From: Mohamad Gebai Date: Mon, 8 Jul 2013 16:52:22 +0000 (-0400) Subject: Add support for kvm x86 specific tracepoints X-Git-Tag: v2.3.0-rc1~3 X-Git-Url: https://git.lttng.org./?a=commitdiff_plain;h=b3c40230ad700b12c39640d8593aece428a2702b;p=lttng-modules.git Add support for kvm x86 specific tracepoints Two new probes for kvm-x86 and kvm-x86-mmu. Signed-off-by: Mohamad Gebai Signed-off-by: Mathieu Desnoyers --- diff --git a/instrumentation/events/lttng-module/arch/x86/kvm/mmutrace.h b/instrumentation/events/lttng-module/arch/x86/kvm/mmutrace.h new file mode 100644 index 00000000..56ddbabf --- /dev/null +++ b/instrumentation/events/lttng-module/arch/x86/kvm/mmutrace.h @@ -0,0 +1,285 @@ +#if !defined(_TRACE_KVMMMU_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVMMMU_H + +#include +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvmmmu + +#define KVM_MMU_PAGE_FIELDS \ + __field(__u64, gfn) \ + __field(__u32, role) \ + __field(__u32, root_count) \ + __field(bool, unsync) + +#define KVM_MMU_PAGE_ASSIGN(sp) \ + tp_assign(gfn, sp->gfn) \ + tp_assign(role, sp->role.word) \ + tp_assign(root_count, sp->root_count) \ + tp_assign(unsync, sp->unsync) + +#define KVM_MMU_PAGE_PRINTK() ({ \ + const char *ret = p->buffer + p->len; \ + static const char *access_str[] = { \ + "---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" \ + }; \ + union kvm_mmu_page_role role; \ + \ + role.word = __entry->role; \ + \ + trace_seq_printf(p, "sp gfn %llx %u%s q%u%s %s%s" \ + " %snxe root %u %s%c", \ + __entry->gfn, role.level, \ + role.cr4_pae ? " pae" : "", \ + role.quadrant, \ + role.direct ? " direct" : "", \ + access_str[role.access], \ + role.invalid ? " invalid" : "", \ + role.nxe ? "" : "!", \ + __entry->root_count, \ + __entry->unsync ? "unsync" : "sync", 0); \ + ret; \ + }) + +#define kvm_mmu_trace_pferr_flags \ + { PFERR_PRESENT_MASK, "P" }, \ + { PFERR_WRITE_MASK, "W" }, \ + { PFERR_USER_MASK, "U" }, \ + { PFERR_RSVD_MASK, "RSVD" }, \ + { PFERR_FETCH_MASK, "F" } + +/* + * A pagetable walk has started + */ +TRACE_EVENT( + kvm_mmu_pagetable_walk, + TP_PROTO(u64 addr, u32 pferr), + TP_ARGS(addr, pferr), + + TP_STRUCT__entry( + __field(__u64, addr) + __field(__u32, pferr) + ), + + TP_fast_assign( + tp_assign(addr, addr) + tp_assign(pferr, pferr) + ), + + TP_printk("addr %llx pferr %x %s", __entry->addr, __entry->pferr, + __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags)) +) + + +/* We just walked a paging element */ +TRACE_EVENT( + kvm_mmu_paging_element, + TP_PROTO(u64 pte, int level), + TP_ARGS(pte, level), + + TP_STRUCT__entry( + __field(__u64, pte) + __field(__u32, level) + ), + + TP_fast_assign( + tp_assign(pte, pte) + tp_assign(level, level) + ), + + TP_printk("pte %llx level %u", __entry->pte, __entry->level) +) + +DECLARE_EVENT_CLASS(kvm_mmu_set_bit_class, + + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), + + TP_ARGS(table_gfn, index, size), + + TP_STRUCT__entry( + __field(__u64, gpa) + ), + + TP_fast_assign( + tp_assign(gpa, ((u64)table_gfn << PAGE_SHIFT) + + index * size) + ), + + TP_printk("gpa %llx", __entry->gpa) +) + +/* We set a pte accessed bit */ +DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_accessed_bit, + + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), + + TP_ARGS(table_gfn, index, size) +) + +/* We set a pte dirty bit */ +DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_dirty_bit, + + TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size), + + TP_ARGS(table_gfn, index, size) +) + +TRACE_EVENT( + kvm_mmu_walker_error, + TP_PROTO(u32 pferr), + TP_ARGS(pferr), + + TP_STRUCT__entry( + __field(__u32, pferr) + ), + + TP_fast_assign( + tp_assign(pferr, pferr) + ), + + TP_printk("pferr %x %s", __entry->pferr, + __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags)) +) + +TRACE_EVENT( + kvm_mmu_get_page, + TP_PROTO(struct kvm_mmu_page *sp, bool created), + TP_ARGS(sp, created), + + TP_STRUCT__entry( + KVM_MMU_PAGE_FIELDS + __field(bool, created) + ), + + TP_fast_assign( + KVM_MMU_PAGE_ASSIGN(sp) + tp_assign(created, created) + ), + + TP_printk("%s %s", KVM_MMU_PAGE_PRINTK(), + __entry->created ? "new" : "existing") +) + +DECLARE_EVENT_CLASS(kvm_mmu_page_class, + + TP_PROTO(struct kvm_mmu_page *sp), + TP_ARGS(sp), + + TP_STRUCT__entry( + KVM_MMU_PAGE_FIELDS + ), + + TP_fast_assign( + KVM_MMU_PAGE_ASSIGN(sp) + ), + + TP_printk("%s", KVM_MMU_PAGE_PRINTK()) +) + +DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_sync_page, + TP_PROTO(struct kvm_mmu_page *sp), + + TP_ARGS(sp) +) + +DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_unsync_page, + TP_PROTO(struct kvm_mmu_page *sp), + + TP_ARGS(sp) +) + +DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page, + TP_PROTO(struct kvm_mmu_page *sp), + + TP_ARGS(sp) +) + +TRACE_EVENT( + mark_mmio_spte, + TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access), + TP_ARGS(sptep, gfn, access), + + TP_STRUCT__entry( + __field(void *, sptep) + __field(gfn_t, gfn) + __field(unsigned, access) + ), + + TP_fast_assign( + tp_assign(sptep, sptep) + tp_assign(gfn, gfn) + tp_assign(access, access) + ), + + TP_printk("sptep:%p gfn %llx access %x", __entry->sptep, __entry->gfn, + __entry->access) +) + +TRACE_EVENT( + handle_mmio_page_fault, + TP_PROTO(u64 addr, gfn_t gfn, unsigned access), + TP_ARGS(addr, gfn, access), + + TP_STRUCT__entry( + __field(u64, addr) + __field(gfn_t, gfn) + __field(unsigned, access) + ), + + TP_fast_assign( + tp_assign(addr, addr) + tp_assign(gfn, gfn) + tp_assign(access, access) + ), + + TP_printk("addr:%llx gfn %llx access %x", __entry->addr, __entry->gfn, + __entry->access) +) + +#define __spte_satisfied(__spte) \ + (__entry->retry && is_writable_pte(__entry->__spte)) + +TRACE_EVENT( + fast_page_fault, + TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + u64 *sptep, u64 old_spte, bool retry), + TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(gva_t, gva) + __field(u32, error_code) + __field(u64 *, sptep) + __field(u64, old_spte) + __field(u64, new_spte) + __field(bool, retry) + ), + + TP_fast_assign( + tp_assign(vcpu_id, vcpu->vcpu_id) + tp_assign(gva, gva) + tp_assign(error_code, error_code) + tp_assign(sptep, sptep) + tp_assign(old_spte, old_spte) + tp_assign(new_spte, *sptep) + tp_assign(retry, retry) + ), + + TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + " new %llx spurious %d fixed %d", __entry->vcpu_id, + __entry->gva, __print_flags(__entry->error_code, "|", + kvm_mmu_trace_pferr_flags), __entry->sptep, + __entry->old_spte, __entry->new_spte, + __spte_satisfied(old_spte), __spte_satisfied(new_spte) + ) +) +#endif /* _TRACE_KVMMMU_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ../instrumentation/events/lttng-module/arch/x86/kvm +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE mmutrace + +/* This part must be outside protection */ +#include "../../../../../../probes/define_trace.h" diff --git a/instrumentation/events/lttng-module/arch/x86/kvm/trace.h b/instrumentation/events/lttng-module/arch/x86/kvm/trace.h new file mode 100644 index 00000000..8e71a7f5 --- /dev/null +++ b/instrumentation/events/lttng-module/arch/x86/kvm/trace.h @@ -0,0 +1,833 @@ +#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_H + +#include +#include +#include +#include +#include +#include <../arch/x86/kvm/lapic.h> +#include <../arch/x86/kvm/kvm_cache_regs.