* [RFC PATCH v3] target/mips: Increase number of TLB entries on the 34Kf core (16 -> 64)
@ 2020-10-16 13:33 Philippe Mathieu-Daudé
2020-10-16 17:28 ` Richard Henderson
0 siblings, 1 reply; 3+ messages in thread
From: Philippe Mathieu-Daudé @ 2020-10-16 13:33 UTC (permalink / raw)
To: qemu-devel, Victor Kamensky
Cc: Aleksandar Rikalo, Khem Raj, Philippe Mathieu-Daudé,
Richard Purdie, Aurelien Jarno, Richard Henderson
Per "MIPS32 34K Processor Core Family Software User's Manual,
Revision 01.13" page 8 in "Joint TLB (JTLB)" section:
"The JTLB is a fully associative TLB cache containing 16, 32,
or 64-dual-entries mapping up to 128 virtual pages to their
corresponding physical addresses."
There is no particular reason to restrict the 34Kf core model to
16 TLB entries, so raise its config to 64.
This is helpful for other projects, in particular the Yocto Project:
Yocto Project uses qemu-system-mips 34Kf cpu model, to run 32bit
MIPS CI loop. It was observed that in this case CI test execution
time was almost twice longer than 64bit MIPS variant that runs
under MIPS64R2-generic model. It was investigated and concluded
that the difference in number of TLBs 16 in 34Kf case vs 64 in
MIPS64R2-generic is responsible for most of CI real time execution
difference. Because with 16 TLBs linux user-land trashes TLB more
and it needs to execute more instructions in TLB refill handler
calls, as result it runs much longer.
(https://lists.gnu.org/archive/html/qemu-devel/2020-10/msg03428.html)
Buglink: https://bugzilla.yoctoproject.org/show_bug.cgi?id=13992
Reported-by: Victor Kamensky <kamensky@cisco.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
---
v3: KISS
Supersedes: <20201015224746.540027-1-f4bug@amsat.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
---
target/mips/translate_init.c.inc | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/target/mips/translate_init.c.inc b/target/mips/translate_init.c.inc
index 637caccd890..ad21756f4d9 100644
--- a/target/mips/translate_init.c.inc
+++ b/target/mips/translate_init.c.inc
@@ -254,7 +254,7 @@ const mips_def_t mips_defs[] =
.CP0_PRid = 0x00019500,
.CP0_Config0 = MIPS_CONFIG0 | (0x1 << CP0C0_AR) |
(MMU_TYPE_R4000 << CP0C0_MT),
- .CP0_Config1 = MIPS_CONFIG1 | (1 << CP0C1_FP) | (15 << CP0C1_MMU) |
+ .CP0_Config1 = MIPS_CONFIG1 | (1 << CP0C1_FP) | (63 << CP0C1_MMU) |
(0 << CP0C1_IS) | (3 << CP0C1_IL) | (1 << CP0C1_IA) |
(0 << CP0C1_DS) | (3 << CP0C1_DL) | (1 << CP0C1_DA) |
(1 << CP0C1_CA),
--
2.26.2
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [RFC PATCH v3] target/mips: Increase number of TLB entries on the 34Kf core (16 -> 64)
2020-10-16 13:33 [RFC PATCH v3] target/mips: Increase number of TLB entries on the 34Kf core (16 -> 64) Philippe Mathieu-Daudé
@ 2020-10-16 17:28 ` Richard Henderson
2020-10-17 9:06 ` Philippe Mathieu-Daudé
0 siblings, 1 reply; 3+ messages in thread
From: Richard Henderson @ 2020-10-16 17:28 UTC (permalink / raw)
To: Philippe Mathieu-Daudé, qemu-devel, Victor Kamensky
Cc: Aleksandar Rikalo, Richard Purdie, Aurelien Jarno, Khem Raj
On 10/16/20 6:33 AM, Philippe Mathieu-Daudé wrote:
> Per "MIPS32 34K Processor Core Family Software User's Manual,
> Revision 01.13" page 8 in "Joint TLB (JTLB)" section:
>
> "The JTLB is a fully associative TLB cache containing 16, 32,
> or 64-dual-entries mapping up to 128 virtual pages to their
> corresponding physical addresses."
