mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 02:26:41 +07:00
8577370fb0
The problem: On -rt, an emulated LAPIC timer instances has the following path: 1) hard interrupt 2) ksoftirqd is scheduled 3) ksoftirqd wakes up vcpu thread 4) vcpu thread is scheduled This extra context switch introduces unnecessary latency in the LAPIC path for a KVM guest. The solution: Allow waking up vcpu thread from hardirq context, thus avoiding the need for ksoftirqd to be scheduled. Normal waitqueues make use of spinlocks, which on -RT are sleepable locks. Therefore, waking up a waitqueue waiter involves locking a sleeping lock, which is not allowed from hard interrupt context. cyclictest command line: This patch reduces the average latency in my tests from 14us to 11us. Daniel writes: Paolo asked for numbers from kvm-unit-tests/tscdeadline_latency benchmark on mainline. The test was run 1000 times on tip/sched/core 4.4.0-rc8-01134-g0905f04: ./x86-run x86/tscdeadline_latency.flat -cpu host with idle=poll. The test seems not to deliver really stable numbers though most of them are smaller. Paolo write: "Anything above ~10000 cycles means that the host went to C1 or lower---the number means more or less nothing in that case. The mean shows an improvement indeed." Before: min max mean std count 1000.000000 1000.000000 1000.000000 1000.000000 mean 5162.596000 2019270.084000 5824.491541 20681.645558 std 75.431231 622607.723969 89.575700 6492.272062 min 4466.000000 23928.000000 5537.926500 585.864966 25% 5163.000000 1613252.750000 5790.132275 16683.745433 50% 5175.000000 2281919.000000 5834.654000 23151.990026 75% 5190.000000 2382865.750000 5861.412950 24148.206168 max 5228.000000 4175158.000000 6254.827300 46481.048691 After min max mean std count 1000.000000 1000.00000 1000.000000 1000.000000 mean 5143.511000 2076886.10300 5813.312474 21207.357565 std 77.668322 610413.09583 86.541500 6331.915127 min 4427.000000 25103.00000 5529.756600 559.187707 25% 5148.000000 1691272.75000 5784.889825 17473.518244 50% 5160.000000 2308328.50000 5832.025000 23464.837068 75% 5172.000000 2393037.75000 5853.177675 24223.969976 max 5222.000000 3922458.00000 6186.720500 42520.379830 [Patch was originaly based on the swait implementation found in the -rt tree. Daniel ported it to mainline's version and gathered the benchmark numbers for tscdeadline_latency test.] Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-rt-users@vger.kernel.org Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1455871601-27484-4-git-send-email-wagi@monom.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
327 lines
8.3 KiB
C
327 lines
8.3 KiB
C
/*
|
|
* Copyright (C) 2012 - ARM Ltd
|
|
* Author: Marc Zyngier <marc.zyngier@arm.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program 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 General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#include <linux/preempt.h>
|
|
#include <linux/kvm_host.h>
|
|
#include <linux/wait.h>
|
|
|
|
#include <asm/cputype.h>
|
|
#include <asm/kvm_emulate.h>
|
|
#include <asm/kvm_psci.h>
|
|
#include <asm/kvm_host.h>
|
|
|
|
#include <uapi/linux/psci.h>
|
|
|
|
/*
|
|
* This is an implementation of the Power State Coordination Interface
|
|
* as described in ARM document number ARM DEN 0022A.
|
|
*/
|
|
|
|
#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
|
|
|
|
static unsigned long psci_affinity_mask(unsigned long affinity_level)
|
|
{
|
|
if (affinity_level <= 3)
|
|
return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
|
|
{
|
|
/*
|
|
* NOTE: For simplicity, we make VCPU suspend emulation to be
|
|
* same-as WFI (Wait-for-interrupt) emulation.
|
|
*
|
|
* This means for KVM the wakeup events are interrupts and
|
|
* this is consistent with intended use of StateID as described
|
|
* in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
|
|
*
|
|
* Further, we also treat power-down request to be same as
|
|
* stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
|
|
* specification (ARM DEN 0022A). This means all suspend states
|
|
* for KVM will preserve the register state.
|
|
*/
|
|
kvm_vcpu_block(vcpu);
|
|
|
|
return PSCI_RET_SUCCESS;
|
|
}
|
|
|
|
static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
|
|
{
|
|
vcpu->arch.power_off = true;
|
|
}
|
|
|
|
static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
|
|
{
|
|
struct kvm *kvm = source_vcpu->kvm;
|
|
struct kvm_vcpu *vcpu = NULL;
|
|
struct swait_queue_head *wq;
|
|
unsigned long cpu_id;
|
|
unsigned long context_id;
|
|
phys_addr_t target_pc;
|
|
|
|
cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
|
|
if (vcpu_mode_is_32bit(source_vcpu))
|
|
cpu_id &= ~((u32) 0);
|
|
|
|
vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id);
|
|
|
|
/*
|
|
* Make sure the caller requested a valid CPU and that the CPU is
|
|
* turned off.
