On Mon, Oct 09, 2017 at 04:20:25PM +0100, Marc Zyngier wrote:
> Calling __cpuc_coherent_user_range to invalidate the icache on
> a PIPT icache machine has some pointless overhead, as it starts
> by cleaning the dcache to the PoU, while we're guaranteed to
> have already cleaned it to the PoC.
>
> As KVM is the only user of such a feature, let's implement some
> ad-hoc cache flushing in kvm_mmu.h. Should it become useful to
> other subsystems, it can be moved to a more global location.
>
> Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx>
> ---
> arch/arm/include/asm/kvm_hyp.h | 2 ++
> arch/arm/include/asm/kvm_mmu.h | 24 ++++++++++++++++++++++--
> 2 files changed, 24 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
> index 14b5903f0224..ad541f9ecc78 100644
> --- a/arch/arm/include/asm/kvm_hyp.h
> +++ b/arch/arm/include/asm/kvm_hyp.h
> @@ -69,6 +69,8 @@
> #define HIFAR __ACCESS_CP15(c6, 4, c0, 2)
> #define HPFAR __ACCESS_CP15(c6, 4, c0, 4)
> #define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0)
> +#define BPIALLIS __ACCESS_CP15(c7, 0, c1, 6)
> +#define ICIMVAU __ACCESS_CP15(c7, 0, c5, 1)
> #define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0)
> #define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0)
> #define TLBIALL __ACCESS_CP15(c8, 0, c7, 0)
> diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
> index f553aa62d0c3..6773dcf21bff 100644
> --- a/arch/arm/include/asm/kvm_mmu.h
> +++ b/arch/arm/include/asm/kvm_mmu.h
> @@ -37,6 +37,8 @@
>
> #include <linux/highmem.h>
> #include <asm/cacheflush.h>
> +#include <asm/cputype.h>
> +#include <asm/kvm_hyp.h>
> #include <asm/pgalloc.h>
> #include <asm/stage2_pgtable.h>
>
> @@ -157,6 +159,8 @@ static inline void __coherent_icache_guest_page(struct kvm_vcpu *vcpu,
> kvm_pfn_t pfn,
> unsigned long size)
> {
> + u32 iclsz;
> +
> /*
> * If we are going to insert an instruction page and the icache is
> * either VIPT or PIPT, there is a potential problem where the host
> @@ -182,17 +186,33 @@ static inline void __coherent_icache_guest_page(struct kvm_vcpu *vcpu,
> }
>
> /* PIPT cache. As for the d-side, use a temporary kernel mapping. */
> + iclsz = 4 << (read_cpuid(CPUID_CACHETYPE) & 0xf);
> +
nit: the 4 here is a bit cryptic, could we say something like (perhaps
slightly over-explained):
/*
* CTR IminLine contains Log2 of the number of words in the cache line,
* so we can get the number of words as 2 << (IminLine - 1). To get the
* number of bytes, we multiply by 4 (the number of bytes in a 32-bit
* word), and get 4 << (IminLine).
*/
> while (size) {
> void *va = kmap_atomic_pfn(pfn);
> + void *end = va + PAGE_SIZE;
> + void *addr = va;
> +
> + do {
> + write_sysreg(addr, ICIMVAU);
Maybe an oddball place to ask this, but I don't recall why we need PoU
everywhere, would PoC potentially be enough?
> + addr += iclsz;
> + } while (addr < end);
>
> - __cpuc_coherent_user_range((unsigned long)va,
> - (unsigned long)va + PAGE_SIZE);
> + dsb(ishst);
> + isb();
Do we really need this in every iteration of the loop?
>
> size -= PAGE_SIZE;
> pfn++;
>
> kunmap_atomic(va);
> }
> +
> + /* Check if we need to invalidate the BTB */
> + if ((read_cpuid_ext(CPUID_EXT_MMFR1) >> 24) != 4) {
Either I'm having a bad day or you meant to shift this 28, not 24?
> + write_sysreg(0, BPIALLIS);
> + dsb(ishst);
> + isb();
> + }
> }
>
> static inline void __kvm_flush_dcache_pte(pte_t pte)
> --
> 2.14.1
>
Thanks,
-Christoffer
