KVM: PPC: Add support for Book3S processors in hypervisor mode
This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode. Using hypervisor mode means
that the guest can use the processor's supervisor mode. That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host. This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.
This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses. That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification. In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.
Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.
This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.
With the guest running in supervisor mode, most exceptions go straight
to the guest. We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest. Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.
We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.
In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount. Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.
The POWER7 processor has a restriction that all threads in a core have
to be in the same partition. MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest. At present we require the host and guest to run
in single-thread mode because of this hardware restriction.
This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA). We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management. This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.
This also adds a few new exports needed by the book3s_hv code.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 069eb9f..4a3f790 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -33,7 +33,9 @@
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 4
+#ifdef CONFIG_KVM_MMIO
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#endif
/* We don't currently support large pages. */
#define KVM_HPAGE_GFN_SHIFT(x) 0
@@ -133,7 +135,26 @@
};
};
+struct kvmppc_pginfo {
+ unsigned long pfn;
+ atomic_t refcnt;
+};
+
struct kvm_arch {
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+ unsigned long hpt_virt;
+ unsigned long ram_npages;
+ unsigned long ram_psize;
+ unsigned long ram_porder;
+ struct kvmppc_pginfo *ram_pginfo;
+ unsigned int lpid;
+ unsigned int host_lpid;
+ unsigned long host_lpcr;
+ unsigned long sdr1;
+ unsigned long host_sdr1;
+ int tlbie_lock;
+ unsigned short last_vcpu[NR_CPUS];
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
};
struct kvmppc_pte {
@@ -190,7 +211,7 @@
ulong rmcall;
ulong host_paca_phys;
struct kvmppc_slb slb[64];
- int slb_max; /* # valid entries in slb[] */
+ int slb_max; /* 1 + index of last valid entry in slb[] */
int slb_nr; /* total number of entries in SLB */
struct kvmppc_mmu mmu;
#endif
@@ -212,7 +233,7 @@
#endif
#ifdef CONFIG_VSX
- u64 vsr[32];
+ u64 vsr[64];
#endif
#ifdef CONFIG_PPC_BOOK3S
@@ -220,18 +241,24 @@
u32 qpr[32];
#endif
-#ifdef CONFIG_BOOKE
ulong pc;
ulong ctr;
ulong lr;
ulong xer;
u32 cr;
-#endif
#ifdef CONFIG_PPC_BOOK3S
ulong hflags;
ulong guest_owned_ext;
+ ulong purr;
+ ulong spurr;
+ ulong lpcr;
+ ulong dscr;
+ ulong amr;
+ ulong uamor;
+ u32 ctrl;
+ ulong dabr;
#endif
u32 vrsave; /* also USPRG0 */
u32 mmucr;
@@ -270,6 +297,9 @@
u32 dbcr1;
u32 dbsr;
+ u64 mmcr[3];
+ u32 pmc[6];
+
#ifdef CONFIG_KVM_EXIT_TIMING
struct mutex exit_timing_lock;
struct kvmppc_exit_timing timing_exit;
@@ -284,8 +314,12 @@
struct dentry *debugfs_exit_timing;
#endif
+#ifdef CONFIG_PPC_BOOK3S
+ ulong fault_dar;
+ u32 fault_dsisr;
+#endif
+
#ifdef CONFIG_BOOKE
- u32 last_inst;
ulong fault_dear;
ulong fault_esr;
ulong queued_dear;
@@ -300,16 +334,25 @@
u8 dcr_is_write;
u8 osi_needed;
u8 osi_enabled;
+ u8 hcall_needed;
u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
struct hrtimer dec_timer;
struct tasklet_struct tasklet;
u64 dec_jiffies;
+ u64 dec_expires;
unsigned long pending_exceptions;
+ u16 last_cpu;
+ u32 last_inst;
+ int trap;
struct kvm_vcpu_arch_shared *shared;
unsigned long magic_page_pa; /* phys addr to map the magic page to */
unsigned long magic_page_ea; /* effect. addr to map the magic page to */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+ struct kvm_vcpu_arch_shared shregs;
+#endif
};
#endif /* __POWERPC_KVM_HOST_H__ */