|
|
*/
|
|
if (!vcpu)
|
|
return PSCI_RET_INVALID_PARAMS;
|
|
if (!vcpu->arch.power_off) {
|
|
if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
|
|
return PSCI_RET_ALREADY_ON;
|
|
else
|
|
return PSCI_RET_INVALID_PARAMS;
|
|
}
|
|
|
|
target_pc = vcpu_get_reg(source_vcpu, 2);
|
|
context_id = vcpu_get_reg(source_vcpu, 3);
|
|
|
|
kvm_reset_vcpu(vcpu);
|
|
|
|
/* Gracefully handle Thumb2 entry point */
|
|
if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
|
|
target_pc &= ~((phys_addr_t) 1);
|
|
vcpu_set_thumb(vcpu);
|
|
}
|
|
|
|
/* Propagate caller endianness */
|
|
if (kvm_vcpu_is_be(source_vcpu))
|
|
kvm_vcpu_set_be(vcpu);
|
|
|
|
*vcpu_pc(vcpu) = target_pc;
|
|
/*
|
|
* NOTE: We always update r0 (or x0) because for PSCI v0.1
|
|
* the general puspose registers are undefined upon CPU_ON.
|
|
*/
|
|
vcpu_set_reg(vcpu, 0, context_id);
|
|
vcpu->arch.power_off = false;
|
|
smp_mb(); /* Make sure the above is visible */
|
|
|
|
wq = kvm_arch_vcpu_wq(vcpu);
|
|
swake_up(wq);
|
|
|
|
return PSCI_RET_SUCCESS;
|
|
}
|
|
|
|
static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
|
|
{
|
|
int i, matching_cpus = 0;
|
|
unsigned long mpidr;
|
|
unsigned long target_affinity;
|
|
unsigned long target_affinity_mask;
|
|
unsigned long lowest_affinity_level;
|
|
struct kvm *kvm = vcpu->kvm;
|
|
struct kvm_vcpu *tmp;
|
|
|
|
target_affinity = vcpu_get_reg(vcpu, 1);
|
|
lowest_affinity_level = vcpu_get_reg(vcpu, 2);
|
|
|
|
/* Determine target affinity mask */
|
|
target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
|
|
if (!target_affinity_mask)
|
|
return PSCI_RET_INVALID_PARAMS;
|
|
|
|
/* Ignore other bits of target affinity */
|
|
target_affinity &= target_affinity_mask;
|
|
|
|
/*
|
|
* If one or more VCPU matching target affinity are running
|
|
* then ON else OFF
|
|
*/
|
|
kvm_for_each_vcpu(i, tmp, kvm) {
|
|
mpidr = kvm_vcpu_get_mpidr_aff(tmp);
|
|
if ((mpidr & target_affinity_mask) == target_affinity) {
|
|
matching_cpus++;
|
|
if (!tmp->arch.power_off)
|
|
return PSCI_0_2_AFFINITY_LEVEL_ON;
|
|
}
|
|
}
|
|
|
|
if (!matching_cpus)
|
|
return PSCI_RET_INVALID_PARAMS;
|
|
|
|
return PSCI_0_2_AFFINITY_LEVEL_OFF;
|
|
}
|
|
|
|
static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
|
|
{
|
|
int i;
|
|
struct kvm_vcpu *tmp;
|
|
|
|
/*
|
|
* The KVM ABI specifies that a system event exit may call KVM_RUN
|
|
* again and may perform shutdown/reboot at a later time that when the
|
|
* actual request is made. Since we are implementing PSCI and a
|
|
* caller of PSCI reboot and shutdown expects that the system shuts
|
|
* down or reboots immediately, let's make sure that VCPUs are not run
|
|
* after this call is handled and before the VCPUs have been
|
|
* re-initialized.