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm + +/* + * Tracepoint for guest mode entry. + */ +TRACE_EVENT(kvm_entry, + TP_PROTO(unsigned int vcpu_id), + TP_ARGS(vcpu_id), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + ), + + TP_fast_assign( + tp_assign(vcpu_id, vcpu_id) + ), + + TP_printk("vcpu %u", __entry->vcpu_id) +) + +/* + * Tracepoint for hypercall. + */ +TRACE_EVENT(kvm_hypercall, + TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3), + TP_ARGS(nr, a0, a1, a2, a3), + + TP_STRUCT__entry( + __field( unsigned long, nr ) + __field( unsigned long, a0 ) + __field( unsigned long, a1 ) + __field( unsigned long, a2 ) + __field( unsigned long, a3 ) + ), + + TP_fast_assign( + tp_assign(nr, nr) + tp_assign(a0, a0) + tp_assign(a1, a1) + tp_assign(a2, a2) + tp_assign(a3, a3) + ), + + TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx", + __entry->nr, __entry->a0, __entry->a1, __entry->a2, + __entry->a3) +) + +/* + * Tracepoint for hypercall. + */ +TRACE_EVENT(kvm_hv_hypercall, + TP_PROTO(__u16 code, bool fast, __u16 rep_cnt, __u16 rep_idx, + __u64 ingpa, __u64 outgpa), + TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa), + + TP_STRUCT__entry( + __field( __u16, rep_cnt ) + __field( __u16, rep_idx ) + __field( __u64, ingpa ) + __field( __u64, outgpa ) + __field( __u16, code ) + __field( bool, fast ) + ), + + TP_fast_assign( + tp_assign(rep_cnt, rep_cnt) + tp_assign(rep_idx, rep_idx) + tp_assign(ingpa, ingpa) + tp_assign(outgpa, outgpa) + tp_assign(code, code) + tp_assign(fast, fast) + ), + + TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx", + __entry->code, __entry->fast ? "fast" : "slow", + __entry->rep_cnt, __entry->rep_idx, __entry->ingpa, + __entry->outgpa) +) + +/* + * Tracepoint for PIO. + */ +TRACE_EVENT(kvm_pio, + TP_PROTO(unsigned int rw, unsigned int port, unsigned int size, + unsigned int count), + TP_ARGS(rw, port, size, count), + + TP_STRUCT__entry( + __field( unsigned int, rw ) + __field( unsigned int, port ) + __field( unsigned int, size ) + __field( unsigned int, count ) + ), + + TP_fast_assign( + tp_assign(rw, rw) + tp_assign(port, port) + tp_assign(size, size) + tp_assign(count, count) + ), + + TP_printk("pio_%s at 0x%x size %d count %d", + __entry->rw ? "write" : "read", + __entry->port, __entry->size, __entry->count) +) + +/* + * Tracepoint for cpuid. + */ +TRACE_EVENT(kvm_cpuid, + TP_PROTO(unsigned int function, unsigned long rax, unsigned long rbx, + unsigned long rcx, unsigned long rdx), + TP_ARGS(function, rax, rbx, rcx, rdx), + + TP_STRUCT__entry( + __field( unsigned int, function ) + __field( unsigned long, rax ) + __field( unsigned long, rbx ) + __field( unsigned long, rcx ) + __field( unsigned long, rdx ) + ), + + TP_fast_assign( + tp_assign(function, function) + tp_assign(rax, rax) + tp_assign(rbx, rbx) + tp_assign(rcx, rcx) + tp_assign(rdx, rdx) + ), + + TP_printk("func %x rax %lx rbx %lx rcx %lx rdx %lx", + __entry->function, __entry->rax, + __entry->rbx, __entry->rcx, __entry->rdx) +) + +#define AREG(x) { APIC_##x, "APIC_" #x } + +#define kvm_trace_symbol_apic \ + AREG(ID), AREG(LVR), AREG(TASKPRI), AREG(ARBPRI), AREG(PROCPRI), \ + AREG(EOI), AREG(RRR), AREG(LDR), AREG(DFR), AREG(SPIV), AREG(ISR), \ + AREG(TMR), AREG(IRR), AREG(ESR), AREG(ICR), AREG(ICR2), AREG(LVTT), \ + AREG(LVTTHMR), AREG(LVTPC), AREG(LVT0), AREG(LVT1), AREG(LVTERR), \ + AREG(TMICT), AREG(TMCCT), AREG(TDCR), AREG(SELF_IPI), AREG(EFEAT), \ + AREG(ECTRL) +/* + * Tracepoint for apic access. + */ +TRACE_EVENT(kvm_apic, + TP_PROTO(unsigned int rw, unsigned int reg, unsigned int val), + TP_ARGS(rw, reg, val), + + TP_STRUCT__entry( + __field( unsigned