redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

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>
hifive-unleashed-5.2
Sean Christopherson 2019-04-30 10:36:17 -07:00 committed by Paolo Bonzini
parent 0c55671f84
commit de3cd117ed
6 changed files with 105 additions and 80 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
arch/x86/kvm/cpuid.c
View File

@ -962,13 +962,13 @@ int kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
if (cpuid_fault_enabled(vcpu) && !kvm_require_cpl(vcpu, 0))
return 1;
eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
eax = kvm_rax_read(vcpu);
ecx = kvm_rcx_read(vcpu);
kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true);
kvm_register_write(vcpu, VCPU_REGS_RAX, eax);
kvm_register_write(vcpu, VCPU_REGS_RBX, ebx);
kvm_register_write(vcpu, VCPU_REGS_RCX, ecx);
kvm_register_write(vcpu, VCPU_REGS_RDX, edx);
kvm_rax_write(vcpu, eax);
kvm_rbx_write(vcpu, ebx);
kvm_rcx_write(vcpu, ecx);
kvm_rdx_write(vcpu, edx);
return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);

24
arch/x86/kvm/hyperv.c
View File

@ -1526,10 +1526,10 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
longmode = is_64_bit_mode(vcpu);
if (longmode)
kvm_register_write(vcpu, VCPU_REGS_RAX, result);
kvm_rax_write(vcpu, result);
else {
kvm_register_write(vcpu, VCPU_REGS_RDX, result >> 32);
kvm_register_write(vcpu, VCPU_REGS_RAX, result & 0xffffffff);
kvm_rdx_write(vcpu, result >> 32);
kvm_rax_write(vcpu, result & 0xffffffff);
}
}
@ -1602,18 +1602,18 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
longmode = is_64_bit_mode(vcpu);
if (!longmode) {
param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
param = ((u64)kvm_rdx_read(vcpu) << 32) |
(kvm_rax_read(vcpu) & 0xffffffff);
ingpa = ((u64)kvm_rbx_read(vcpu) << 32) |
(kvm_rcx_read(vcpu) & 0xffffffff);
outgpa = ((u64)kvm_rdi_read(vcpu) << 32) |
(kvm_rsi_read(vcpu) & 0xffffffff);
}
#ifdef CONFIG_X86_64
else {
param = kvm_register_read(vcpu, VCPU_REGS_RCX);
ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
param = kvm_rcx_read(vcpu);
ingpa = kvm_rdx_read(vcpu);
outgpa = kvm_r8_read(vcpu);
}
#endif

32
arch/x86/kvm/kvm_cache_regs.h
View File

@ -9,6 +9,34 @@
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
| X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
#define BUILD_KVM_GPR_ACCESSORS(lname, uname) \
static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
{ \
return vcpu->arch.regs[VCPU_REGS_##uname]; \
} \
static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu, \
unsigned long val) \
{ \
vcpu->arch.regs[VCPU_REGS_##uname] = val; \
}
BUILD_KVM_GPR_ACCESSORS(rax, RAX)
BUILD_KVM_GPR_ACCESSORS(rbx, RBX)
BUILD_KVM_GPR_ACCESSORS(rcx, RCX)
BUILD_KVM_GPR_ACCESSORS(rdx, RDX)
BUILD_KVM_GPR_ACCESSORS(rbp, RBP)
BUILD_KVM_GPR_ACCESSORS(rsi, RSI)
BUILD_KVM_GPR_ACCESSORS(rdi, RDI)
#ifdef CONFIG_X86_64
BUILD_KVM_GPR_ACCESSORS(r8, R8)
BUILD_KVM_GPR_ACCESSORS(r9, R9)
BUILD_KVM_GPR_ACCESSORS(r10, R10)
BUILD_KVM_GPR_ACCESSORS(r11, R11)
BUILD_KVM_GPR_ACCESSORS(r12, R12)
BUILD_KVM_GPR_ACCESSORS(r13, R13)
BUILD_KVM_GPR_ACCESSORS(r14, R14)
BUILD_KVM_GPR_ACCESSORS(r15, R15)
#endif
static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
enum kvm_reg reg)
{
@ -83,8 +111,8 @@ static inline ulong kvm_read_cr4(struct kvm_vcpu *vcpu)
static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
{
return (kvm_register_read(vcpu, VCPU_REGS_RAX) & -1u)
| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
return (kvm_rax_read(vcpu) & -1u)
| ((u64)(kvm_rdx_read(vcpu) & -1u) << 32);
}
static inline void enter_guest_mode(struct kvm_vcpu *vcpu)

