KVM: x86: Update vPMCs when retiring branch instructions

When KVM retires a guest branch instruction through emulation,
increment any vPMCs that are configured to monitor "branch
instructions retired," and update the sample period of those counters
so that they will overflow at the right time.

Signed-off-by: Eric Hankland <ehankland@google.com>
[jmattson:
  - Split the code to increment "branch instructions retired" into a
    separate commit.
  - Moved/consolidated the calls to kvm_pmu_trigger_event() in the
    emulation of VMLAUNCH/VMRESUME to accommodate the evolution of
    that code.
]
Fixes: f5132b01386b ("KVM: Expose a version 2 architectural PMU to a guests")
Signed-off-by: Jim Mattson <jmattson@google.com>
Message-Id: <20211130074221.93635-7-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 28b1a4e57827e0c8474adf566d2c07b87dbcc51d..166a145fc1e6933284b0f26454fc05408152f420 100644 (file)
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -175,6 +175,7 @@
 #define No16       ((u64)1 << 53)  /* No 16 bit operand */
 #define IncSP       ((u64)1 << 54)  /* SP is incremented before ModRM calc */
 #define TwoMemOp    ((u64)1 << 55)  /* Instruction has two memory operand */
+#define IsBranch    ((u64)1 << 56)  /* Instruction is considered a branch. */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -191,8 +192,9 @@
 #define FASTOP_SIZE 8
 
 struct opcode {
-       u64 flags : 56;
-       u64 intercept : 8;
+       u64 flags;
+       u8 intercept;
+       u8 pad[7];
        union {
                int (*execute)(struct x86_emulate_ctxt *ctxt);
                const struct opcode *group;
@@ -4364,10 +4366,10 @@ static const struct opcode group4[] = {
 static const struct opcode group5[] = {
        F(DstMem | SrcNone | Lock,              em_inc),
        F(DstMem | SrcNone | Lock,              em_dec),
-       I(SrcMem | NearBranch,                  em_call_near_abs),
-       I(SrcMemFAddr | ImplicitOps,            em_call_far),
-       I(SrcMem | NearBranch,                  em_jmp_abs),
-       I(SrcMemFAddr | ImplicitOps,            em_jmp_far),
+       I(SrcMem | NearBranch | IsBranch,       em_call_near_abs),
+       I(SrcMemFAddr | ImplicitOps | IsBranch, em_call_far),
+       I(SrcMem | NearBranch | IsBranch,       em_jmp_abs),
+       I(SrcMemFAddr | ImplicitOps | IsBranch, em_jmp_far),
        I(SrcMem | Stack | TwoMemOp,            em_push), D(Undefined),
 };
 