int, rw ) + __field( unsigned int, reg ) + __field( unsigned int, val ) + ), + + TP_fast_assign( + tp_assign(rw, rw) + tp_assign(reg, reg) + tp_assign(val, val) + ), + + TP_printk("apic_%s %s = 0x%x", + __entry->rw ? "write" : "read", + __print_symbolic(__entry->reg, kvm_trace_symbol_apic), + __entry->val) +) + +#define trace_kvm_apic_read(reg, val) trace_kvm_apic(0, reg, val) +#define trace_kvm_apic_write(reg, val) trace_kvm_apic(1, reg, val) + +#define KVM_ISA_VMX 1 +#define KVM_ISA_SVM 2 + +/* + * Tracepoint for kvm guest exit: + */ +TRACE_EVENT(kvm_exit, + TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu, u32 isa, u64 info1, u64 info2), + TP_ARGS(exit_reason, vcpu, isa, info1, info2), + + TP_STRUCT__entry( + __field( unsigned int, exit_reason ) + __field( unsigned long, guest_rip ) + __field( u32, isa ) + __field( u64, info1 ) + __field( u64, info2 ) + ), + + TP_fast_assign( + tp_assign(exit_reason, exit_reason) + tp_assign(guest_rip, kvm_rip_read(vcpu)) + tp_assign(isa, isa) + kvm_x86_ops->get_exit_info(vcpu, &info1, + &info2); + tp_assign(info1, info1) + tp_assign(info2, info2) + ), + + TP_printk("reason %s rip info %llx %llx", + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS), + /* __entry->guest_rip,*/ __entry->info1, __entry->info2) +) + +/* + * Tracepoint for kvm interrupt injection: + */ +TRACE_EVENT(kvm_inj_virq, + TP_PROTO(unsigned int irq), + TP_ARGS(irq), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + ), + + TP_fast_assign( + tp_assign(irq, irq) + ), + + TP_printk("irq %u", __entry->irq) +) + +#define EXS(x) { x##_VECTOR, "#" #x } + +#define kvm_trace_sym_exc \ + EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ + EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ + EXS(MF), EXS(MC) + +/* + * Tracepoint for kvm interrupt injection: + */ +TRACE_EVENT(kvm_inj_exception, + TP_PROTO(unsigned exception, bool has_error, unsigned error_code), + TP_ARGS(exception, has_error, error_code), + + TP_STRUCT__entry( + __field( u8, exception ) + __field( u8, has_error ) + __field( u32, error_code ) + ), + + TP_fast_assign( + tp_assign(exception, exception) + tp_assign(has_error, has_error) + tp_assign(error_code, error_code) + ), + + TP_printk("%s (0x%x)", + __print_symbolic(__entry->exception, kvm_trace_sym_exc), + /* FIXME: don't print error_code if not present */ + __entry->has_error ? __entry->error_code : 0) +) + +/* + * Tracepoint for page fault. + */ +TRACE_EVENT(kvm_page_fault, + TP_PROTO(unsigned long fault_address, unsigned int error_code), + TP_ARGS(fault_address, error_code), + + TP_STRUCT__entry( + __field( unsigned long, fault_address ) + __field( unsigned int, error_code ) + ), + + TP_fast_assign( + tp_assign(fault_address, fault_address) + tp_assign(error_code, error_code) + ), + + TP_printk("address %lx error_code %x", + __entry->fault_address, __entry->error_code) +) + +/* + * Tracepoint for guest MSR access. + */ +TRACE_EVENT(kvm_msr, + TP_PROTO(unsigned write, u32 ecx, u64 data, bool exception), + TP_ARGS(write, ecx, data, exception), + + TP_STRUCT__entry( + __field( unsigned, write ) + __field( u32, ecx ) + __field( u64, data ) + __field( u8, exception ) + ), + + TP_fast_assign( + tp_assign(write, write) + tp_assign(ecx, ecx) + tp_assign(data, data) + tp_assign(exception, exception) + ), + + TP_printk("msr_%s %x = 0x%llx%s", + __entry->write ? "write" : "read", + __entry->ecx, __entry->data, + __entry->exception ? " (#GP)" : "") +) + +#define trace_kvm_msr_read(ecx, data) trace_kvm_msr(0, ecx, data, false) +#define trace_kvm_msr_write(ecx, data) trace_kvm_msr(1, ecx, data, false) +#define trace_kvm_msr_read_ex(ecx) trace_kvm_msr(0, ecx, 