* immediately.
*/
compare_cpu_mode_with_primary r4, r5, r6, r7
- movne pc, lr
+ retne lr
/*
* Once we have given up on one CPU, we do not try to install the
*/
cmp r4, #HYP_MODE
- movne pc, lr @ give up if the CPU is not in HYP mode
+ retne lr @ give up if the CPU is not in HYP mode
/*
* Configure HSCTLR to set correct exception endianness/instruction set
mcr p15, 4, r7, c1, c1, 3 @ HSTR
THUMB( orr r7, #(1 << 30) ) @ HSCTLR.TE
- #ifdef CONFIG_CPU_BIG_ENDIAN
- orr r7, #(1 << 9) @ HSCTLR.EE
- #endif
+ ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE
mcr p15, 4, r7, c1, c0, 0 @ HSCTLR
mrc p15, 4, r7, c1, c1, 1 @ HDCR
@ fall through
ENTRY(__hyp_set_vectors)
__HVC(0)
- mov pc, lr
+ ret lr
ENDPROC(__hyp_set_vectors)
#ifndef ZIMAGE
return false;
}
- int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
- {
- return 0;
- }
-
- u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
- {
- return 0;
- }
-
#else
#define NUM_TIMER_REGS 3
int __attribute_const__ kvm_target_cpu(void)
{
- unsigned long implementor = read_cpuid_implementor();
- unsigned long part_number = read_cpuid_part_number();
-
- if (implementor != ARM_CPU_IMP_ARM)
- return -EINVAL;
-
- switch (part_number) {
+ switch (read_cpuid_part()) {
case ARM_CPU_PART_CORTEX_A7:
return KVM_ARM_TARGET_CORTEX_A7;
case ARM_CPU_PART_CORTEX_A15:
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
#include <asm/unified.h>
#include <asm/asm-offsets.h>
#include <asm/kvm_asm.h>
bne phase2 @ Yes, second stage init
@ Set the HTTBR to point to the hypervisor PGD pointer passed
- mcrr p15, 4, r2, r3, c2
+ mcrr p15, 4, rr_lo_hi(r2, r3), c2
@ Set the HTCR and VTCR to the same shareability and cacheability
@ settings as the non-secure TTBCR and with T0SZ == 0.
ldr r0, =TRAMPOLINE_VA
adr r1, target
bfi r0, r1, #0, #PAGE_SHIFT
- mov pc, r0
+ ret r0
target: @ We're now in the trampoline code, switch page tables
- mcrr p15, 4, r2, r3, c2
+ mcrr p15, 4, rr_lo_hi(r2, r3), c2
isb
@ Invalidate the old TLBs
/* IVPR must be 64KiB-aligned. */
#define VCPU_SIZE_ORDER 4
#define VCPU_SIZE_LOG (VCPU_SIZE_ORDER + 12)
- #define VCPU_TLB_PGSZ PPC44x_TLB_64K
#define VCPU_SIZE_BYTES (1<<VCPU_SIZE_LOG)
#define BOOKE_INTERRUPT_CRITICAL 0
#define BOOK3S_INTERRUPT_H_DATA_STORAGE 0xe00
#define BOOK3S_INTERRUPT_H_INST_STORAGE 0xe20
#define BOOK3S_INTERRUPT_H_EMUL_ASSIST 0xe40
+#define BOOK3S_INTERRUPT_HMI 0xe60
#define BOOK3S_INTERRUPT_H_DOORBELL 0xe80
#define BOOK3S_INTERRUPT_PERFMON 0xf00
#define BOOK3S_INTERRUPT_ALTIVEC 0xf20
#define BOOK3S_HFLAG_NATIVE_PS 0x8
#define BOOK3S_HFLAG_MULTI_PGSIZE 0x10
#define BOOK3S_HFLAG_NEW_TLBIE 0x20
+ #define BOOK3S_HFLAG_SPLIT_HACK 0x40
#define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */
#define RESUME_FLAG_HOST (1<<1) /* Resume host? */
#define PPC_INST_ISEL 0x7c00001e
#define PPC_INST_ISEL_MASK 0xfc00003e
#define PPC_INST_LDARX 0x7c0000a8
+ #define PPC_INST_LOGMPP 0x7c0007e4
