Re: [PATCH RFC v2 00/20] mm: optimize unnecessary loads due to ptep_get() and friends out
Will Deacon <[email protected]>
| Newsgroups | gmane.comp.emulators.kvm.risc-v,gmane.linux.ports.arm.kernel,gmane.linux.kernel,gmane.linux.ports.mips,gmane.linux.kernel.cross-arch,gmane.linux.kernel.mm,gmane.comp.emulators.kvm.devel,gmane.linux.ports.riscv |
|---|---|
| Message-ID | <[email protected]> |
On Wed, 22 Jul 2026 16:30:08 +0100, Yeoreum Yun wrote:
> Using ptep_get() and its counterparts in common code is suboptimal on
> kernel configurations with generic compile-time folded page tables.
> By default, ptep_get() and its friends expands to READ_ONCE(),
> forcing the compiler to emit a load even when the value is not used afterwards.
>
> This issue was recently reported by Christophe Leroy [1] for ppc32
> preventing futher code conversion to ptep_get()/pmdp_get()/... helper
> and the same behavior can also be observed on arm64 when built with
> 2- or 3-level page tables
>
> [...]
Applied the arm64 patch on the end to arm64 (for-next/mm), thanks!
[20/20] arm64: pgtable: convert pte_present() from macro to static inline
https://git.kernel.org/arm64/c/3b56ebafecc4
Cheers,
--
Will
https://fixes.arm64.dev
https://next.arm64.dev
https://will.arm64.dev
--
kvm-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kvm-riscv