linux_dsm_epyc7002/arch/powerpc/kvm
Paul Mackerras 371fefd6f2 KVM: PPC: Allow book3s_hv guests to use SMT processor modes
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>
2011-07-12 13:16:57 +03:00
..
44x_emulate.c KVM: PPC: fix exit accounting for SPRs, tlbwe, tlbsx 2011-05-22 08:47:47 -04:00
44x_tlb.c KVM: PPC: e500: Add shadow PID support 2011-07-12 13:16:39 +03:00
44x_tlb.h KVM: ppc: rename 44x MMU functions used in booke.c 2009-03-24 11:02:56 +02:00
44x.c KVM: PPC: booke: add sregs support 2011-05-22 08:47:53 -04:00
book3s_32_mmu_host.c KVM: PPC: Implement correct SID mapping on Book3s_32 2010-10-24 10:52:15 +02:00
book3s_32_mmu.c KVM: PPC: Put segment registers in shared page 2010-10-24 10:52:11 +02:00
book3s_32_sr.S KVM: PPC: Add SR swapping code 2010-05-17 12:18:17 +03:00
book3s_64_mmu_host.c KVM: PPC: Implement correct SID mapping on Book3s_32 2010-10-24 10:52:15 +02:00
book3s_64_mmu_hv.c KVM: PPC: Add support for Book3S processors in hypervisor mode 2011-07-12 13:16:54 +03:00
book3s_64_mmu.c KVM: PPC: Move fields between struct kvm_vcpu_arch and kvmppc_vcpu_book3s 2011-07-12 13:16:46 +03:00
book3s_64_slb.S KVM: PPC: Make SLB switching code the new segment framework 2010-05-17 12:18:38 +03:00
book3s_64_vio_hv.c KVM: PPC: Accelerate H_PUT_TCE by implementing it in real mode 2011-07-12 13:16:56 +03:00
book3s_emulate.c KVM: PPC: Move BAT handling code into spr handler 2010-10-24 10:52:10 +02:00
book3s_exports.c KVM: PPC: Add support for Book3S processors in hypervisor mode 2011-07-12 13:16:54 +03:00
book3s_hv_interrupts.S KVM: PPC: Add support for Book3S processors in hypervisor mode 2011-07-12 13:16:54 +03:00
book3s_hv_rm_mmu.c KVM: PPC: Handle some PAPR hcalls in the kernel 2011-07-12 13:16:55 +03:00
book3s_hv_rmhandlers.S KVM: PPC: Allow book3s_hv guests to use SMT processor modes 2011-07-12 13:16:57 +03:00
book3s_hv.c KVM: PPC: Allow book3s_hv guests to use SMT processor modes 2011-07-12 13:16:57 +03:00
book3s_interrupts.S KVM: PPC: Split host-state fields out of kvmppc_book3s_shadow_vcpu 2011-07-12 13:16:53 +03:00
book3s_mmu_hpte.c KVM: PPC: Move fields between struct kvm_vcpu_arch and kvmppc_vcpu_book3s 2011-07-12 13:16:46 +03:00
book3s_paired_singles.c Merge branch 'kvm-updates/2.6.37' of git://git.kernel.org/pub/scm/virt/kvm/kvm 2010-10-24 12:47:25 -07:00
book3s_pr.c KVM: PPC: Move guest enter/exit down into subarch-specific code 2011-07-12 13:16:51 +03:00
book3s_rmhandlers.S KVM: PPC: Split host-state fields out of kvmppc_book3s_shadow_vcpu 2011-07-12 13:16:53 +03:00
book3s_segment.S KVM: PPC: Add support for Book3S processors in hypervisor mode 2011-07-12 13:16:54 +03:00
book3s.c KVM: PPC: Deliver program interrupts right away instead of queueing them 2011-07-12 13:16:49 +03:00
booke_emulate.c KVM: PPC: Convert SRR0 and SRR1 to shared page 2010-10-24 10:50:45 +02:00
booke_interrupts.S KVM: PPC: e500: Add shadow PID support 2011-07-12 13:16:39 +03:00
booke.c KVM: PPC: Move guest enter/exit down into subarch-specific code 2011-07-12 13:16:51 +03:00
booke.h KVM: PPC: e500: Add shadow PID support 2011-07-12 13:16:39 +03:00
e500_emulate.c KVM: PPC: e500: Add shadow PID support 2011-07-12 13:16:39 +03:00
e500_tlb.c KVM: PPC: e500: Don't search over the entire TLB0. 2011-07-12 13:16:40 +03:00
e500_tlb.h KVM: PPC: e500: Add shadow PID support 2011-07-12 13:16:39 +03:00
e500.c KVM: PPC: e500: Save/restore SPE state 2011-07-12 13:16:32 +03:00
emulate.c KVM: PPC: booke: add sregs support 2011-05-22 08:47:53 -04:00
fpu.S powerpc: Remove fpscr use from [kvm_]cvt_{fd,df} 2010-09-02 14:07:32 +10:00
Kconfig KVM: PPC: Add support for Book3S processors in hypervisor mode 2011-07-12 13:16:54 +03:00
Makefile KVM: PPC: Accelerate H_PUT_TCE by implementing it in real mode 2011-07-12 13:16:56 +03:00
powerpc.c KVM: PPC: Allow book3s_hv guests to use SMT processor modes 2011-07-12 13:16:57 +03:00
timing.c KVM: PPC: fix partial application of "exit timing in ticks" 2011-07-12 13:16:28 +03:00
timing.h KVM: powerpc: Fix BUILD_BUG_ON condition 2009-12-03 09:32:22 +02:00
trace.h KVM: PPC: Add support for Book3S processors in hypervisor mode 2011-07-12 13:16:54 +03:00