From 474bd0b82e24e8b928910aba876c20c49098ae6d Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 10 Feb 2018 23:39:24 +0000 Subject: [PATCH] KVM/x86: Reduce retpoline performance impact in slot_handle_level_range(), by always inlining iterator helper methods MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit commit 928a4c39484281f8ca366f53a1db79330d058401 upstream. With retpoline, tight loops of "call this function for every XXX" are very much pessimised by taking a prediction miss *every* time. This one is by far the biggest contributor to the guest launch time with retpoline. By marking the iterator slot_handle_…() functions always_inline, we can ensure that the indirect function call can be optimised away into a direct call and it actually generates slightly smaller code because some of the other conditionals can get optimised away too. Performance is now pretty close to what we see with nospectre_v2 on the command line. Suggested-by: Linus Torvalds Tested-by: Filippo Sironi Signed-off-by: David Woodhouse Reviewed-by: Filippo Sironi Acked-by: Paolo Bonzini Cc: Andy Lutomirski Cc: Arjan van de Ven Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: David Woodhouse Cc: Greg Kroah-Hartman Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arjan.van.de.ven@intel.com Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: rkrcmar@redhat.com Link: http://lkml.kernel.org/r/1518305967-31356-4-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index beb7f8795bc1..ca000fc644bc 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5063,7 +5063,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ -static bool +static __always_inline bool slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) @@ -5093,7 +5093,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, return flush; } -static bool +static __always_inline bool slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool lock_flush_tlb) @@ -5104,7 +5104,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5112,7 +5112,7 @@ slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5120,7 +5120,7 @@ slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { -- 2.20.1