linux_dsm_epyc7002/arch/x86/kvm/mmu/mmutrace.h
Ben Gardon bb18842e21 kvm: x86/mmu: Add TDP MMU PF handler
Add functions to handle page faults in the TDP MMU. These page faults
are currently handled in much the same way as the x86 shadow paging
based MMU, however the ordering of some operations is slightly
different. Future patches will add eager NX splitting, a fast page fault
handler, and parallel page faults.

Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.

This series can be viewed in Gerrit at:
	https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538

Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20201014182700.2888246-11-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2020-10-23 03:42:04 -04:00

393 lines
8.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#if !defined(_TRACE_KVMMMU_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_KVMMMU_H
#include <linux/tracepoint.h>
#include <linux/trace_events.h>
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvmmmu
#define KVM_MMU_PAGE_FIELDS \
__field(__u8, mmu_valid_gen) \
__field(__u64, gfn) \
__field(__u32, role) \
__field(__u32, root_count) \
__field(bool, unsync)
#define KVM_MMU_PAGE_ASSIGN(sp) \
__entry->mmu_valid_gen = sp->mmu_valid_gen; \
__entry->gfn = sp->gfn; \
__entry->role = sp->role.word; \
__entry->root_count = sp->root_count; \
__entry->unsync = sp->unsync;
#define KVM_MMU_PAGE_PRINTK() ({ \
const char *saved_ptr = trace_seq_buffer_ptr(p); \
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 gen %u gfn %llx l%u %u-byte q%u%s %s%s" \
" %snxe %sad root %u %s%c", \
__entry->mmu_valid_gen, \
__entry->gfn, role.level, \
role.gpte_is_8_bytes ? 8 : 4, \
role.quadrant, \
role.direct ? " direct" : "", \
access_str[role.access], \
role.invalid ? " invalid" : "", \
role.nxe ? "" : "!", \
role.ad_disabled ? "!" : "", \
__entry->root_count, \
__entry->unsync ? "unsync" : "sync", 0); \
saved_ptr; \
})
#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(
__entry->addr = addr;
__entry->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(
__entry->pte = pte;
__entry->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(
__entry->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(
__entry->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)
__entry->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, u64 spte),
TP_ARGS(sptep, gfn, spte),
TP_STRUCT__entry(
__field(void *, sptep)
__field(gfn_t, gfn)
__field(unsigned, access)
__field(unsigned int, gen)
),
TP_fast_assign(
__entry->sptep = sptep;
__entry->gfn = gfn;
__entry->access = spte & ACC_ALL;
__entry->gen = get_mmio_spte_generation(spte);
),
TP_printk("sptep:%p gfn %llx access %x gen %x", __entry->sptep,
__entry->gfn, __entry->access, __entry->gen)
);
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(
__entry->addr = addr;
__entry->gfn = gfn;
__entry->access = access;
),
TP_printk("addr:%llx gfn %llx access %x", __entry->addr, __entry->gfn,
__entry->access)
);
TRACE_EVENT(
fast_page_fault,
TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code,
u64 *sptep, u64 old_spte, int ret),
TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, ret),
TP_STRUCT__entry(
__field(int, vcpu_id)
__field(gpa_t, cr2_or_gpa)
__field(u32, error_code)
__field(u64 *, sptep)
__field(u64, old_spte)
__field(u64, new_spte)
__field(int, ret)
),
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
__entry->cr2_or_gpa = cr2_or_gpa;
__entry->error_code = error_code;
__entry->sptep = sptep;
__entry->old_spte = old_spte;
__entry->new_spte = *sptep;
__entry->ret = ret;
),
TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
" new %llx spurious %d fixed %d", __entry->vcpu_id,
__entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
kvm_mmu_trace_pferr_flags), __entry->sptep,
__entry->old_spte, __entry->new_spte,
__entry->ret == RET_PF_SPURIOUS, __entry->ret == RET_PF_FIXED
)
);
TRACE_EVENT(
kvm_mmu_zap_all_fast,
TP_PROTO(struct kvm *kvm),
TP_ARGS(kvm),
TP_STRUCT__entry(
__field(__u8, mmu_valid_gen)
__field(unsigned int, mmu_used_pages)
),
TP_fast_assign(
__entry->mmu_valid_gen = kvm->arch.mmu_valid_gen;
__entry->mmu_used_pages = kvm->arch.n_used_mmu_pages;
),
TP_printk("kvm-mmu-valid-gen %u used_pages %x",
__entry->mmu_valid_gen, __entry->mmu_used_pages
)
);
TRACE_EVENT(
check_mmio_spte,
TP_PROTO(u64 spte, unsigned int kvm_gen, unsigned int spte_gen),
TP_ARGS(spte, kvm_gen, spte_gen),
TP_STRUCT__entry(
__field(unsigned int, kvm_gen)
__field(unsigned int, spte_gen)
__field(u64, spte)
),
TP_fast_assign(
__entry->kvm_gen = kvm_gen;
__entry->spte_gen = spte_gen;
__entry->spte = spte;
),
TP_printk("spte %llx kvm_gen %x spte-gen %x valid %d", __entry->spte,
__entry->kvm_gen, __entry->spte_gen,
__entry->kvm_gen == __entry->spte_gen
)
);
TRACE_EVENT(
kvm_mmu_set_spte,
TP_PROTO(int level, gfn_t gfn, u64 *sptep),
TP_ARGS(level, gfn, sptep),
TP_STRUCT__entry(
__field(u64, gfn)
__field(u64, spte)
__field(u64, sptep)
__field(u8, level)
/* These depend on page entry type, so compute them now. */
__field(bool, r)
__field(bool, x)
__field(signed char, u)
),
TP_fast_assign(
__entry->gfn = gfn;
__entry->spte = *sptep;
__entry->sptep = virt_to_phys(sptep);
__entry->level = level;
__entry->r = shadow_present_mask || (__entry->spte & PT_PRESENT_MASK);
__entry->x = is_executable_pte(__entry->spte);
__entry->u = shadow_user_mask ? !!(__entry->spte & shadow_user_mask) : -1;
),
TP_printk("gfn %llx spte %llx (%s%s%s%s) level %d at %llx",
__entry->gfn, __entry->spte,
__entry->r ? "r" : "-",
__entry->spte & PT_WRITABLE_MASK ? "w" : "-",
__entry->x ? "x" : "-",
__entry->u == -1 ? "" : (__entry->u ? "u" : "-"),
__entry->level, __entry->sptep
)
);
TRACE_EVENT(
kvm_mmu_spte_requested,
TP_PROTO(gpa_t addr, int level, kvm_pfn_t pfn),
TP_ARGS(addr, level, pfn),
TP_STRUCT__entry(
__field(u64, gfn)
__field(u64, pfn)
__field(u8, level)
),
TP_fast_assign(
__entry->gfn = addr >> PAGE_SHIFT;
__entry->pfn = pfn | (__entry->gfn & (KVM_PAGES_PER_HPAGE(level) - 1));
__entry->level = level;
),
TP_printk("gfn %llx pfn %llx level %d",
__entry->gfn, __entry->pfn, __entry->level
)
);
#endif /* _TRACE_KVMMMU_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH mmu
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE mmutrace
/* This part must be outside protection */
#include <trace/define_trace.h>