diff options
Diffstat (limited to 'common/recipes-kernel/linux/linux-yocto-4.9.21/0025-KVM-x86-Reduce-retpoline-performance-impact-in-slot_.patch')
-rw-r--r-- | common/recipes-kernel/linux/linux-yocto-4.9.21/0025-KVM-x86-Reduce-retpoline-performance-impact-in-slot_.patch | 103 |
1 files changed, 103 insertions, 0 deletions
diff --git a/common/recipes-kernel/linux/linux-yocto-4.9.21/0025-KVM-x86-Reduce-retpoline-performance-impact-in-slot_.patch b/common/recipes-kernel/linux/linux-yocto-4.9.21/0025-KVM-x86-Reduce-retpoline-performance-impact-in-slot_.patch new file mode 100644 index 00000000..eb633c9c --- /dev/null +++ b/common/recipes-kernel/linux/linux-yocto-4.9.21/0025-KVM-x86-Reduce-retpoline-performance-impact-in-slot_.patch @@ -0,0 +1,103 @@ +From 15ca5afe3e56a0f80151aa4b6f06233b39736a2e Mon Sep 17 00:00:00 2001 +From: David Woodhouse <dwmw@amazon.co.uk> +Date: Sat, 10 Feb 2018 23:39:24 +0000 +Subject: [PATCH 25/33] 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=UTF-8 +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 <torvalds@linux-foundation.org> +Tested-by: Filippo Sironi <sironi@amazon.de> +Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> +Reviewed-by: Filippo Sironi <sironi@amazon.de> +Acked-by: Paolo Bonzini <pbonzini@redhat.com> +Cc: Andy Lutomirski <luto@kernel.org> +Cc: Arjan van de Ven <arjan@linux.intel.com> +Cc: Borislav Petkov <bp@alien8.de> +Cc: Dan Williams <dan.j.williams@intel.com> +Cc: Dave Hansen <dave.hansen@linux.intel.com> +Cc: David Woodhouse <dwmw2@infradead.org> +Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +Cc: Josh Poimboeuf <jpoimboe@redhat.com> +Cc: Peter Zijlstra <peterz@infradead.org> +Cc: Thomas Gleixner <tglx@linutronix.de> +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 <mingo@kernel.org> +Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +--- + 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 d9c7e98..ee4af7a 100644 +--- a/arch/x86/kvm/mmu.c ++++ b/arch/x86/kvm/mmu.c +@@ -4636,7 +4636,7 @@ 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) +@@ -4666,7 +4666,7 @@ 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) +@@ -4677,7 +4677,7 @@ 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) + { +@@ -4685,7 +4685,7 @@ 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) + { +@@ -4693,7 +4693,7 @@ 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) + { +-- +2.7.4 + |