#define PPC_INST_LSWI 0x7c0004aa
#define PPC_INST_LSWX 0x7c00042a
#define PPC_INST_LWARX 0x7c000028
#define PPC_INST_MCRXR_MASK 0xfc0007fe
#define PPC_INST_MFSPR_PVR 0x7c1f42a6
#define PPC_INST_MFSPR_PVR_MASK 0xfc1fffff
+#define PPC_INST_MFTMR 0x7c0002dc
#define PPC_INST_MSGSND 0x7c00019c
#define PPC_INST_MSGSNDP 0x7c00011c
+#define PPC_INST_MTTMR 0x7c0003dc
#define PPC_INST_NOP 0x60000000
#define PPC_INST_POPCNTB 0x7c0000f4
#define PPC_INST_POPCNTB_MASK 0xfc0007fe
#define __PPC_EH(eh) 0
#endif
+ /* POWER8 Micro Partition Prefetch (MPP) parameters */
+ /* Address mask is common for LOGMPP instruction and MPPR SPR */
+ #define PPC_MPPE_ADDRESS_MASK 0xffffffffc000
+
+ /* Bits 60 and 61 of MPP SPR should be set to one of the following */
+ /* Aborting the fetch is indeed setting 00 in the table size bits */
+ #define PPC_MPPR_FETCH_ABORT (0x0ULL << 60)
+ #define PPC_MPPR_FETCH_WHOLE_TABLE (0x2ULL << 60)
+
+ /* Bits 54 and 55 of register for LOGMPP instruction should be set to: */
+ #define PPC_LOGMPP_LOG_L2 (0x02ULL << 54)
+ #define PPC_LOGMPP_LOG_L2L3 (0x01ULL << 54)
+ #define PPC_LOGMPP_LOG_ABORT (0x03ULL << 54)
+
/* Deal with instructions that older assemblers aren't aware of */
#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_INST_DCBAL | \
__PPC_RA(a) | __PPC_RB(b))
#define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LDARX | \
___PPC_RT(t) | ___PPC_RA(a) | \
___PPC_RB(b) | __PPC_EH(eh))
+ #define PPC_LOGMPP(b) stringify_in_c(.long PPC_INST_LOGMPP | \
+ __PPC_RB(b))
#define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \
___PPC_RT(t) | ___PPC_RA(a) | \
___PPC_RB(b) | __PPC_EH(eh))
#define TABORT(r) stringify_in_c(.long PPC_INST_TABORT \
| __PPC_RA(r))
+/* book3e thread control instructions */
+#define TMRN(x) ((((x) & 0x1f) << 16) | (((x) & 0x3e0) << 6))
+#define MTTMR(tmr, r) stringify_in_c(.long PPC_INST_MTTMR | \
+ TMRN(tmr) | ___PPC_RS(r))
+#define MFTMR(tmr, r) stringify_in_c(.long PPC_INST_MFTMR | \
+ TMRN(tmr) | ___PPC_RT(r))
+
#endif /* _ASM_POWERPC_PPC_OPCODE_H */
#define CTRL_TE 0x00c00000 /* thread enable */
#define CTRL_RUNLATCH 0x1
#define SPRN_DAWR 0xB4
+ #define SPRN_MPPR 0xB8 /* Micro Partition Prefetch Register */
#define SPRN_RPR 0xBA /* Relative Priority Register */
#define SPRN_CIABR 0xBB
#define CIABR_PRIV 0x3
#define DSISR_PROTFAULT 0x08000000 /* protection fault */
#define DSISR_ISSTORE 0x02000000 /* access was a store */
#define DSISR_DABRMATCH 0x00400000 /* hit data breakpoint */
-#define DSISR_NOSEGMENT 0x00200000 /* STAB/SLB miss */
+#define DSISR_NOSEGMENT 0x00200000 /* SLB miss */
#define DSISR_KEYFAULT 0x00200000 /* Key fault */
#define SPRN_TBRL 0x10C /* Time Base Read Lower Register (user, R/O) */
#define SPRN_TBRU 0x10D /* Time Base Read Upper Register (user, R/O) */
* readable variant for reads, which can avoid a fault
* with KVM type virtualization.