26
arch/x86/kvm/svm.c
View File

@ -2091,7 +2091,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
init_vmcb(svm);
kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true);
kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
kvm_rdx_write(vcpu, eax);
if (kvm_vcpu_apicv_active(vcpu) && !init_event)
avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE);
@ -3388,7 +3388,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
} else {
(void)kvm_set_cr3(&svm->vcpu, hsave->save.cr3);
}
kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax);
kvm_rax_write(&svm->vcpu, hsave->save.rax);
kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp);
kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, hsave->save.rip);
svm->vmcb->save.dr7 = 0;
@ -3496,7 +3496,7 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
kvm_mmu_reset_context(&svm->vcpu);
svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax);
kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
@ -3787,11 +3787,11 @@ static int invlpga_interception(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX),
kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
trace_kvm_invlpga(svm->vmcb->save.rip, kvm_rcx_read(&svm->vcpu),
kvm_rax_read(&svm->vcpu));
/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu));
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
return kvm_skip_emulated_instruction(&svm->vcpu);
@ -3799,7 +3799,7 @@ static int invlpga_interception(struct vcpu_svm *svm)
static int skinit_interception(struct vcpu_svm *svm)
{
trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
trace_kvm_skinit(svm->vmcb->save.rip, kvm_rax_read(&svm->vcpu));
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
@ -3813,7 +3813,7 @@ static int wbinvd_interception(struct vcpu_svm *svm)
static int xsetbv_interception(struct vcpu_svm *svm)
{
u64 new_bv = kvm_read_edx_eax(&svm->vcpu);
u32 index = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
u32 index = kvm_rcx_read(&svm->vcpu);
if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) {
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
@ -4209,7 +4209,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
static int rdmsr_interception(struct vcpu_svm *svm)
{
u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
u32 ecx = kvm_rcx_read(&svm->vcpu);
struct msr_data msr_info;
msr_info.index = ecx;
@ -4221,10 +4221,8 @@ static int rdmsr_interception(struct vcpu_svm *svm)
} else {
trace_kvm_msr_read(ecx, msr_info.data);
kvm_register_write(&svm->vcpu, VCPU_REGS_RAX,
msr_info.data & 0xffffffff);
kvm_register_write(&svm->vcpu, VCPU_REGS_RDX,
msr_info.data >> 32);
kvm_rax_write(&svm->vcpu, msr_info.data & 0xffffffff);
kvm_rdx_write(&svm->vcpu, msr_info.data >> 32);
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
return kvm_skip_emulated_instruction(&svm->vcpu);
}
@ -4418,7 +4416,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
static int wrmsr_interception(struct vcpu_svm *svm)
{
struct msr_data msr;
u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
u32 ecx = kvm_rcx_read(&svm->vcpu);
u64 data = kvm_read_edx_eax(&svm->vcpu);
msr.data = data;

2
arch/x86/kvm/vmx/vmx.c
View File

@ -4926,7 +4926,7 @@ static int handle_wbinvd(struct kvm_vcpu *vcpu)
static int handle_xsetbv(struct kvm_vcpu *vcpu)
{
u64 new_bv = kvm_read_edx_eax(vcpu);
u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX);
u32 index = kvm_rcx_read(vcpu);
if (kvm_set_xcr(vcpu, index, new_bv) == 0)
return kvm_skip_emulated_instruction(vcpu);

89
arch/x86/kvm/x86.c
View File

@ -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);