This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip. Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core. With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.
Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.
To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread. In addition we extend the core_info struct to
have information on each subcore. When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.
Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode. It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.
This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap. In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered. The default is 6.
With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch. These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.
It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest. In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path. In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@xxxxxxxxx>
---
arch/powerpc/include/asm/kvm_book3s_asm.h | 20 ++
arch/powerpc/include/asm/kvm_host.h | 3 +
arch/powerpc/kernel/asm-offsets.c | 7 +
arch/powerpc/kvm/book3s_hv.c | 369 ++++++++++++++++++++++++++----
arch/powerpc/kvm/book3s_hv_builtin.c | 25 +-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 113 +++++++--
6 files changed, 475 insertions(+), 62 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 5bdfb5d..4024d24 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -25,6 +25,12 @@
#define XICS_MFRR 0xc
#define XICS_IPI 2 /* interrupt source # for IPIs */
+/* Maximum number of threads per physical core */
+#define MAX_THREADS 8
+
+/* Maximum number of subcores per physical core */
+#define MAX_SUBCORES 4
+
#ifdef __ASSEMBLY__
#ifdef CONFIG_KVM_BOOK3S_HANDLER
@@ -65,6 +71,19 @@ kvmppc_resume_\intno:
#else /*__ASSEMBLY__ */
+struct kvmppc_vcore;
+
+/* Struct used for coordinating micro-threading (split-core) mode changes */
+struct kvm_split_mode {
+ unsigned long rpr;
+ unsigned long pmmar;
+ unsigned long ldbar;
+ u8 subcore_size;
+ u8 do_nap;
+ u8 napped[MAX_THREADS];
+ struct kvmppc_vcore *master_vcs[MAX_SUBCORES];
+};
+
/*
* 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
@@ -100,6 +119,7 @@ struct kvmppc_host_state {
u64 host_spurr;
u64 host_dscr;
u64 dec_expires;
+ struct kvm_split_mode *kvm_split_mode;
#endif
#ifdef CONFIG_PPC_BOOK3S_64
u64 cfar;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 2b74490..80eb29a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -302,6 +302,9 @@ struct kvmppc_vcore {
#define VCORE_EXIT_MAP(vc) ((vc)->entry_exit_map >> 8)
#define VCORE_IS_EXITING(vc) (VCORE_EXIT_MAP(vc) != 0)
+/* This bit is used when a vcore exit is triggered from outside the vcore */
+#define VCORE_EXIT_REQ 0x10000
+
/*
* Values for vcore_state.
* Note that these are arranged such that lower values
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d333664..c3e11e0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -676,7 +676,14 @@ int main(void)
HSTATE_FIELD(HSTATE_DSCR, host_dscr);
HSTATE_FIELD(HSTATE_DABR, dabr);
HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+ HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
DEFINE(IPI_PRIORITY, IPI_PRIORITY);
+ DEFINE(KVM_SPLIT_RPR, offsetof(struct kvm_split_mode, rpr));
+ DEFINE(KVM_SPLIT_PMMAR, offsetof(struct kvm_split_mode, pmmar));
+ DEFINE(KVM_SPLIT_LDBAR, offsetof(struct kvm_split_mode, ldbar));
+ DEFINE(KVM_SPLIT_SIZE, offsetof(struct kvm_split_mode, subcore_size));
+ DEFINE(KVM_SPLIT_DO_NAP, offsetof(struct kvm_split_mode, do_nap));
+ DEFINE(KVM_SPLIT_NAPPED, offsetof(struct kvm_split_mode, napped));
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2048309..32377de 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -81,6 +81,9 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
#define MPP_BUFFER_ORDER 3
#endif
+static int dynamic_mt_modes = 6;
+module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes");