*
- * (*) Under KVM, the host SPRG1 is used to point to
- * the current VCPU data structure
- *
* 32-bit 8xx:
* - SPRG0 scratch for exception vectors
* - SPRG1 scratch for exception vectors
: "r" ((unsigned long)(v)) \
: "memory")
+ static inline unsigned long mfvtb (void)
+ {
+ #ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ return mfspr(SPRN_VTB);
+ #endif
+ return 0;
+ }
+
#ifdef __powerpc64__
#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E)
#define mftb() ({unsigned long rval; \
#endif /* CONFIG_PPC_BOOK3E */
#ifdef CONFIG_PPC_STD_MMU_64
- DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real));
- DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr));
DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp));
DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
+ DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
+ DEFINE(VCPU_SPRG9, offsetof(struct kvm_vcpu, arch.sprg9));
DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
common-objs-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
$(KVM)/eventfd.o
- CFLAGS_44x_tlb.o := -I.
CFLAGS_e500_mmu.o := -I.
CFLAGS_e500_mmu_host.o := -I.
CFLAGS_emulate.o := -I.
+ CFLAGS_emulate_loadstore.o := -I.
- common-objs-y += powerpc.o emulate.o
+ common-objs-y += powerpc.o emulate.o emulate_loadstore.o
obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o
AFLAGS_booke_interrupts.o := -I$(obj)
- kvm-440-objs := \
- $(common-objs-y) \
- booke.o \
- booke_emulate.o \
- booke_interrupts.o \
- 44x.o \
- 44x_tlb.o \
- 44x_emulate.o
- kvm-objs-$(CONFIG_KVM_440) := $(kvm-440-objs)
-
kvm-e500-objs := \
$(common-objs-y) \
booke.o \
kvm-pr-y := \
fpu.o \
+ emulate.o \
book3s_paired_singles.o \
book3s_pr.o \
book3s_pr_papr.o \
book3s_hv_rm_mmu.o \
book3s_hv_ras.o \
book3s_hv_builtin.o \
- book3s_hv_cma.o \
$(kvm-book3s_64-builtin-xics-objs-y)
endif
$(KVM)/kvm_main.o \
$(KVM)/eventfd.o \
powerpc.o \
- emulate.o \
+ emulate_loadstore.o \
book3s.o \
book3s_64_vio.o \
book3s_rtas.o \
kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
- obj-$(CONFIG_KVM_440) += kvm.o
obj-$(CONFIG_KVM_E500V2) += kvm.o
obj-$(CONFIG_KVM_E500MC) += kvm.o
obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
#include <asm/ppc-opcode.h>
#include <asm/cputable.h>
-#include "book3s_hv_cma.h"
-
/* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
#define MAX_LPID_970 63
}
kvm->arch.hpt_cma_alloc = 0;
- VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER);
page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
if (page) {
hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
+ memset((void *)hpt, 0, (1 << order));
kvm->arch.hpt_cma_alloc = 1;
}
unsigned long slb_v;
unsigned long pp, key;
unsigned long v, gr;
- unsigned long *hptep;
+ __be64 *hptep;
int index;
int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
preempt_enable();
return -ENOENT;
}
- hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
- v = hptep[0] & ~HPTE_V_HVLOCK;
+ hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
+ v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
gr = kvm->arch.revmap[index].guest_rpte;
/* Unlock the HPTE */
asm volatile("lwsync" : : : "memory");
- hptep[0] = v;
+ hptep[0] = cpu_to_be64(v);
preempt_enable();
gpte->eaddr = eaddr;
static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned long gpa, gva_t ea, int is_store)
{
- int ret;
u32 last_inst;
- unsigned long srr0 = kvmppc_get_pc(vcpu);
- /* We try to load the last instruction. We don't let
- * emulate_instruction do it as it doesn't check what
- * kvmppc_ld returns.
