Star64_linux/arch/powerpc/include/asm/paca.h
Paul Mackerras de56a948b9 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>
2011-07-12 13:16:54 +03:00

173 lines
5.7 KiB
C

/*
* This control block defines the PACA which defines the processor
* specific data for each logical processor on the system.
* There are some pointers defined that are utilized by PLIC.
*
* C 2001 PPC 64 Team, IBM Corp
*
* 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.
*/
#ifndef _ASM_POWERPC_PACA_H
#define _ASM_POWERPC_PACA_H
#ifdef __KERNEL__
#ifdef CONFIG_PPC64
#include <linux/init.h>
#include <asm/types.h>
#include <asm/lppaca.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/exception-64e.h>
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
#include <asm/kvm_book3s_asm.h>
#endif
register struct paca_struct *local_paca asm("r13");
#if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
/*
* Add standard checks that preemption cannot occur when using get_paca():
* otherwise the paca_struct it points to may be the wrong one just after.
*/
#define get_paca() ((void) debug_smp_processor_id(), local_paca)
#else
#define get_paca() local_paca
#endif
#define get_lppaca() (get_paca()->lppaca_ptr)
#define get_slb_shadow() (get_paca()->slb_shadow_ptr)
struct task_struct;
/*
* Defines the layout of the paca.
*
* This structure is not directly accessed by firmware or the service
* processor.
*/
struct paca_struct {
#ifdef CONFIG_PPC_BOOK3S
/*
* Because hw_cpu_id, unlike other paca fields, is accessed
* routinely from other CPUs (from the IRQ code), we stick to
* read-only (after boot) fields in the first cacheline to
* avoid cacheline bouncing.
*/
struct lppaca *lppaca_ptr; /* Pointer to LpPaca for PLIC */
#endif /* CONFIG_PPC_BOOK3S */
/*
* MAGIC: the spinlock functions in arch/powerpc/lib/locks.c
* load lock_token and paca_index with a single lwz
* instruction. They must travel together and be properly
* aligned.
*/
u16 lock_token; /* Constant 0x8000, used in locks */
u16 paca_index; /* Logical processor number */
u64 kernel_toc; /* Kernel TOC address */
u64 kernelbase; /* Base address of kernel */
u64 kernel_msr; /* MSR while running in kernel */
#ifdef CONFIG_PPC_STD_MMU_64
u64 stab_real; /* Absolute address of segment table */
u64 stab_addr; /* Virtual address of segment table */
#endif /* CONFIG_PPC_STD_MMU_64 */
void *emergency_sp; /* pointer to emergency stack */
u64 data_offset; /* per cpu data offset */
s16 hw_cpu_id; /* Physical processor number */
u8 cpu_start; /* At startup, processor spins until */
/* this becomes non-zero. */
u8 kexec_state; /* set when kexec down has irqs off */
#ifdef CONFIG_PPC_STD_MMU_64
struct slb_shadow *slb_shadow_ptr;
struct dtl_entry *dispatch_log;
struct dtl_entry *dispatch_log_end;
/*
* Now, starting in cacheline 2, the exception save areas
*/
/* used for most interrupts/exceptions */
u64 exgen[11] __attribute__((aligned(0x80)));
u64 exmc[11]; /* used for machine checks */
u64 exslb[11]; /* used for SLB/segment table misses
* on the linear mapping */
/* SLB related definitions */
u16 vmalloc_sllp;
u16 slb_cache_ptr;
u16 slb_cache[SLB_CACHE_ENTRIES];
#endif /* CONFIG_PPC_STD_MMU_64 */
#ifdef CONFIG_PPC_BOOK3E
pgd_t *pgd; /* Current PGD */
pgd_t *kernel_pgd; /* Kernel PGD */
u64 exgen[8] __attribute__((aligned(0x80)));
/* We can have up to 3 levels of reentrancy in the TLB miss handler */
u64 extlb[3][EX_TLB_SIZE / sizeof(u64)] __attribute__((aligned(0x80)));
u64 exmc[8]; /* used for machine checks */
u64 excrit[8]; /* used for crit interrupts */
u64 exdbg[8]; /* used for debug interrupts */
/* Kernel stack pointers for use by special exceptions */
void *mc_kstack;
void *crit_kstack;
void *dbg_kstack;
#endif /* CONFIG_PPC_BOOK3E */
mm_context_t context;
/*
* then miscellaneous read-write fields
*/
struct task_struct *__current; /* Pointer to current */
u64 kstack; /* Saved Kernel stack addr */
u64 stab_rr; /* stab/slb round-robin counter */
u64 saved_r1; /* r1 save for RTAS calls or PM */
u64 saved_msr; /* MSR saved here by enter_rtas */
u16 trap_save; /* Used when bad stack is encountered */
u8 soft_enabled; /* irq soft-enable flag */
u8 hard_enabled; /* set if irqs are enabled in MSR */
u8 io_sync; /* writel() needs spin_unlock sync */
u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */
/* Stuff for accurate time accounting */
u64 user_time; /* accumulated usermode TB ticks */
u64 system_time; /* accumulated system TB ticks */
u64 user_time_scaled; /* accumulated usermode SPURR ticks */
u64 starttime; /* TB value snapshot */
u64 starttime_user; /* TB value on exit to usermode */
u64 startspurr; /* SPURR value snapshot */
u64 utime_sspurr; /* ->user_time when ->startspurr set */
u64 stolen_time; /* TB ticks taken by hypervisor */
u64 dtl_ridx; /* read index in dispatch log */
struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */
#ifdef CONFIG_KVM_BOOK3S_HANDLER
#ifdef CONFIG_KVM_BOOK3S_PR
/* We use this to store guest state in */
struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
#endif
struct kvmppc_host_state kvm_hstate;
#endif
};
extern struct paca_struct *paca;
extern __initdata struct paca_struct boot_paca;
extern void initialise_paca(struct paca_struct *new_paca, int cpu);
extern void setup_paca(struct paca_struct *new_paca);
extern void allocate_pacas(void);
extern void free_unused_pacas(void);
#else /* CONFIG_PPC64 */
static inline void allocate_pacas(void) { };
static inline void free_unused_pacas(void) { };
#endif /* CONFIG_PPC64 */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_PACA_H */