mfcr/gen_op_mtcr Paolo Bonzini
2014-09-18 19:49   ` Tom Musta
2014-09-18 21:38   ` Richard Henderson
2014-09-19 13:31     ` Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 09/14] ppc: introduce ppc_get_crf and ppc_set_crf Paolo Bonzini
2014-09-18 19:51   ` Tom Musta
2014-09-19 14:52     ` Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 10/14] ppc: use movcond for isel Paolo Bonzini
2014-09-18 20:05   ` Tom Musta
2014-09-15 15:03 ` [Qemu-devel] [PATCH 11/14] ppc: store CR registers in 32 1-bit registers Paolo Bonzini
2014-09-18 20:25   ` Tom Musta
2014-09-19 13:53     ` Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 12/14] ppc: use movcond to implement evsel Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 13/14] ppc: inline ppc_set_crf when clearer Paolo Bonzini
2014-09-18 20:33   ` Tom Musta
2014-09-19 13:51     ` Paolo Bonzini
2014-09-15 15:03 ` [Qemu-devel] [PATCH 14/14] ppc: dump all 32 CR bits Paolo Bonzini
2014-09-18 20:43 ` [Qemu-devel] [PATCH v2 00/14] TCG ppc speedups Tom Musta
2014-09-19 15:16   ` Paolo Bonzini
2014-11-03 11:56 ` Alexander Graf

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=54194BF9.7010102@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=agraf@suse.de \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    --cc=rth@twiddle.net \
    --cc=tommusta@gmail.com \
    /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).