+ /*
* If we fail, we just return to the guest and try executing it again.
*/
- if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) {
- ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
- if (ret != EMULATE_DONE || last_inst == KVM_INST_FETCH_FAILED)
- return RESUME_GUEST;
- vcpu->arch.last_inst = last_inst;
- }
+ if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) !=
+ EMULATE_DONE)
+ return RESUME_GUEST;
/*
* WARNING: We do not know for sure whether the instruction we just
* we just return and retry the instruction.
*/
- if (instruction_is_store(kvmppc_get_last_inst(vcpu)) != !!is_store)
+ if (instruction_is_store(last_inst) != !!is_store)
return RESUME_GUEST;
/*
unsigned long ea, unsigned long dsisr)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long *hptep, hpte[3], r;
+ unsigned long hpte[3], r;
+ __be64 *hptep;
unsigned long mmu_seq, psize, pte_size;
unsigned long gpa_base, gfn_base;
unsigned long gpa, gfn, hva, pfn;
if (ea != vcpu->arch.pgfault_addr)
return RESUME_GUEST;
index = vcpu->arch.pgfault_index;
- hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+ hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
rev = &kvm->arch.revmap[index];
preempt_disable();
while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
cpu_relax();
- hpte[0] = hptep[0] & ~HPTE_V_HVLOCK;
- hpte[1] = hptep[1];
+ hpte[0] = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
+ hpte[1] = be64_to_cpu(hptep[1]);
hpte[2] = r = rev->guest_rpte;
asm volatile("lwsync" : : : "memory");
- hptep[0] = hpte[0];
+ hptep[0] = cpu_to_be64(hpte[0]);
preempt_enable();
if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
preempt_disable();
while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
cpu_relax();
- if ((hptep[0] & ~HPTE_V_HVLOCK) != hpte[0] || hptep[1] != hpte[1] ||
- rev->guest_rpte != hpte[2])
+ if ((be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK) != hpte[0] ||
+ be64_to_cpu(hptep[1]) != hpte[1] ||
+ rev->guest_rpte != hpte[2])
/* HPTE has been changed under us; let the guest retry */
goto out_unlock;
hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
r &= rcbits | ~(HPTE_R_R | HPTE_R_C);
- if (hptep[0] & HPTE_V_VALID) {
+ if (be64_to_cpu(hptep[0]) & HPTE_V_VALID) {
/* HPTE was previously valid, so we need to invalidate it */
unlock_rmap(rmap);
- hptep[0] |= HPTE_V_ABSENT;
+ hptep[0] |= cpu_to_be64(HPTE_V_ABSENT);
kvmppc_invalidate_hpte(kvm, hptep, index);
/* don't lose previous R and C bits */
- r |= hptep[1] & (HPTE_R_R | HPTE_R_C);
+ r |= be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C);
} else {
kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
}
- hptep[1] = r;
+ hptep[1] = cpu_to_be64(r);
eieio();
- hptep[0] = hpte[0];
+ hptep[0] = cpu_to_be64(hpte[0]);
asm volatile("ptesync" : : : "memory");
preempt_enable();
if (page && hpte_is_writable(r))
return ret;
out_unlock:
- hptep[0] &= ~HPTE_V_HVLOCK;
+ hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
preempt_enable();
goto out_put;
}
{
struct revmap_entry *rev = kvm->arch.revmap;
unsigned long h, i, j;
- unsigned long *hptep;
+ __be64 *hptep;
unsigned long ptel, psize, rcbits;
for (;;) {
* rmap chain lock.