0, true) +#define trace_kvm_msr_write_ex(ecx, data) trace_kvm_msr(1, ecx, data, true) + +/* + * Tracepoint for guest CR access. + */ +TRACE_EVENT(kvm_cr, + TP_PROTO(unsigned int rw, unsigned int cr, unsigned long val), + TP_ARGS(rw, cr, val), + + TP_STRUCT__entry( + __field( unsigned int, rw ) + __field( unsigned int, cr ) + __field( unsigned long, val ) + ), + + TP_fast_assign( + tp_assign(rw, rw) + tp_assign(cr, cr) + tp_assign(val, val) + ), + + TP_printk("cr_%s %x = 0x%lx", + __entry->rw ? "write" : "read", + __entry->cr, __entry->val) +) + +#define trace_kvm_cr_read(cr, val) trace_kvm_cr(0, cr, val) +#define trace_kvm_cr_write(cr, val) trace_kvm_cr(1, cr, val) + +TRACE_EVENT(kvm_pic_set_irq, + TP_PROTO(__u8 chip, __u8 pin, __u8 elcr, __u8 imr, bool coalesced), + TP_ARGS(chip, pin, elcr, imr, coalesced), + + TP_STRUCT__entry( + __field( __u8, chip ) + __field( __u8, pin ) + __field( __u8, elcr ) + __field( __u8, imr ) + __field( bool, coalesced ) + ), + + TP_fast_assign( + tp_assign(chip, chip) + tp_assign(pin, pin) + tp_assign(elcr, elcr) + tp_assign(imr, imr) + tp_assign(coalesced, coalesced) + ), + + TP_printk("chip %u pin %u (%s%s)%s", + __entry->chip, __entry->pin, + (__entry->elcr & (1 << __entry->pin)) ? "level":"edge", + (__entry->imr & (1 << __entry->pin)) ? "|masked":"", + __entry->coalesced ? " (coalesced)" : "") +) + +#define kvm_apic_dst_shorthand \ + {0x0, "dst"}, \ + {0x1, "self"}, \ + {0x2, "all"}, \ + {0x3, "all-but-self"} + +TRACE_EVENT(kvm_apic_ipi, + TP_PROTO(__u32 icr_low, __u32 dest_id), + TP_ARGS(icr_low, dest_id), + + TP_STRUCT__entry( + __field( __u32, icr_low ) + __field( __u32, dest_id ) + ), + + TP_fast_assign( + tp_assign(icr_low, icr_low) + tp_assign(dest_id, dest_id) + ), + + TP_printk("dst %x vec %u (%s|%s|%s|%s|%s)", + __entry->dest_id, (u8)__entry->icr_low, + __print_symbolic((__entry->icr_low >> 8 & 0x7), + kvm_deliver_mode), + (__entry->icr_low & (1<<11)) ? "logical" : "physical", + (__entry->icr_low & (1<<14)) ? "assert" : "de-assert", + (__entry->icr_low & (1<<15)) ? "level" : "edge", + __print_symbolic((__entry->icr_low >> 18 & 0x3), + kvm_apic_dst_shorthand)) +) + +TRACE_EVENT(kvm_apic_accept_irq, + TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec, bool coalesced), + TP_ARGS(apicid, dm, tm, vec, coalesced), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( __u16, dm ) + __field( __u8, tm ) + __field( __u8, vec ) + __field( bool, coalesced ) + ), + + TP_fast_assign( + tp_assign(apicid, apicid) + tp_assign(dm, dm) + tp_assign(tm, tm) + tp_assign(vec, vec) + tp_assign(coalesced, coalesced) + ), + + TP_printk("apicid %x vec %u (%s|%s)%s", + __entry->apicid, __entry->vec, + __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode), + __entry->tm ? "level" : "edge", + __entry->coalesced ? " (coalesced)" : "") +) + +TRACE_EVENT(kvm_eoi, + TP_PROTO(struct kvm_lapic *apic, int vector), + TP_ARGS(apic, vector), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( int, vector ) + ), + + TP_fast_assign( + tp_assign(apicid, apic->vcpu->vcpu_id) + tp_assign(vector, vector) + ), + + TP_printk("apicid %x vector %d", __entry->apicid, __entry->vector) +) + +TRACE_EVENT(kvm_pv_eoi, + TP_PROTO(struct kvm_lapic *apic, int vector), + TP_ARGS(apic, vector), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( int, vector ) + ), + + TP_fast_assign( + tp_assign(apicid, apic->vcpu->vcpu_id) + tp_assign(vector, vector) + ), + + TP_printk("apicid %x vector %d", __entry->apicid, __entry->vector) +) + +/* + * Tracepoint for nested VMRUN + */ +TRACE_EVENT(kvm_nested_vmrun, + TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl, + __u32 event_inj, bool