KVM/x86: Reduce retpoline performance impact in slot_handle_level_range(), by...

KVM/x86: Reduce retpoline performance impact in slot_handle_level_range(), by always inlining iterator helper methods

commit 928a4c39 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.ukSigned-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/kvm/mmu.c

@@ -4503,7 +4503,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
 
 /* 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)
@@ -4533,7 +4533,7 @@ 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)
@@ -4544,7 +4544,7 @@ 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)
 {
@@ -4552,7 +4552,7 @@ 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)
 {
@@ -4560,7 +4560,7 @@ 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)
 {