*/
i = *rmapp & KVMPPC_RMAP_INDEX;
- hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+ hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4));
if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
/* unlock rmap before spinning on the HPTE lock */
unlock_rmap(rmapp);
- while (hptep[0] & HPTE_V_HVLOCK)
+ while (be64_to_cpu(hptep[0]) & HPTE_V_HVLOCK)
cpu_relax();
continue;
}
/* Now check and modify the HPTE */
ptel = rev[i].guest_rpte;
- psize = hpte_page_size(hptep[0], ptel);
- if ((hptep[0] & HPTE_V_VALID) &&
+ psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel);
+ if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) &&
hpte_rpn(ptel, psize) == gfn) {
if (kvm->arch.using_mmu_notifiers)
- hptep[0] |= HPTE_V_ABSENT;
+ hptep[0] |= cpu_to_be64(HPTE_V_ABSENT);
kvmppc_invalidate_hpte(kvm, hptep, i);
/* Harvest R and C */
- rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
+ rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C);
*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
if (rcbits & ~rev[i].guest_rpte) {
rev[i].guest_rpte = ptel | rcbits;
}
}
unlock_rmap(rmapp);
- hptep[0] &= ~HPTE_V_HVLOCK;
+ hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
}
return 0;
}
{
struct revmap_entry *rev = kvm->arch.revmap;
unsigned long head, i, j;
- unsigned long *hptep;
+ __be64 *hptep;
int ret = 0;
retry:
i = head = *rmapp & KVMPPC_RMAP_INDEX;
do {
- hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+ hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4));
j = rev[i].forw;
/* If this HPTE isn't referenced, ignore it */
- if (!(hptep[1] & HPTE_R_R))
+ if (!(be64_to_cpu(hptep[1]) & HPTE_R_R))
continue;
if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
/* unlock rmap before spinning on the HPTE lock */
unlock_rmap(rmapp);
- while (hptep[0] & HPTE_V_HVLOCK)
+ while (be64_to_cpu(hptep[0]) & HPTE_V_HVLOCK)
cpu_relax();
goto retry;
}
/* Now check and modify the HPTE */
- if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) {
+ if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) &&
+ (be64_to_cpu(hptep[1]) & HPTE_R_R)) {
kvmppc_clear_ref_hpte(kvm, hptep, i);
if (!(rev[i].guest_rpte & HPTE_R_R)) {
rev[i].guest_rpte |= HPTE_R_R;
}
ret = 1;
}
- hptep[0] &= ~HPTE_V_HVLOCK;
+ hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
} while ((i = j) != head);
unlock_rmap(rmapp);
do {
hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4));
j = rev[i].forw;
- if (hp[1] & HPTE_R_R)
+ if (be64_to_cpu(hp[1]) & HPTE_R_R)
goto out;
} while ((i = j) != head);
}
unsigned long head, i, j;
unsigned long n;
unsigned long v, r;
- unsigned long *hptep;
+ __be64 *hptep;
int npages_dirty = 0;
retry:
i = head = *rmapp & KVMPPC_RMAP_INDEX;
do {
- hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+ unsigned long hptep1;
+ hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4));
j = rev[i].forw;
/*
* Otherwise we need to do the tlbie even if C==0 in
* order to pick up any delayed writeback of C.
