371fefd6f2
This lifts the restriction that book3s_hv guests can only run one hardware thread per core, and allows them to use up to 4 threads per core on POWER7. The host still has to run single-threaded. This capability is advertised to qemu through a new KVM_CAP_PPC_SMT capability. The return value of the ioctl querying this capability is the number of vcpus per virtual CPU core (vcore), currently 4. To use this, the host kernel should be booted with all threads active, and then all the secondary threads should be offlined. This will put the secondary threads into nap mode. KVM will then wake them from nap mode and use them for running guest code (while they are still offline). To wake the secondary threads, we send them an IPI using a new xics_wake_cpu() function, implemented in arch/powerpc/sysdev/xics/icp-native.c. In other words, at this stage we assume that the platform has a XICS interrupt controller and we are using icp-native.c to drive it. Since the woken thread will need to acknowledge and clear the IPI, we also export the base physical address of the XICS registers using kvmppc_set_xics_phys() for use in the low-level KVM book3s code. When a vcpu is created, it is assigned to a virtual CPU core. The vcore number is obtained by dividing the vcpu number by the number of threads per core in the host. This number is exported to userspace via the KVM_CAP_PPC_SMT capability. If qemu wishes to run the guest in single-threaded mode, it should make all vcpu numbers be multiples of the number of threads per core. We distinguish three states of a vcpu: runnable (i.e., ready to execute the guest), blocked (that is, idle), and busy in host. We currently implement a policy that the vcore can run only when all its threads are runnable or blocked. This way, if a vcpu needs to execute elsewhere in the kernel or in qemu, it can do so without being starved of CPU by the other vcpus. When a vcore starts to run, it executes in the context of one of the vcpu threads. The other vcpu threads all go to sleep and stay asleep until something happens requiring the vcpu thread to return to qemu, or to wake up to run the vcore (this can happen when another vcpu thread goes from busy in host state to blocked). It can happen that a vcpu goes from blocked to runnable state (e.g. because of an interrupt), and the vcore it belongs to is already running. In that case it can start to run immediately as long as the none of the vcpus in the vcore have started to exit the guest. We send the next free thread in the vcore an IPI to get it to start to execute the guest. It synchronizes with the other threads via the vcore->entry_exit_count field to make sure that it doesn't go into the guest if the other vcpus are exiting by the time that it is ready to actually enter the guest. Note that there is no fixed relationship between the hardware thread number and the vcpu number. Hardware threads are assigned to vcpus as they become runnable, so we will always use the lower-numbered hardware threads in preference to higher-numbered threads if not all the vcpus in the vcore are runnable, regardless of which vcpus are runnable. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
95 lines
2 KiB
ArmAsm
95 lines
2 KiB
ArmAsm
/*
|
|
* This file contains the power_save function for 970-family CPUs.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/threads.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/page.h>
|
|
#include <asm/cputable.h>
|
|
#include <asm/thread_info.h>
|
|
#include <asm/ppc_asm.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/ppc-opcode.h>
|
|
|
|
#undef DEBUG
|
|
|
|
.text
|
|
|
|
_GLOBAL(power7_idle)
|
|
/* Now check if user or arch enabled NAP mode */
|
|
LOAD_REG_ADDRBASE(r3,powersave_nap)
|
|
lwz r4,ADDROFF(powersave_nap)(r3)
|
|
cmpwi 0,r4,0
|
|
beqlr
|
|
|
|
/* NAP is a state loss, we create a regs frame on the
|
|
* stack, fill it up with the state we care about and
|
|
* stick a pointer to it in PACAR1. We really only
|
|
* need to save PC, some CR bits and the NV GPRs,
|
|
* but for now an interrupt frame will do.
|
|
*/
|
|
mflr r0
|
|
std r0,16(r1)
|
|
stdu r1,-INT_FRAME_SIZE(r1)
|
|
std r0,_LINK(r1)
|
|
std r0,_NIP(r1)
|
|
|
|
#ifndef CONFIG_SMP
|
|
/* Make sure FPU, VSX etc... are flushed as we may lose
|
|
* state when going to nap mode
|
|
*/
|
|
bl .discard_lazy_cpu_state
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/* Hard disable interrupts */
|
|
mfmsr r9
|
|
rldicl r9,r9,48,1
|
|
rotldi r9,r9,16
|
|
mtmsrd r9,1 /* hard-disable interrupts */
|
|
li r0,0
|
|
stb r0,PACASOFTIRQEN(r13) /* we'll hard-enable shortly */
|
|
stb r0,PACAHARDIRQEN(r13)
|
|
|
|
/* Continue saving state */
|
|
SAVE_GPR(2, r1)
|
|
SAVE_NVGPRS(r1)
|
|
mfcr r3
|
|
std r3,_CCR(r1)
|
|
std r9,_MSR(r1)
|
|
std r1,PACAR1(r13)
|
|
|
|
/* Magic NAP mode enter sequence */
|
|
std r0,0(r1)
|
|
ptesync
|
|
ld r0,0(r1)
|
|
1: cmp cr0,r0,r0
|
|
bne 1b
|
|
PPC_NAP
|
|
b .
|
|
|
|
_GLOBAL(power7_wakeup_loss)
|
|
ld r1,PACAR1(r13)
|
|
REST_NVGPRS(r1)
|
|
REST_GPR(2, r1)
|
|
ld r3,_CCR(r1)
|
|
ld r4,_MSR(r1)
|
|
ld r5,_NIP(r1)
|
|
addi r1,r1,INT_FRAME_SIZE
|
|
mtcr r3
|
|
mtspr SPRN_SRR1,r4
|
|
mtspr SPRN_SRR0,r5
|
|
rfid
|
|
|
|
_GLOBAL(power7_wakeup_noloss)
|
|
ld r1,PACAR1(r13)
|
|
ld r4,_MSR(r1)
|
|
ld r5,_NIP(r1)
|
|
addi r1,r1,INT_FRAME_SIZE
|
|
mtspr SPRN_SRR1,r4
|
|
mtspr SPRN_SRR0,r5
|
|
rfid
|