@@ -4577,7 +4579,7 @@ static const struct opcode opcode_table[256] = {
        I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */
        I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */
        /* 0x70 - 0x7F */
-       X16(D(SrcImmByte | NearBranch)),
+       X16(D(SrcImmByte | NearBranch | IsBranch)),
        /* 0x80 - 0x87 */
        G(ByteOp | DstMem | SrcImm, group1),
        G(DstMem | SrcImm, group1),
@@ -4596,7 +4598,7 @@ static const struct opcode opcode_table[256] = {
        DI(SrcAcc | DstReg, pause), X7(D(SrcAcc | DstReg)),
        /* 0x98 - 0x9F */
        D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd),
-       I(SrcImmFAddr | No64, em_call_far), N,
+       I(SrcImmFAddr | No64 | IsBranch, em_call_far), N,
        II(ImplicitOps | Stack, em_pushf, pushf),
        II(ImplicitOps | Stack, em_popf, popf),
        I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf),
@@ -4616,17 +4618,19 @@ static const struct opcode opcode_table[256] = {
        X8(I(DstReg | SrcImm64 | Mov, em_mov)),
        /* 0xC0 - 0xC7 */
        G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2),
-       I(ImplicitOps | NearBranch | SrcImmU16, em_ret_near_imm),
-       I(ImplicitOps | NearBranch, em_ret),
+       I(ImplicitOps | NearBranch | SrcImmU16 | IsBranch, em_ret_near_imm),
+       I(ImplicitOps | NearBranch | IsBranch, em_ret),
        I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg),
        I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg),
        G(ByteOp, group11), G(0, group11),
        /* 0xC8 - 0xCF */
-       I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave),
-       I(ImplicitOps | SrcImmU16, em_ret_far_imm),
-       I(ImplicitOps, em_ret_far),
-       D(ImplicitOps), DI(SrcImmByte, intn),
-       D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
+       I(Stack | SrcImmU16 | Src2ImmByte | IsBranch, em_enter),
+       I(Stack | IsBranch, em_leave),
+       I(ImplicitOps | SrcImmU16 | IsBranch, em_ret_far_imm),
+       I(ImplicitOps | IsBranch, em_ret_far),
+       D(ImplicitOps | IsBranch), DI(SrcImmByte | IsBranch, intn),
+       D(ImplicitOps | No64 | IsBranch),
+       II(ImplicitOps | IsBranch, em_iret, iret),
        /* 0xD0 - 0xD7 */
        G(Src2One | ByteOp, group2), G(Src2One, group2),
        G(Src2CL | ByteOp, group2), G(Src2CL, group2),
@@ -4637,14 +4641,15 @@ static const struct opcode opcode_table[256] = {
        /* 0xD8 - 0xDF */
        N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
        /* 0xE0 - 0xE7 */
-       X3(I(SrcImmByte | NearBranch, em_loop)),
-       I(SrcImmByte | NearBranch, em_jcxz),
+       X3(I(SrcImmByte | NearBranch | IsBranch, em_loop)),
+       I(SrcImmByte | NearBranch | IsBranch, em_jcxz),
        I2bvIP(SrcImmUByte | DstAcc, em_in,  in,  check_perm_in),
        I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out),
        /* 0xE8 - 0xEF */
-       I(SrcImm | NearBranch, em_call), D(SrcImm | ImplicitOps | NearBranch),
-       I(SrcImmFAddr | No64, em_jmp_far),
-       D(SrcImmByte | ImplicitOps | NearBranch),
+       I(SrcImm | NearBranch | IsBranch, em_call),
+       D(SrcImm | ImplicitOps | NearBranch | IsBranch),
+       I(SrcImmFAddr | No64 | IsBranch, em_jmp_far),
+       D(SrcImmByte | ImplicitOps | NearBranch | IsBranch),
        I2bvIP(SrcDX | DstAcc, em_in,  in,  check_perm_in),
        I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out),
        /* 0xF0 - 0xF7 */
@@ -4660,7 +4665,7 @@ static const struct opcode opcode_table[256] = {
 static const struct opcode twobyte_table[256] = {
        /* 0x00 - 0x0F */
        G(0, group6), GD(0, &group7), N, N,
-       N, I(ImplicitOps | EmulateOnUD, em_syscall),
+       N, I(ImplicitOps | EmulateOnUD | IsBranch, em_syscall),
        II(ImplicitOps | Priv, em_clts, clts), N,
        DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
        N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N,
@@ -4691,8 +4696,8 @@ static const struct opcode twobyte_table[256] = {
        IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc),
        II(ImplicitOps | Priv, em_rdmsr, rdmsr),
        IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc),
-       I(ImplicitOps | EmulateOnUD, em_sysenter),
-       I(ImplicitOps | Priv | EmulateOnUD, em_sysexit),
+       I(ImplicitOps | EmulateOnUD | IsBranch, em_sysenter),
+       I(ImplicitOps | Priv | EmulateOnUD | IsBranch, em_sysexit),
        N, N,
        N, N, N, N, N, N, N, N,
        /* 0x40 - 0x4F */
@@ -4710,7 +4715,7 @@ static const struct opcode twobyte_table[256] = {
        N, N, N, N,
        N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f),
        /* 0x80 - 0x8F */
-       X16(D(SrcImm | NearBranch)),
+       X16(D(SrcImm | NearBranch | IsBranch)),
        /* 0x90 - 0x9F */
        X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
        /* 0xA0 - 0xA7 */
@@ -5224,6 +5229,8 @@ done_prefixes:
                ctxt->d |= opcode.flags;
        }
 
+       ctxt->is_branch = opcode.flags & IsBranch;
+
        /* Unrecognised? */
        if (ctxt->d == 0)
                return EMULATION_FAILED;

diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 68b420289d7edeb0219073930292a31342bb9c52..39eded2426ffd2f4b2551ab56a2e80b72e352d7e 100644 (file)
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -369,6 +369,7 @@ struct x86_emulate_ctxt {
        struct fetch_cache fetch;
        struct read_cache io_read;
        struct read_cache mem_read;
+       bool is_branch;
 };
 
 /* Repeat String Operation Prefix */

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d07a7fa75783768fd227d6048f2ef9cbaf9854e1..f235f77cbc037a1f1dc819ab5685dab5d34622a2 100644 (file)
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3526,10 +3526,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
        if (evmptrld_status == EVMPTRLD_ERROR) {
                kvm_queue_exception(vcpu, UD_VECTOR);
                return 1;
-       } else if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) {
-               return nested_vmx_failInvalid(vcpu);
        }
 
+       kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+
+       if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
+               return nested_vmx_failInvalid(vcpu);
+
        if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) &&
               vmx->nested.current_vmptr == INVALID_GPA))
                return nested_vmx_failInvalid(vcpu);

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4fbde3a9b9d0d27a304fbaa0184d2035f2f8f715..42bde45a1bc2e3a5c2063435f28643cf011b5d5c 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8255,6 +8255,8 @@ writeback:
                if (!ctxt->have_exception ||
                    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
                        kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS);
+                       if (ctxt->is_branch)
+                               kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
                        kvm_rip_write(vcpu, ctxt->eip);
                        if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
                                r = kvm_vcpu_do_singlestep(vcpu);