|
|
*/
|
|
kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
|
|
tmp->arch.power_off = true;
|
|
kvm_vcpu_kick(tmp);
|
|
}
|
|
|
|
memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
|
|
vcpu->run->system_event.type = type;
|
|
vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
|
|
}
|
|
|
|
static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
|
|
{
|
|
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN);
|
|
}
|
|
|
|
static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
|
|
{
|
|
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
|
|
}
|
|
|
|
int kvm_psci_version(struct kvm_vcpu *vcpu)
|
|
{
|
|
if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
|
|
return KVM_ARM_PSCI_0_2;
|
|
|
|
return KVM_ARM_PSCI_0_1;
|
|
}
|
|
|
|
static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
|
|
{
|
|
int ret = 1;
|
|
unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
|
|
unsigned long val;
|
|
|
|
switch (psci_fn) {
|
|
case PSCI_0_2_FN_PSCI_VERSION:
|
|
/*
|
|
* Bits[31:16] = Major Version = 0
|
|
* Bits[15:0] = Minor Version = 2
|
|
*/
|
|
val = 2;
|
|
break;
|
|
case PSCI_0_2_FN_CPU_SUSPEND:
|
|
case PSCI_0_2_FN64_CPU_SUSPEND:
|
|
val = kvm_psci_vcpu_suspend(vcpu);
|
|
break;
|
|
case PSCI_0_2_FN_CPU_OFF:
|
|
kvm_psci_vcpu_off(vcpu);
|
|
val = PSCI_RET_SUCCESS;
|
|
break;
|
|
case PSCI_0_2_FN_CPU_ON:
|
|
case PSCI_0_2_FN64_CPU_ON:
|
|
val = kvm_psci_vcpu_on(vcpu);
|
|
break;
|
|
case PSCI_0_2_FN_AFFINITY_INFO:
|
|
case PSCI_0_2_FN64_AFFINITY_INFO:
|
|
val = kvm_psci_vcpu_affinity_info(vcpu);
|
|
break;
|
|
case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
|
|
/*
|
|
* Trusted OS is MP hence does not require migration
|
|
* or
|
|
* Trusted OS is not present
|
|
*/
|
|
val = PSCI_0_2_TOS_MP;
|
|
break;
|
|
case PSCI_0_2_FN_SYSTEM_OFF:
|
|
kvm_psci_system_off(vcpu);
|
|
/*
|
|
* We should'nt be going back to guest VCPU after
|
|
* receiving SYSTEM_OFF request.
|
|
*
|
|
* If user space accidently/deliberately resumes
|
|
* guest VCPU after SYSTEM_OFF request then guest
|
|
* VCPU should see internal failure from PSCI return
|
|
* value. To achieve this, we preload r0 (or x0) with
|
|
* PSCI return value INTERNAL_FAILURE.
|
|
*/
|
|
val = PSCI_RET_INTERNAL_FAILURE;
|
|
ret = 0;
|
|
break;
|
|
case PSCI_0_2_FN_SYSTEM_RESET:
|
|
kvm_psci_system_reset(vcpu);
|
|
/*
|
|
* Same reason as SYSTEM_OFF for preloading r0 (or x0)
|
|
* with PSCI return value INTERNAL_FAILURE.
|
|
*/
|
|
val = PSCI_RET_INTERNAL_FAILURE;
|
|
ret = 0;
|
|
break;
|
|
default:
|
|
val = PSCI_RET_NOT_SUPPORTED;
|
|
break;
|
|
}
|
|
|
|
vcpu_set_reg(vcpu, 0, val);
|
|
return ret;
|
|
}
|
|
|
|
static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
|
|
{
|
|
unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
|
|
unsigned long val;
|
|
|
|
switch (psci_fn) {
|
|
case KVM_PSCI_FN_CPU_OFF:
|
|
kvm_psci_vcpu_off(vcpu);
|
|
val = PSCI_RET_SUCCESS;
|
|
break;
|
|
case KVM_PSCI_FN_CPU_ON:
|
|
val = kvm_psci_vcpu_on(vcpu);
|
|
break;
|
|
default:
|
|
val = PSCI_RET_NOT_SUPPORTED;
|
|
break;
|
|
}
|
|
|
|
vcpu_set_reg(vcpu, 0, val);
|
|
return 1;
|
|
}
|
|
|
|
/**
|
|
* kvm_psci_call - handle PSCI call if r0 value is in range
|
|
* @vcpu: Pointer to the VCPU struct
|
|
*
|
|
* Handle PSCI calls from guests through traps from HVC instructions.
|
|
* The calling convention is similar to SMC calls to the secure world
|
|
* where the function number is placed in r0.
|
|
*
|
|
* This function returns: > 0 (success), 0 (success but exit to user
|
|
* space), and < 0 (errors)
|
|
*
|
|
* Errors:
|
|
* -EINVAL: Unrecognized PSCI function
|
|
*/
|
|
int kvm_psci_call(struct kvm_vcpu *vcpu)
|
|
{
|
|
switch (kvm_psci_version(vcpu)) {
|
|
case KVM_ARM_PSCI_0_2:
|
|
return kvm_psci_0_2_call(vcpu);
|
|
case KVM_ARM_PSCI_0_1:
|
|
return kvm_psci_0_1_call(vcpu);
|
|
default:
|
|
return -EINVAL;
|
|
};
|
|
}
|