qemu-arm
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Qemu-arm] [PATCH 04/11] hw/arm/aspeed: add a 'mmio-exec' property t


From: Cédric Le Goater
Subject: Re: [Qemu-arm] [PATCH 04/11] hw/arm/aspeed: add a 'mmio-exec' property to boot from the FMC flash module
Date: Mon, 24 Sep 2018 15:28:22 +0200
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.9.1

On 09/24/2018 01:41 PM, Peter Maydell wrote:
> On 19 September 2018 at 11:19, Cédric Le Goater <address@hidden> wrote:
>> These are the number of read operations done on the flash memory region :
>>
>>     922478 ~ 3.5 MBytes   OpenBMC U-Boot
>>   20569977 ~ 80  MBytes   Mainline U-Boot
>>
>>
>> So we are trashing the TBs I would say. Is there a way to increase the
>> TB size ? or some other TB parameter ? Is that directly linked to the
>> instruction cache size ?
> 
> Well, execution direct from MMIO means we read each instruction
> as we execute it -- there's no caching of TBs. (We generate a
> temporary TB with a single insn and throw it away after executing
> from it.) This is because we can't be sure that we would get the
> same data value the next time we read from the address.

In our case, we should have the same data. So may be I can introduce 
a read-only region with a cache to speed up the accesses. A bit like 
this was done with the previous mmio inteface.

> So we definitely expect things to go slower -- I'm just a little
> surprised that we spend so much time executing from flash devices
> that aren't in "romd" mode.

Yes. it is very slow but some instructions are loaded more than 
250.000 times. See below.

Thanks,

C.





count   address
    ... ...
 149113 0x28a18
 149113 0x28a1c
 149113 0x28a20
 149113 0x28a24
 149113 0x28a28
 149113 0x28a2c
 149113 0x28a30
 149113 0x28a34
 149113 0x28a38
 149113 0x28a3c
 149113 0x28a40
 253584 0x288b4
 253584 0x288bc
 253584 0x288c0
 253584 0x288c8
 253584 0x288cc
 253584 0x288d4
 253584 0x288e0
 253584 0x288e4
 253584 0x288f0
 253584 0x288f4
 253584 0x288fc
 253584 0x28904
 253584 0x28908
 253584 0x28910
 253584 0x28914
 253584 0x28920
 253584 0x28924
 253584 0x28928
 253584 0x2892c
 253584 0x28934
 253584 0x28938
 253584 0x2893c
 253584 0x28940
 253584 0x28944
 253584 0x2894c
 253584 0x28954
 253584 0x28958
 253584 0x2895c
 253584 0x28960
 253584 0x28964
 253584 0x28968
 253584 0x2896c
 253584 0x28970
 253584 0x28974
 253584 0x28978
 253584 0x2897c
 253584 0x28980
 253584 0x53364
 253585 0x288b8
 253585 0x288c4
 253585 0x288d0
 253585 0x288d8
 253585 0x288dc
 253585 0x288f8
 253585 0x28900
 253585 0x2890c
 253585 0x28918
 253585 0x2891c
 253585 0x28948
 253585 0x53344
 253586 0x28930
 253586 0x28950
 253587 0x288b0
 257497 0x53348
 277523 0x53354



reply via email to

[Prev in Thread] Current Thread [Next in Thread]