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

["Christophe Leroy (CS GROUP)" <chleroy@kernel.org>]

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.

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 ?

Christophe