diff options
| author | Paolo Bonzini <pbonzini@redhat.com> | 2026-09-17 06:03:20 -0400 |
|---|---|---|
| committer | Sean Christopherson <seanjc@google.com> | 2026-09-28 16:40:32 -0700 |
| commit | ba70065fec49766cd9e5a53ca6540703c9f53b85 (patch) | |
| tree | 6bd52ff45c0b54c2f4ffd8b0c2bb138c508f29b4 /arch/x86/include/asm | |
| parent | 07de87723b6f7a7d4a699eb94e75ebe85b6b8c98 (diff) | |
| download | linux-next-ba70065fec49766cd9e5a53ca6540703c9f53b85.tar.gz linux-next-ba70065fec49766cd9e5a53ca6540703c9f53b85.zip | |
KVM: x86: remove "full" out-argument from flush_tlb_gva
The "full" out-argument in flush_tlb_gva is only ever set on AMD
processors, where the TLB flush is little more than a memory write and
thus extremely cheap anyway.
Simplify the code by letting the implementation of Hyper-V TLB flush
hypercalls always go through all the addresses queued in tlb_flush_fifo;
there are no performance concerns since that is already the case on
VMX, and also was on SVM prior to commit 26505e1b5b54 ("KVM: SVM: make
svm_flush_tlb_gva do a full asid flush if NPT enabled", 2026-08-06).
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://patch.msgid.link/20260917100320.21899-1-pbonzini@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Diffstat (limited to 'arch/x86/include/asm')
| -rw-r--r-- | arch/x86/include/asm/kvm_host.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e369faf3c285..1bfe56fbb8a6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1580,7 +1580,7 @@ struct kvm_x86_ops { * Can potentially get non-canonical addresses through INVLPGs, which * the implementation may choose to ignore if appropriate. */ - void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr, bool *full); + void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr); /* * Flush any TLB entries created by the guest. Like tlb_flush_gva(), |