*/
- if (!(hptep[1] & HPTE_R_C) &&
- (!hpte_is_writable(hptep[1]) || vcpus_running(kvm)))
+ hptep1 = be64_to_cpu(hptep[1]);
+ if (!(hptep1 & HPTE_R_C) &&
+ (!hpte_is_writable(hptep1) || vcpus_running(kvm)))
continue;
if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
/* unlock rmap before spinning on the HPTE lock */
unlock_rmap(rmapp);
- while (hptep[0] & HPTE_V_HVLOCK)
+ while (hptep[0] & cpu_to_be64(HPTE_V_HVLOCK))
cpu_relax();
goto retry;
}
/* Now check and modify the HPTE */
- if (!(hptep[0] & HPTE_V_VALID))
+ if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID)))
continue;
/* need to make it temporarily absent so C is stable */
- hptep[0] |= HPTE_V_ABSENT;
+ hptep[0] |= cpu_to_be64(HPTE_V_ABSENT);
kvmppc_invalidate_hpte(kvm, hptep, i);
- v = hptep[0];
- r = hptep[1];
+ v = be64_to_cpu(hptep[0]);
+ r = be64_to_cpu(hptep[1]);
if (r & HPTE_R_C) {
- hptep[1] = r & ~HPTE_R_C;
+ hptep[1] = cpu_to_be64(r & ~HPTE_R_C);
if (!(rev[i].guest_rpte & HPTE_R_C)) {
rev[i].guest_rpte |= HPTE_R_C;
note_hpte_modification(kvm, &rev[i]);
}
v &= ~(HPTE_V_ABSENT | HPTE_V_HVLOCK);
v |= HPTE_V_VALID;
- hptep[0] = v;
+ hptep[0] = cpu_to_be64(v);
} while ((i = j) != head);
unlock_rmap(rmapp);
* Returns 1 if this HPT entry has been modified or has pending
* R/C bit changes.
*/
- static int hpte_dirty(struct revmap_entry *revp, unsigned long *hptp)
+ static int hpte_dirty(struct revmap_entry *revp, __be64 *hptp)
{
unsigned long rcbits_unset;
/* Also need to consider changes in reference and changed bits */
rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
- if ((hptp[0] & HPTE_V_VALID) && (hptp[1] & rcbits_unset))
+ if ((be64_to_cpu(hptp[0]) & HPTE_V_VALID) &&
+ (be64_to_cpu(hptp[1]) & rcbits_unset))
return 1;
return 0;
}
- static long record_hpte(unsigned long flags, unsigned long *hptp,
+ static long record_hpte(unsigned long flags, __be64 *hptp,
unsigned long *hpte, struct revmap_entry *revp,
int want_valid, int first_pass)
{
return 0;
valid = 0;
- if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) {
+ if (be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)) {
valid = 1;
if ((flags & KVM_GET_HTAB_BOLTED_ONLY) &&
- !(hptp[0] & HPTE_V_BOLTED))
+ !(be64_to_cpu(hptp[0]) & HPTE_V_BOLTED))
valid = 0;
}
if (valid != want_valid)
preempt_disable();
while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
cpu_relax();
- v = hptp[0];
+ v = be64_to_cpu(hptp[0]);
/* re-evaluate valid and dirty from synchronized HPTE value */
valid = !!(v & HPTE_V_VALID);
/* Harvest R and C into guest view if necessary */
rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
- if (valid && (rcbits_unset & hptp[1])) {
- revp->guest_rpte |= (hptp[1] & (HPTE_R_R | HPTE_R_C)) |
- HPTE_GR_MODIFIED;
+ if (valid && (rcbits_unset & be64_to_cpu(hptp[1]))) {
+ revp->guest_rpte |= (be64_to_cpu(hptp[1]) &
+ (HPTE_R_R | HPTE_R_C)) | HPTE_GR_MODIFIED;
dirty = 1;
}
revp->guest_rpte = r;
}
asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
- hptp[0] &= ~HPTE_V_HVLOCK;
+ hptp[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
preempt_enable();
if (!(valid == want_valid && (first_pass || dirty)))
ok = 0;
}
- hpte[0] = v;
- hpte[1] = r;
+ hpte[0] = cpu_to_be64(v);
+ hpte[1] = cpu_to_be64(r);