npt), + TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u64, vmcb ) + __field( __u64, nested_rip ) + __field( __u32, int_ctl ) + __field( __u32, event_inj ) + __field( bool, npt ) + ), + + TP_fast_assign( + tp_assign(rip, rip) + tp_assign(vmcb, vmcb) + tp_assign(nested_rip, nested_rip) + tp_assign(int_ctl, int_ctl) + tp_assign(event_inj, event_inj) + tp_assign(npt, npt) + ), + + TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " + "event_inj: 0x%08x npt: %s", + __entry->rip, __entry->vmcb, __entry->nested_rip, + __entry->int_ctl, __entry->event_inj, + __entry->npt ? "on" : "off") +) + +TRACE_EVENT(kvm_nested_intercepts, + TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept), + TP_ARGS(cr_read, cr_write, exceptions, intercept), + + TP_STRUCT__entry( + __field( __u16, cr_read ) + __field( __u16, cr_write ) + __field( __u32, exceptions ) + __field( __u64, intercept ) + ), + + TP_fast_assign( + tp_assign(cr_read, cr_read) + tp_assign(cr_write, cr_write) + tp_assign(exceptions, exceptions) + tp_assign(intercept, intercept) + ), + + TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx", + __entry->cr_read, __entry->cr_write, __entry->exceptions, + __entry->intercept) +) +/* + * Tracepoint for #VMEXIT while nested + */ +TRACE_EVENT(kvm_nested_vmexit, + TP_PROTO(__u64 rip, __u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa), + TP_ARGS(rip, exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err, isa), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + __field( __u32, isa ) + ), + + TP_fast_assign( + tp_assign(rip, rip) + tp_assign(exit_code, exit_code) + tp_assign(exit_info1, exit_info1) + tp_assign(exit_info2, exit_info2) + tp_assign(exit_int_info, exit_int_info) + tp_assign(exit_int_info_err, exit_int_info_err) + tp_assign(isa, isa) + ), + TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", + __entry->rip, + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +) + +/* + * Tracepoint for #VMEXIT reinjected to the guest + */ +TRACE_EVENT(kvm_nested_vmexit_inject, + TP_PROTO(__u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa), + TP_ARGS(exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err, isa), + + TP_STRUCT__entry( + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + __field( __u32, isa ) + ), + + TP_fast_assign( + tp_assign(exit_code, exit_code) + tp_assign(exit_info1, exit_info1) + tp_assign(exit_info2, exit_info2) + tp_assign(exit_int_info, exit_int_info) + tp_assign(exit_int_info_err, exit_int_info_err) + tp_assign(isa, isa) + ), + + TP_printk("reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +) + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_nested_intr_vmexit, + TP_PROTO(__u64 rip), + TP_ARGS(rip), + + TP_STRUCT__entry( + __field( __u64, rip ) + ), + + TP_fast_assign( + tp_assign(rip, rip) + ), + + TP_printk("rip: 0x%016llx", __entry->rip) +) + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_invlpga, + TP_PROTO(__u64 rip, int asid, u64 address), + TP_ARGS(rip, asid, address), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( int, asid ) + __field( __u64, address ) + ), + + TP_fast_assign( + tp_assign(rip, rip) + tp_assign(asid, asid) + tp_assign(address, address) + ), + + TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", + __entry->rip, __entry->asid, __entry->address) +) + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_skinit, + TP_PROTO(__u64 rip, __u32 slb), + TP_ARGS(rip, slb), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, slb ) + ), + + TP_fast_assign( + tp_assign(rip, rip) + tp_assign(slb, slb) + ), + + TP_printk("rip: 0x%016llx slb: 0x%08x", + __entry->rip, __entry->slb) +) + +#define KVM_EMUL_INSN_F_CR0_PE (1 << 0) +#define KVM_EMUL_INSN_F_EFL_VM (1 << 1) +#define KVM_EMUL_INSN_F_CS_D (1 << 2) +#define KVM_EMUL_INSN_F_CS_L (1 << 3) + +#define kvm_trace_symbol_emul_flags \ + { 0, "real" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_EFL_VM, "vm16" }, \ + { KVM_EMUL_INSN_F_CR0_PE, "prot16" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_D, "prot32" }, \ + { KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_L, "prot64" } + +#define kei_decode_mode(mode) ({ \ + u8 flags = 0xff; \ + switch (mode) { \ + case X86EMUL_MODE_REAL: \ + flags = 0; \ + break; \ + case X86EMUL_MODE_VM86: \ + flags = KVM_EMUL_INSN_F_EFL_VM; \ + break; \ + case X86EMUL_MODE_PROT16: \ + flags = KVM_EMUL_INSN_F_CR0_PE; \ + break; \ + case X86EMUL_MODE_PROT32: \ + flags = KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_D; \ + break; \ + case X86EMUL_MODE_PROT64: \ + flags = KVM_EMUL_INSN_F_CR0_PE \ + | KVM_EMUL_INSN_F_CS_L; \ + break; \ + } \ + flags; \ + }) + +TRACE_EVENT(kvm_emulate_insn, + TP_PROTO(struct kvm_vcpu *vcpu, __u8 failed), + TP_ARGS(vcpu, failed), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, csbase ) + __field( __u8, len ) + __array( __u8, insn, 15 ) + __field( __u8, flags ) + __field( __u8, failed ) + ), + + TP_fast_assign( + tp_assign(rip, vcpu->arch.emulate_ctxt.fetch.start) + tp_assign(csbase, kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS)) + tp_assign(len, vcpu->arch.emulate_ctxt._eip + - vcpu->arch.emulate_ctxt.fetch.start) + tp_memcpy(insn, + vcpu->arch.emulate_ctxt.fetch.data, + 15) + tp_assign(flags, kei_decode_mode(vcpu->arch.emulate_ctxt.mode)) + tp_assign(failed, failed) + ), + + TP_printk("%x:%llx:%s (%s)%s", + __entry->csbase, __entry->rip, + __print_hex(__entry->insn, __entry->len), + __print_symbolic(__entry->flags, + kvm_trace_symbol_emul_flags), + __entry->failed ? " failed" : "" + ) + ) + +#define trace_kvm_emulate_insn_start(vcpu) trace_kvm_emulate_insn(vcpu, 0) +#define trace_kvm_emulate_insn_failed(vcpu) trace_kvm_emulate_insn(vcpu, 1) + +TRACE_EVENT( + vcpu_match_mmio, + TP_PROTO(gva_t gva, gpa_t gpa, bool write, bool gpa_match), + TP_ARGS(gva, gpa, write, gpa_match), + + TP_STRUCT__entry( + __field(gva_t, gva) + __field(gpa_t, gpa) + __field(bool, write) + __field(bool, gpa_match) + ), + + TP_fast_assign( + tp_assign(gva, gva) + tp_assign(gpa, gpa) + tp_assign(write, write) + tp_assign(gpa_match, gpa_match) + ), + + TP_printk("gva %#lx gpa %#llx %s %s", __entry->gva, __entry->gpa, + __entry->write ? "Write" : "Read", + __entry->gpa_match ? "GPA" : "GVA") +) + +#ifdef CONFIG_X86_64 + +#define host_clocks \ + {VCLOCK_NONE, "none"}, \ + {VCLOCK_TSC, "tsc"}, \ + {VCLOCK_HPET, "hpet"} \ + +TRACE_EVENT(kvm_update_master_clock, + TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched), + TP_ARGS(use_master_clock, host_clock, offset_matched), + + TP_STRUCT__entry( + __field( bool, use_master_clock ) + __field( unsigned int, host_clock ) + __field( bool, offset_matched ) + ), + + TP_fast_assign( + tp_assign(use_master_clock, use_master_clock) + tp_assign(host_clock, host_clock) + tp_assign(offset_matched, offset_matched) + ), + + TP_printk("masterclock %d hostclock %s offsetmatched %u", + __entry->use_master_clock, + __print_symbolic(__entry->host_clock, host_clocks), + __entry->offset_matched) +) + +TRACE_EVENT(kvm_track_tsc, + TP_PROTO(unsigned int vcpu_id, unsigned int nr_matched, + unsigned int online_vcpus, bool use_master_clock, + unsigned int host_clock), + TP_ARGS(vcpu_id, nr_matched, online_vcpus, use_master_clock, + host_clock), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( unsigned int, nr_vcpus_matched_tsc ) + __field( unsigned