Skip to contentSkip to conversation

KVM: x86: small optimization for is_mtrr_mask calculation

PATCH linmiaohe 2 participants 2 messages Mar 6, 2020 KVM

lore
Share & tools
lore

linmiaohe

author
#0 lore raw

Hi,

Quoted 14 lines · Paolo Bonzini

Review

Quoted 10 lines · linmiaohe

From: Miaohe Lin <[email protected]>

We can get is_mtrr_mask by calculating (msr - 0x200) % 2 directly.

(quoted diff) +1 -1
 		index = (msr - 0x200) / 2;
-		is_mtrr_mask = msr - 0x200 - 2 * index;
+		is_mtrr_mask = (msr - 0x200) % 2;
 		if (!is_mtrr_mask)
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
 		else

If you're going to do that, might as well use ">> 1" for index instead of "/ 2", and "msr & 1" for is_mtrr_mask.

Many thanks for suggestion. What do you mean is like this ?

	index = (msr - 0x200) >> 1;
	is_mtrr_mask = msr & 1;

Thanks again.

#1 lore raw
Quoted 18 lines · linmiaohe

Hi,

Quoted 13 lines · Paolo Bonzini

Review

Quoted 10 lines · linmiaohe

From: Miaohe Lin <[email protected]>

We can get is_mtrr_mask by calculating (msr - 0x200) % 2 directly.

(quoted diff) +1 -1
 		index = (msr - 0x200) / 2;
-		is_mtrr_mask = msr - 0x200 - 2 * index;
+		is_mtrr_mask = (msr - 0x200) % 2;
 		if (!is_mtrr_mask)
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
 		else

If you're going to do that, might as well use ">> 1" for index instead

of "/ 2", and "msr & 1" for is_mtrr_mask.

Quoted 1 line
Quoted 6 lines

Many thanks for suggestion. What do you mean is like this ?

	index = (msr - 0x200) >> 1;
	is_mtrr_mask = msr & 1;

Thanks again.

You realize that the compiler will probably produce exactly the same code, right? As such, it is about making the code easy for the human reader.

Even if it didn't, this code is as far from performance critical as one can possibly get.

Signature · 1 line
Sent from my Android device with K-9 Mail. Please excuse my brevity.