return ok;
}
struct kvm_htab_ctx *ctx = file->private_data;
struct kvm *kvm = ctx->kvm;
struct kvm_get_htab_header hdr;
- unsigned long *hptp;
+ __be64 *hptp;
struct revmap_entry *revp;
unsigned long i, nb, nw;
unsigned long __user *lbuf;
flags = ctx->flags;
i = ctx->index;
- hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+ hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
revp = kvm->arch.revmap + i;
lbuf = (unsigned long __user *)buf;
unsigned long i, j;
unsigned long v, r;
unsigned long __user *lbuf;
- unsigned long *hptp;
+ __be64 *hptp;
unsigned long tmp[2];
ssize_t nb;
long int err, ret;
i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte)
break;
- hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+ hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
lbuf = (unsigned long __user *)buf;
for (j = 0; j < hdr.n_valid; ++j) {
err = -EFAULT;
lbuf += 2;
nb += HPTE_SIZE;
- if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+ if (be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT))
kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
err = -EIO;
ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, i, v, r,
}
for (j = 0; j < hdr.n_invalid; ++j) {
- if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
+ if (be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT))
kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
++i;
hptp += 2;
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/sizes.h>
+#include <linux/cma.h>
#include <asm/cputable.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
-#include "book3s_hv_cma.h"
+#define KVM_CMA_CHUNK_ORDER 18
+
/*
* Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
* should be power of 2.
unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT; /* 128MB */
EXPORT_SYMBOL_GPL(kvm_rma_pages);
+static struct cma *kvm_cma;
+
/* Work out RMLS (real mode limit selector) field value for a given RMA size.
Assumes POWER7 or PPC970. */
static inline int lpcr_rmls(unsigned long rma_size)
ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
if (!ri)
return NULL;
- page = kvm_alloc_cma(kvm_rma_pages, kvm_rma_pages);
+ page = cma_alloc(kvm_cma, kvm_rma_pages, get_order(kvm_rma_pages));
if (!page)
goto err_out;
atomic_set(&ri->use_count, 1);
void kvm_release_rma(struct kvm_rma_info *ri)
{
if (atomic_dec_and_test(&ri->use_count)) {
- kvm_release_cma(pfn_to_page(ri->base_pfn), kvm_rma_pages);
+ cma_release(kvm_cma, pfn_to_page(ri->base_pfn), kvm_rma_pages);
kfree(ri);
}
}
{
unsigned long align_pages = HPT_ALIGN_PAGES;
+ VM_BUG_ON(get_order(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+
/* Old CPUs require HPT aligned on a multiple of its size */
if (!cpu_has_feature(CPU_FTR_ARCH_206))
align_pages = nr_pages;
- return kvm_alloc_cma(nr_pages, align_pages);
+ return cma_alloc(kvm_cma, nr_pages, get_order(align_pages));
}
EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
void kvm_release_hpt(struct page *page, unsigned long nr_pages)
{
- kvm_release_cma(page, nr_pages);
+ cma_release(kvm_cma, page, nr_pages);
}
EXPORT_SYMBOL_GPL(kvm_release_hpt);
align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
- kvm_cma_declare_contiguous(selected_size, align_size);
