Vincent Donnefort c353fde17d KVM: arm64: np-guest CMOs with PMD_SIZE fixmap ... With the introduction of stage-2 huge mappings in the pKVM hypervisor, guest pages CMO is needed for PMD_SIZE size. Fixmap only supports PAGE_SIZE and iterating over the huge-page is time consuming (mostly due to TLBI on hyp_fixmap_unmap) which is a problem for EL2 latency. Introduce a shared PMD_SIZE fixmap (hyp_fixblock_map/hyp_fixblock_unmap) to improve guest page CMOs when stage-2 huge mappings are installed. On a Pixel6, the iterative solution resulted in a latency of ~700us, while the PMD_SIZE fixmap reduces it to ~100us. Because of the horrendous private range allocation that would be necessary, this is disabled for 64KiB pages systems. Suggested-by: Quentin Perret <qperret@google.com> Signed-off-by: Vincent Donnefort <vdonnefort@google.com> Signed-off-by: Quentin Perret <qperret@google.com> Link: https://lore.kernel.org/r/20250521124834.1070650-11-vdonnefort@google.com Signed-off-by: Marc Zyngier <maz@kernel.org>		2025-05-21 14:33:51 +01:00
..
early_alloc.h	KVM: arm64: Introduce an early Hyp page allocator	2021-03-19 12:01:20 +00:00
ffa.h	KVM: arm64: Update the identification range for the FF-A smcs	2024-06-14 20:28:30 +00:00
gfp.h	KVM: arm64: Make hyp_page::order a u8	2024-12-20 09:43:59 +00:00
mem_protect.h	KVM: arm64: Add a range to __pkvm_host_test_clear_young_guest()	2025-05-21 14:33:51 +01:00
memory.h	KVM: arm64: Introduce for_each_hyp_page	2025-05-21 14:33:51 +01:00
mm.h	KVM: arm64: np-guest CMOs with PMD_SIZE fixmap	2025-05-21 14:33:51 +01:00
pkvm.h	KVM: arm64: Create each pKVM hyp vcpu after its corresponding host vcpu	2025-03-14 16:06:03 -07:00
spinlock.h	KVM: arm64: Add hyp_spinlock_t static initializer	2022-11-11 16:40:54 +00:00
trap_handler.h	KVM: arm64: Move pkvm_vcpu_init_traps() to init_pkvm_hyp_vcpu()	2024-10-31 18:45:24 +00:00