linux_dsm_epyc7002/arch/powerpc/include/asm/kvm_book3s_asm.h
Paul Mackerras 19ccb76a19 KVM: PPC: Implement H_CEDE hcall for book3s_hv in real-mode code
With a KVM guest operating in SMT4 mode (i.e. 4 hardware threads per
core), whenever a CPU goes idle, we have to pull all the other
hardware threads in the core out of the guest, because the H_CEDE
hcall is handled in the kernel.  This is inefficient.

This adds code to book3s_hv_rmhandlers.S to handle the H_CEDE hcall
in real mode.  When a guest vcpu does an H_CEDE hcall, we now only
exit to the kernel if all the other vcpus in the same core are also
idle.  Otherwise we mark this vcpu as napping, save state that could
be lost in nap mode (mainly GPRs and FPRs), and execute the nap
instruction.  When the thread wakes up, because of a decrementer or
external interrupt, we come back in at kvm_start_guest (from the
system reset interrupt vector), find the `napping' flag set in the
paca, and go to the resume path.

This has some other ramifications.  First, when starting a core, we
now start all the threads, both those that are immediately runnable and
those that are idle.  This is so that we don't have to pull all the
threads out of the guest when an idle thread gets a decrementer interrupt
and wants to start running.  In fact the idle threads will all start
with the H_CEDE hcall returning; being idle they will just do another
H_CEDE immediately and go to nap mode.

This required some changes to kvmppc_run_core() and kvmppc_run_vcpu().
These functions have been restructured to make them simpler and clearer.
We introduce a level of indirection in the wait queue that gets woken
when external and decrementer interrupts get generated for a vcpu, so
that we can have the 4 vcpus in a vcore using the same wait queue.
We need this because the 4 vcpus are being handled by one thread.

Secondly, when we need to exit from the guest to the kernel, we now
have to generate an IPI for any napping threads, because an HDEC
interrupt doesn't wake up a napping thread.

Thirdly, we now need to be able to handle virtual external interrupts
and decrementer interrupts becoming pending while a thread is napping,
and deliver those interrupts to the guest when the thread wakes.
This is done in kvmppc_cede_reentry, just before fast_guest_return.

Finally, since we are not using the generic kvm_vcpu_block for book3s_hv,
and hence not calling kvm_arch_vcpu_runnable, we can remove the #ifdef
from kvm_arch_vcpu_runnable.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
2011-09-25 19:52:30 +03:00

126 lines
3.1 KiB
C

/*
* 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, write to the Free Software
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright SUSE Linux Products GmbH 2009
*
* Authors: Alexander Graf <agraf@suse.de>
*/
#ifndef __ASM_KVM_BOOK3S_ASM_H__
#define __ASM_KVM_BOOK3S_ASM_H__
#ifdef __ASSEMBLY__
#ifdef CONFIG_KVM_BOOK3S_HANDLER
#include <asm/kvm_asm.h>
.macro DO_KVM intno
.if (\intno == BOOK3S_INTERRUPT_SYSTEM_RESET) || \
(\intno == BOOK3S_INTERRUPT_MACHINE_CHECK) || \
(\intno == BOOK3S_INTERRUPT_DATA_STORAGE) || \
(\intno == BOOK3S_INTERRUPT_INST_STORAGE) || \
(\intno == BOOK3S_INTERRUPT_DATA_SEGMENT) || \
(\intno == BOOK3S_INTERRUPT_INST_SEGMENT) || \
(\intno == BOOK3S_INTERRUPT_EXTERNAL) || \
(\intno == BOOK3S_INTERRUPT_EXTERNAL_HV) || \
(\intno == BOOK3S_INTERRUPT_ALIGNMENT) || \
(\intno == BOOK3S_INTERRUPT_PROGRAM) || \
(\intno == BOOK3S_INTERRUPT_FP_UNAVAIL) || \
(\intno == BOOK3S_INTERRUPT_DECREMENTER) || \
(\intno == BOOK3S_INTERRUPT_SYSCALL) || \
(\intno == BOOK3S_INTERRUPT_TRACE) || \
(\intno == BOOK3S_INTERRUPT_PERFMON) || \
(\intno == BOOK3S_INTERRUPT_ALTIVEC) || \
(\intno == BOOK3S_INTERRUPT_VSX)
b kvmppc_trampoline_\intno
kvmppc_resume_\intno:
.endif
.endm
#else
.macro DO_KVM intno
.endm
#endif /* CONFIG_KVM_BOOK3S_HANDLER */
#else /*__ASSEMBLY__ */
/*
* This struct goes in the PACA on 64-bit processors. It is used
* to store host state that needs to be saved when we enter a guest
* and restored when we exit, but isn't specific to any particular
* guest or vcpu. It also has some scratch fields used by the guest
* exit code.
*/
struct kvmppc_host_state {
ulong host_r1;
ulong host_r2;
ulong host_msr;
ulong vmhandler;
ulong scratch0;
ulong scratch1;
u8 in_guest;
u8 restore_hid5;
u8 napping;
#ifdef CONFIG_KVM_BOOK3S_64_HV
struct kvm_vcpu *kvm_vcpu;
struct kvmppc_vcore *kvm_vcore;
unsigned long xics_phys;
u64 dabr;
u64 host_mmcr[3];
u32 host_pmc[8];
u64 host_purr;
u64 host_spurr;
u64 host_dscr;
u64 dec_expires;
#endif
};
struct kvmppc_book3s_shadow_vcpu {
ulong gpr[14];
u32 cr;
u32 xer;
u32 fault_dsisr;
u32 last_inst;
ulong ctr;
ulong lr;
ulong pc;
ulong shadow_srr1;
ulong fault_dar;
#ifdef CONFIG_PPC_BOOK3S_32
u32 sr[16]; /* Guest SRs */
struct kvmppc_host_state hstate;
#endif
#ifdef CONFIG_PPC_BOOK3S_64
u8 slb_max; /* highest used guest slb entry */
struct {
u64 esid;
u64 vsid;
} slb[64]; /* guest SLB */
#endif
};
#endif /*__ASSEMBLY__ */
#endif /* __ASM_KVM_BOOK3S_ASM_H__ */