Re: [PATCH 04/15] powerpc/time: Prepare to stop elapsing in dynticks-idle

[Shrikanth Hegde <sshegde@linux.ibm.com>]

On 2/25/26 4:44 PM, Christophe Leroy (CS GROUP) wrote:
> Hi Hegde,
> 
> Le 25/02/2026 à 11:34, Shrikanth Hegde a écrit :
>> Hi Christophe.
>>
>> On 2/25/26 3:15 PM, Christophe Leroy (CS GROUP) wrote:
>>>
>>> Hope it is more explicit now.
>>>
>>
>> Got it. The main concern was around with additional computation that 
>> sched_clock,
>> not any additional paths per se.
>>
>> yes, that would be possible,
>>
>>
>> How about we do below? This adds only one subtraction.
>> This achieves the same outcome.
> 
> It adds a bit more than just a substration. It adds a call to an extern 
> fonction.

I think we should make it always inline and move it to time.h

> 
> 00000164 <my_account_cpu_user_entry>:
>   164:    94 21 ff f0     stwu    r1,-16(r1)
>   168:    7c 08 02 a6     mflr    r0
>   16c:    90 01 00 14     stw     r0,20(r1)
>   170:    93 e1 00 0c     stw     r31,12(r1)
>   174:    7f ec 42 e6     mftb    r31
>   178:    48 00 00 01     bl      178 <my_account_cpu_user_entry+0x14>
>              178: R_PPC_REL24    get_boot_tb
>   17c:    81 02 00 08     lwz     r8,8(r2)
>   180:    81 22 00 28     lwz     r9,40(r2)
>   184:    7c 84 f8 50     subf    r4,r4,r31
>   188:    7d 29 40 50     subf    r9,r9,r8
>   18c:    7d 29 22 14     add     r9,r9,r4
>   190:    90 82 00 24     stw     r4,36(r2)
>   194:    91 22 00 08     stw     r9,8(r2)
>   198:    80 01 00 14     lwz     r0,20(r1)
>   19c:    83 e1 00 0c     lwz     r31,12(r1)
>   1a0:    7c 08 03 a6     mtlr    r0
>   1a4:    38 21 00 10     addi    r1,r1,16
>   1a8:    4e 80 00 20     blr
> 
> 000001ac <my_account_cpu_user_exit>:
>   1ac:    94 21 ff f0     stwu    r1,-16(r1)
>   1b0:    7c 08 02 a6     mflr    r0
>   1b4:    90 01 00 14     stw     r0,20(r1)
>   1b8:    93 e1 00 0c     stw     r31,12(r1)
>   1bc:    7f ec 42 e6     mftb    r31
>   1c0:    48 00 00 01     bl      1c0 <my_account_cpu_user_exit+0x14>
>              1c0: R_PPC_REL24    get_boot_tb
>   1c4:    81 02 00 0c     lwz     r8,12(r2)
>   1c8:    81 22 00 24     lwz     r9,36(r2)
>   1cc:    7c 84 f8 50     subf    r4,r4,r31
>   1d0:    7d 29 40 50     subf    r9,r9,r8
>   1d4:    7d 29 22 14     add     r9,r9,r4
>   1d8:    90 82 00 28     stw     r4,40(r2)
>   1dc:    91 22 00 0c     stw     r9,12(r2)
>   1e0:    80 01 00 14     lwz     r0,20(r1)
>   1e4:    83 e1 00 0c     lwz     r31,12(r1)
>   1e8:    7c 08 03 a6     mtlr    r0
>   1ec:    38 21 00 10     addi    r1,r1,16
>   1f0:    4e 80 00 20     blr
> 
> 
> I really still can't see the point of this substraction.
> 
> At one place we do
> 
>      tb1 = mftb1;
> 
>      acct->utime += (tb1 - acct->starttime_user);
>      acct->starttime = tb1;
> 
> At the other place we do
> 
>      tb2 = mftb2;
> 
>      acct->stime += (tb2 - acct->starttime);
>      acct->starttime_user = tb2;
> 
> So at the end we have
> 
>      acct->utime += mftb1 - mftb2;
>      acct->stime += mftb2 - mftb1;
> 
> You want to change to
>      tb1 = mftb1 - boot_tb;
>      tb2 = mftb2 - boot_tb;
> 
> At the end we would get
> 
>      acct->utime += mftb1 - boot_tb - mftb2 + boot_tb = mftb1 - mftb2;
>      acct->stime += mftb2 - boot_tb - mftb1 + boot_tb = mftb2 - mftb1;
> 
> So what's the point in doing such a useless substract that disappears at 
> the end ? What am I missing ?
> 

I had similar thought, but I saw this data below when i do exec on the system.

This was the stats seen on PowerNV system with 144 CPUs.
Nothing is running on the system after boot. So it is mostly idle.


======== With the series applied ===

cat /proc/stat | head
cpu  1494 0 135607576 9628633227 16876 142 63 0 0 0
cpu0 0 0 8 67807311 0 2 40 0 0 0
cpu1 0 0 6 67807349 0 0 0 0 0 0

cat /proc/uptime
48.32 96286332.82   << Note this value is too huge. Also system value is also huge.

========= without the series(tip/master) ===============
cat /proc/stat | head
cpu  2003 0 67866261 859414 15923 249 66 0 0 0
cpu0 5 0 23 5595 461 2 38 0 0 0
cpu1 0 0 9 6092 21 0 3 0 0 0

cat /proc/uptime
61.29 8594.82    << This is right. 144*61 = 8784.

But note, the system time reported. i.e 67866261. It is too huge again. And very close to actual mftb value
rather than the diff. i.e we have paths were tb1 is not done. tb2 is effectively mftb - 0


========= with proposed fix of mftb - boot_tb ===============
cat /proc/stat | head
cpu  5187 0 10996 2025690 16566 765 184 0 0 0
cpu0 9 0 28 14096 65 6 108 0 0 0
cpu1 4 0 15 14277 0 0 2 0 0 0

cat /proc/uptime
142.97 20257.42     << Looks correct, since 142*144 is close to 20448

=============================================================

Now lets go to CONFIG_VIRT_CPU_ACCOUNTING_GEN=y

cat /proc/stat | head
cpu  1804 0 3003 791760 15695 0 0 0 0 0
cpu0 22 0 46 5535 0 0 0 0 0 0
cpu1 0 0 7 5637 0 0 0 0 0 0

cat /proc/uptime
56.49 7918.05      << Looks correct. close 56*144


================================================