AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-23 06:43:06 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
21be4ca1ea
linux_dsm_epyc7002/arch/x86/kvm/lapic.h
Sean Christopherson c3941d9e0c KVM: lapic: Allow user to disable adaptive tuning of timer advancement 
The introduction of adaptive tuning of lapic timer advancement did not
allow for the scenario where userspace would want to disable adaptive
tuning but still employ timer advancement, e.g. for testing purposes or
to handle a use case where adaptive tuning is unable to settle on a
suitable time.  This is epecially pertinent now that KVM places a hard
threshold on the maximum advancment time.

Rework the timer semantics to accept signed values, with a value of '-1'
being interpreted as "use adaptive tuning with KVM's internal default",
and any other value being used as an explicit advancement time, e.g. a
time of '0' effectively disables advancement.

Note, this does not completely restore the original behavior of
lapic_timer_advance_ns.  Prior to tracking the advancement per vCPU,
which is necessary to support autotuning, userspace could adjust
lapic_timer_advance_ns for *running* vCPU.  With per-vCPU tracking, the
module params are snapshotted at vCPU creation, i.e. applying a new
advancement effectively requires restarting a VM.

Dynamically updating a running vCPU is possible, e.g. a helper could be
added to retrieve the desired delay, choosing between the global module
param and the per-VCPU value depending on whether or not auto-tuning is
(globally) enabled, but introduces a great deal of complexity.  The
wrapper itself is not complex, but understanding and documenting the
effects of dynamically toggling auto-tuning and/or adjusting the timer
advancement is nigh impossible since the behavior would be dependent on
KVM's implementation as well as compiler optimizations.  In other words,
providing stable behavior would require extremely careful consideration
now and in the future.

Given that the expected use of a manually-tuned timer advancement is to
"tune once, run many", use the vastly simpler approach of recognizing
changes to the module params only when creating a new vCPU.

Cc: Liran Alon <liran.alon@oracle.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Cc: stable@vger.kernel.org
Fixes: 3b8a5df6c4 ("KVM: LAPIC: Tune lapic_timer_advance_ns automatically")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-04-18 18:56:15 +02:00

240 lines
7.4 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_X86_LAPIC_H
#define __KVM_X86_LAPIC_H
#include <kvm/iodev.h>
#include <linux/kvm_host.h>
#define KVM_APIC_INIT 0
#define KVM_APIC_SIPI 1
#define KVM_APIC_LVT_NUM 6
#define KVM_APIC_SHORT_MASK 0xc0000
#define KVM_APIC_DEST_MASK 0x800
#define APIC_BUS_CYCLE_NS 1
#define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS)
enum lapic_mode {
LAPIC_MODE_DISABLED = 0,
LAPIC_MODE_INVALID = X2APIC_ENABLE,
LAPIC_MODE_XAPIC = MSR_IA32_APICBASE_ENABLE,
LAPIC_MODE_X2APIC = MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE,
};
struct kvm_timer {
struct hrtimer timer;
s64 period; /* unit: ns */
ktime_t target_expiration;
u32 timer_mode;
u32 timer_mode_mask;
u64 tscdeadline;
u64 expired_tscdeadline;
u32 timer_advance_ns;
atomic_t pending; /* accumulated triggered timers */
bool hv_timer_in_use;
bool timer_advance_adjust_done;
};
struct kvm_lapic {
unsigned long base_address;
struct kvm_io_device dev;
struct kvm_timer lapic_timer;
u32 divide_count;
struct kvm_vcpu *vcpu;
bool sw_enabled;
bool irr_pending;
bool lvt0_in_nmi_mode;
/* Number of bits set in ISR. */
s16 isr_count;
/* The highest vector set in ISR; if -1 - invalid, must scan ISR. */
int highest_isr_cache;
/**
* APIC register page. The layout matches the register layout seen by
* the guest 1:1, because it is accessed by the vmx microcode.
* Note: Only one register, the TPR, is used by the microcode.
*/
void *regs;
gpa_t vapic_addr;
struct gfn_to_hva_cache vapic_cache;
unsigned long pending_events;
unsigned int sipi_vector;
};
struct dest_map;
int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
void kvm_free_lapic(struct kvm_vcpu *vcpu);
int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu);
int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
void kvm_apic_accept_events(struct kvm_vcpu *vcpu);
void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event);
u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
void kvm_apic_set_version(struct kvm_vcpu *vcpu);
int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val);
int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
void *data);
bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, unsigned int dest, int dest_mode);
bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr);
bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr);
void kvm_apic_update_ppr(struct kvm_vcpu *vcpu);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
struct dest_map *dest_map);
int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map);
u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu);
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
{
return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
}
int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
void kvm_lapic_init(void);
void kvm_lapic_exit(void);
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
static inline void kvm_lapic_set_vector(int vec, void *bitmap)
{
set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}
static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic)
{
kvm_lapic_set_vector(vec, apic->regs + APIC_IRR);
/*
* irr_pending must be true if any interrupt is pending; set it after
* APIC_IRR to avoid race with apic_clear_irr
*/
apic->irr_pending = true;
}
static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off)
{
return *((u32 *) (apic->regs + reg_off));
}
static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
*((u32 *) (apic->regs + reg_off)) = val;
}
extern struct static_key kvm_no_apic_vcpu;
static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu)
{
if (static_key_false(&kvm_no_apic_vcpu))
return vcpu->arch.apic;
return true;
}
extern struct static_key_deferred apic_hw_disabled;
static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
{
if (static_key_false(&apic_hw_disabled.key))
return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
return MSR_IA32_APICBASE_ENABLE;
}
extern struct static_key_deferred apic_sw_disabled;
static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic)
{
if (static_key_false(&apic_sw_disabled.key))
return apic->sw_enabled;
return true;
}
static inline bool kvm_apic_present(struct kvm_vcpu *vcpu)
{
return lapic_in_kernel(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic);
}
static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
{
return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic);
}
static inline int apic_x2apic_mode(struct kvm_lapic *apic)
{
return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
}
static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu)
{
return vcpu->arch.apic && vcpu->arch.apicv_active;
}
static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
{
return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events;
}
static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
{
return (irq->delivery_mode == APIC_DM_LOWEST ||
irq->msi_redir_hint);
}
static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
{
return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
}
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
void wait_lapic_expire(struct kvm_vcpu *vcpu);
bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
const unsigned long *bitmap, u32 bitmap_size);
void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu);
void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu);
void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu);
bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu);
void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu);
static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
{
return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
}
#endif
Reference in New Issue View Git Blame Copy Permalink