int, online_vcpus ) + __field( bool, use_master_clock ) + __field( unsigned int, host_clock ) + ), + + TP_fast_assign( + tp_assign(vcpu_id, vcpu_id) + tp_assign(nr_vcpus_matched_tsc, nr_matched) + tp_assign(online_vcpus, online_vcpus) + tp_assign(use_master_clock, use_master_clock) + tp_assign(host_clock, host_clock) + ), + + TP_printk("vcpu_id %u masterclock %u offsetmatched %u nr_online %u" + " hostclock %s", + __entry->vcpu_id, __entry->use_master_clock, + __entry->nr_vcpus_matched_tsc, __entry->online_vcpus, + __print_symbolic(__entry->host_clock, host_clocks)) +) + +#endif /* CONFIG_X86_64 */ + +#endif /* _TRACE_KVM_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ../instrumentation/events/lttng-module/arch/x86/kvm +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include "../../../../../../probes/define_trace.h" diff --git a/probes/Makefile b/probes/Makefile index 225803c3..13bf2084 100644 --- a/probes/Makefile +++ b/probes/Makefile @@ -18,7 +18,22 @@ obj-m += lttng-probe-power.o obj-m += lttng-probe-statedump.o ifneq ($(CONFIG_KVM),) -obj-m += lttng-probe-kvm.o +kvm = lttng-probe-kvm.o +ifneq ($(CONFIG_X86),) +kvm_dep = $(srctree)/virt/kvm/iodev.h +kvm_x86 = lttng-probe-kvm-x86.o +kvm_x86_mmu = lttng-probe-kvm-x86-mmu.o +kvm_path = $(srctree)/virt/kvm +ifeq ($(wildcard $(kvm_dep)),) +$(warning Files $(kvm_dep) not found. Probe "kvm" x86-specific is disabled. Use full kernel source tree to enable it.) +kvm_x86 = +kvm_path = +endif +obj-m += $(kvm_x86) +obj-m += $(kvm_x86_mmu) +ccflags-y += -I$(kvm_path) +endif +obj-m += $(kvm) endif obj-m += $(shell \ diff --git a/probes/lttng-probe-kvm-x86-mmu.c b/probes/lttng-probe-kvm-x86-mmu.c new file mode 100644 index 00000000..f0cbf885 --- /dev/null +++ b/probes/lttng-probe-kvm-x86-mmu.c @@ -0,0 +1,43 @@ +/* + * probes/lttng-probe-kvm.c + * + * LTTng kvm probes. + * + * Copyright (C) 2010-2012 Mathieu Desnoyers + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; only + * version 2.1 of the License. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include +#include + +/* + * Create the tracepoint static inlines from the kernel to validate that our + * trace event macros match the kernel we run on. + */ +#include "../wrapper/tracepoint.h" + +/* + * Create LTTng tracepoint probes. + */ +#define LTTNG_PACKAGE_BUILD +#define CREATE_TRACE_POINTS + +#define TRACE_INCLUDE_PATH ../instrumentation/events/lttng-module/arch/x86/kvm +#include "../instrumentation/events/lttng-module/arch/x86/kvm/mmutrace.h" + +MODULE_LICENSE("GPL and additional rights"); +MODULE_AUTHOR("Mathieu Desnoyers "); +MODULE_DESCRIPTION("LTTng kvm mmu probes"); diff --git a/probes/lttng-probe-kvm-x86.c b/probes/lttng-probe-kvm-x86.c new file mode 100644 index 00000000..abc93a89 --- /dev/null +++ b/probes/lttng-probe-kvm-x86.c @@ -0,0 +1,45 @@ +/* + * probes/lttng-probe-kvm.c + * + * LTTng kvm probes. + * + * Copyright (C) 2010-2012 Mathieu Desnoyers + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; only + * version 2.1 of the License. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include +#include + +/* + * Create the tracepoint static inlines from the kernel to validate that our + * trace event macros match the kernel we run on. + */ +#include + +#include "../wrapper/tracepoint.h" + +/* + * Create LTTng tracepoint probes. + */ +#define LTTNG_PACKAGE_BUILD +#define CREATE_TRACE_POINTS + +#define TRACE_INCLUDE_PATH ../instrumentation/events/lttng-module/arch/x86/kvm +#include "../instrumentation/events/lttng-module/arch/x86/kvm/trace.h" + +MODULE_LICENSE("GPL and additional rights"); +MODULE_AUTHOR("Mathieu Desnoyers "); +MODULE_DESCRIPTION("LTTng kvm probes");