>
> There is no particular reason to restrict the 34Kf core model to
> 16 TLB entries, so raise its config to 64.
>
> This is helpful for other projects, in particular the Yocto Project:
>
> Yocto Project uses qemu-system-mips 34Kf cpu model, to run 32bit
> MIPS CI loop. It was observed that in this case CI test execution
> time was almost twice longer than 64bit MIPS variant that runs
> under MIPS64R2-generic model. It was investigated and concluded
> that the difference in number of TLBs 16 in 34Kf case vs 64 in
> MIPS64R2-generic is responsible for most of CI real time execution
> difference. Because with 16 TLBs linux user-land trashes TLB more
> and it needs to execute more instructions in TLB refill handler
> calls, as result it runs much longer.
>
> (https://lists.gnu.org/archive/html/qemu-devel/2020-10/msg03428.html)
>
> Buglink: https://bugzilla.yoctoproject.org/show_bug.cgi?id=13992
> Reported-by: Victor Kamensky <kamensky@cisco.com>
> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
> ---
> v3: KISS
> Supersedes: <20201015224746.540027-1-f4bug@amsat.org>
> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
> ---
> target/mips/translate_init.c.inc | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
r~
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [RFC PATCH v3] target/mips: Increase number of TLB entries on the 34Kf core (16 -> 64)
2020-10-16 17:28 ` Richard Henderson
@ 2020-10-17 9:06 ` Philippe Mathieu-Daudé
0 siblings, 0 replies; 3+ messages in thread
From: Philippe Mathieu-Daudé @ 2020-10-17 9:06 UTC (permalink / raw)
To: Richard Henderson, qemu-devel, Victor Kamensky
Cc: Aleksandar Rikalo, Richard Purdie, Khem Raj, Aurelien Jarno
On 10/16/20 7:28 PM, Richard Henderson wrote:
> On 10/16/20 6:33 AM, Philippe Mathieu-Daudé wrote:
>> Per "MIPS32 34K Processor Core Family Software User's Manual,
>> Revision 01.13" page 8 in "Joint TLB (JTLB)" section:
>>
>> "The JTLB is a fully associative TLB cache containing 16, 32,
>> or 64-dual-entries mapping up to 128 virtual pages to their
>> corresponding physical addresses."
>>
>> There is no particular reason to restrict the 34Kf core model to
>> 16 TLB entries, so raise its config to 64.
>>
>> This is helpful for other projects, in particular the Yocto Project:
>>
>> Yocto Project uses qemu-system-mips 34Kf cpu model, to run 32bit
>> MIPS CI loop. It was observed that in this case CI test execution
>> time was almost twice longer than 64bit MIPS variant that runs
>> under MIPS64R2-generic model. It was investigated and concluded
>> that the difference in number of TLBs 16 in 34Kf case vs 64 in
>> MIPS64R2-generic is responsible for most of CI real time execution
>> difference. Because with 16 TLBs linux user-land trashes TLB more
>> and it needs to execute more instructions in TLB refill handler
>> calls, as result it runs much longer.
>>
>> (https://lists.gnu.org/archive/html/qemu-devel/2020-10/msg03428.html)
>>
>> Buglink: https://bugzilla.yoctoproject.org/show_bug.cgi?id=13992
>> Reported-by: Victor Kamensky <kamensky@cisco.com>
>> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
>> ---
>> v3: KISS
>> Supersedes: <20201015224746.540027-1-f4bug@amsat.org>
>> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
>> ---
>> target/mips/translate_init.c.inc | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Thanks, applied to mips-next.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-10-17 9:07 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-10-16 13:33 [RFC PATCH v3] target/mips: Increase number of TLB entries on the 34Kf core (16 -> 64) Philippe Mathieu-Daudé
2020-10-16 17:28 ` Richard Henderson
2020-10-17 9:06 ` Philippe Mathieu-Daudé
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).