KVM: x86: Omit caching logic for always-available GPRs

Except for RSP and RIP, which are held in VMX's VMCS, GPRs are always
treated "available and dirtly" on both VMX and SVM, i.e. are
unconditionally loaded/saved immediately before/after VM-Enter/VM-Exit.

Eliminating the unnecessary caching code reduces the size of KVM by a
non-trivial amount, much of which comes from the most common code paths.
E.g. on x86_64, kvm_emulate_cpuid() is reduced from 342 to 182 bytes and
kvm_emulate_hypercall() from 1362 to 1143, with the total size of KVM
dropping by ~1000 bytes.  With CONFIG_RETPOLINE=y, the numbers are even
more pronounced, e.g.: 353->182, 1418->1172 and well over 2000 bytes.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 44 insertions, 45 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 044ece3a28a4..b352a7c137cd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1096,15 +1096,15 @@ EXPORT_SYMBOL_GPL(kvm_get_dr);
 
 bool kvm_rdpmc(struct kvm_vcpu *vcpu)
 {
-	u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
+	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data;
 	int err;
 
 	err = kvm_pmu_rdpmc(vcpu, ecx, &data);
 	if (err)
 		return err;
-	kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32);
+	kvm_rax_write(vcpu, (u32)data);
+	kvm_rdx_write(vcpu, data >> 32);
 	return err;
 }
 EXPORT_SYMBOL_GPL(kvm_rdpmc);
@@ -6586,7 +6586,7 @@ static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
 static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
 			    unsigned short port)
 {
-	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+	unsigned long val = kvm_rax_read(vcpu);
 	int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
 					    size, port, &val, 1);
 
@@ -6610,8 +6610,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
 	}
 
 	/* For size less than 4 we merge, else we zero extend */
-	val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
-					: 0;
+	val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0;
 
 	/*
 	 * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform
@@ -6619,7 +6618,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
 	 */
 	emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size,
 				 vcpu->arch.pio.port, &val, 1);
-	kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+	kvm_rax_write(vcpu, val);
 
 	return kvm_skip_emulated_instruction(vcpu);
 }
@@ -6631,12 +6630,12 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
 	int ret;
 
 	/* For size less than 4 we merge, else we zero extend */
-	val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0;
+	val = (size < 4) ? kvm_rax_read(vcpu) : 0;
 
 	ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port,
 				       &val, 1);
 	if (ret) {
-		kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+		kvm_rax_write(vcpu, val);
 		return ret;
 	}
 
@@ -7151,11 +7150,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	if (kvm_hv_hypercall_enabled(vcpu->kvm))
 		return kvm_hv_hypercall(vcpu);
 
-	nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	a1 = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	a2 = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	a3 = kvm_register_read(vcpu, VCPU_REGS_RSI);
+	nr = kvm_rax_read(vcpu);
+	a0 = kvm_rbx_read(vcpu);
+	a1 = kvm_rcx_read(vcpu);
+	a2 = kvm_rdx_read(vcpu);
+	a3 = kvm_rsi_read(vcpu);
 
 	trace_kvm_hypercall(nr, a0, a1, a2, a3);
 
@@ -7196,7 +7195,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 out:
 	if (!op_64_bit)
 		ret = (u32)ret;
-	kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	kvm_rax_write(vcpu, ret);
 
 	++vcpu->stat.hypercalls;
 	return kvm_skip_emulated_instruction(vcpu);
@@ -8285,23 +8284,23 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 		emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 	}
-	regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	regs->rdx = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	regs->rsi = kvm_register_read(vcpu, VCPU_REGS_RSI);
-	regs->rdi = kvm_register_read(vcpu, VCPU_REGS_RDI);
+	regs->rax = kvm_rax_read(vcpu);
+	regs->rbx = kvm_rbx_read(vcpu);
+	regs->rcx = kvm_rcx_read(vcpu);
+	regs->rdx = kvm_rdx_read(vcpu);
+	regs->rsi = kvm_rsi_read(vcpu);
+	regs->rdi = kvm_rdi_read(vcpu);
 	regs->rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-	regs->rbp = kvm_register_read(vcpu, VCPU_REGS_RBP);
+	regs->rbp = kvm_rbp_read(vcpu);
 #ifdef CONFIG_X86_64
-	regs->r8 = kvm_register_read(vcpu, VCPU_REGS_R8);
-	regs->r9 = kvm_register_read(vcpu, VCPU_REGS_R9);
-	regs->r10 = kvm_register_read(vcpu, VCPU_REGS_R10);
-	regs->r11 = kvm_register_read(vcpu, VCPU_REGS_R11);
-	regs->r12 = kvm_register_read(vcpu, VCPU_REGS_R12);
-	regs->r13 = kvm_register_read(vcpu, VCPU_REGS_R13);
-	regs->r14 = kvm_register_read(vcpu, VCPU_REGS_R14);
-	regs->r15 = kvm_register_read(vcpu, VCPU_REGS_R15);
+	regs->r8 = kvm_r8_read(vcpu);
+	regs->r9 = kvm_r9_read(vcpu);
+	regs->r10 = kvm_r10_read(vcpu);
+	regs->r11 = kvm_r11_read(vcpu);
+	regs->r12 = kvm_r12_read(vcpu);
+	regs->r13 = kvm_r13_read(vcpu);
+	regs->r14 = kvm_r14_read(vcpu);
+	regs->r15 = kvm_r15_read(vcpu);
 #endif
 
 	regs->rip = kvm_rip_read(vcpu);
@@ -8321,23 +8320,23 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = true;
 	vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 
-	kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, regs->rdx);
-	kvm_register_write(vcpu, VCPU_REGS_RSI, regs->rsi);
-	kvm_register_write(vcpu, VCPU_REGS_RDI, regs->rdi);
+	kvm_rax_write(vcpu, regs->rax);
+	kvm_rbx_write(vcpu, regs->rbx);
+	kvm_rcx_write(vcpu, regs->rcx);
+	kvm_rdx_write(vcpu, regs->rdx);
+	kvm_rsi_write(vcpu, regs->rsi);
+	kvm_rdi_write(vcpu, regs->rdi);
 	kvm_register_write(vcpu, VCPU_REGS_RSP, regs->rsp);
-	kvm_register_write(vcpu, VCPU_REGS_RBP, regs->rbp);
+	kvm_rbp_write(vcpu, regs->rbp);
 #ifdef CONFIG_X86_64
-	kvm_register_write(vcpu, VCPU_REGS_R8, regs->r8);
-	kvm_register_write(vcpu, VCPU_REGS_R9, regs->r9);
-	kvm_register_write(vcpu, VCPU_REGS_R10, regs->r10);
-	kvm_register_write(vcpu, VCPU_REGS_R11, regs->r11);
-	kvm_register_write(vcpu, VCPU_REGS_R12, regs->r12);
-	kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13);
-	kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14);
-	kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15);
+	kvm_r8_write(vcpu, regs->r8);
+	kvm_r9_write(vcpu, regs->r9);
+	kvm_r10_write(vcpu, regs->r10);
+	kvm_r11_write(vcpu, regs->r11);
+	kvm_r12_write(vcpu, regs->r12);
+	kvm_r13_write(vcpu, regs->r13);
+	kvm_r14_write(vcpu, regs->r14);
+	kvm_r15_write(vcpu, regs->r15);
 #endif
 
 	kvm_rip_write(vcpu, regs->rip);