+ cma_declare_contiguous(0, selected_size, 0, align_size,
+ KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma);
}
}
{
return atomic_read(&hv_vm_count) != 0;
}
+
+ extern int hcall_real_table[], hcall_real_table_end[];
+
+ int kvmppc_hcall_impl_hv_realmode(unsigned long cmd)
+ {
+ cmd /= 4;
+ if (cmd < hcall_real_table_end - hcall_real_table &&
+ hcall_real_table[cmd])
+ return 1;
+
+ return 0;
+ }
+ EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode);
#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
- #ifdef __LITTLE_ENDIAN__
- #error Need to fix lppaca and SLB shadow accesses in little endian mode
- #endif
-
/* Values in HSTATE_NAPPING(r13) */
#define NAPPING_CEDE 1
#define NAPPING_NOVCPU 2
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
BEGIN_FTR_SECTION
beq 11f
+ cmpwi cr2, r12, BOOK3S_INTERRUPT_HMI
+ beq cr2, 14f /* HMI check */
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* RFI into the highmem handler, or branch to interrupt handler */
13: b machine_check_fwnmi
+14: mtspr SPRN_HSRR0, r8
+ mtspr SPRN_HSRR1, r7
+ b hmi_exception_after_realmode
+
kvmppc_primary_no_guest:
/* We handle this much like a ceded vcpu */
/* set our bit in napping_threads */
ld r3, VCPU_VPA(r4)
cmpdi r3, 0
beq 25f
- lwz r5, LPPACA_YIELDCOUNT(r3)
+ li r6, LPPACA_YIELDCOUNT
+ LWZX_BE r5, r3, r6
addi r5, r5, 1
- stw r5, LPPACA_YIELDCOUNT(r3)
+ STWX_BE r5, r3, r6
li r6, 1
stb r6, VCPU_VPA_DIRTY(r4)
25:
mr r31, r4
addi r3, r31, VCPU_FPRS_TM
- bl .load_fp_state
+ bl load_fp_state
addi r3, r31, VCPU_VRS_TM
- bl .load_vr_state
+ bl load_vr_state
mr r4, r31
lwz r7, VCPU_VRSAVE_TM(r4)
mtspr SPRN_VRSAVE, r7
/* Save FP/VSX. */
addi r3, r9, VCPU_FPRS_TM
- bl .store_fp_state
+ bl store_fp_state
addi r3, r9, VCPU_VRS_TM
- bl .store_vr_state
+ bl store_vr_state
mfspr r6, SPRN_VRSAVE
stw r6, VCPU_VRSAVE_TM(r9)
1:
ld r8, VCPU_VPA(r9) /* do they have a VPA? */
cmpdi r8, 0
beq 25f
- lwz r3, LPPACA_YIELDCOUNT(r8)
+ li r4, LPPACA_YIELDCOUNT
+ LWZX_BE r3, r8, r4
addi r3, r3, 1
- stw r3, LPPACA_YIELDCOUNT(r8)
+ STWX_BE r3, r8, r4
li r3, 1
stb r3, VCPU_VPA_DIRTY(r9)
25:
33: ld r8,PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
- ld r5,SLBSHADOW_SAVEAREA(r8)
- ld r6,SLBSHADOW_SAVEAREA+8(r8)
+ li r3, SLBSHADOW_SAVEAREA
+ LDX_BE r5, r8, r3
+ addi r3, r3, 8
+ LDX_BE r6, r8, r3
andis. r7,r5,SLB_ESID_V@h
beq 1f
slbmte r6,r5
clrrdi r3,r3,2
cmpldi r3,hcall_real_table_end - hcall_real_table
bge guest_exit_cont
+ /* See if this hcall is enabled for in-kernel handling */
+ ld r4, VCPU_KVM(r9)
+ srdi r0, r3, 8 /* r0 = (r3 / 4) >> 6 */
+ sldi r0, r0, 3 /* index into kvm->arch.enabled_hcalls[] */
+ add r4, r4, r0
+ ld r0, KVM_ENABLED_HCALLS(r4)
+ rlwinm r4, r3, 32-2, 0x3f /* r4 = (r3 / 4) & 0x3f */
+ srd r0, r0, r4
+ andi. r0, r0, 1
+ beq guest_exit_cont
+ /* Get pointer to handler, if any, and call it */
LOAD_REG_ADDR(r4, hcall_real_table)
lwax r3,r3,r4
cmpwi r3,0
beq guest_exit_cont
- add r3,r3,r4
- mtctr r3
+ add r12,r3,r4
+ mtctr r12
mr r3,r9 /* get vcpu pointer */
ld r4,VCPU_GPR(R4)(r9)
bctrl
.long 0 /* 0x12c */
.long 0 /* 0x130 */
.long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
+ .globl hcall_real_table_end
hcall_real_table_end:
ignore_hdec:
cmpdi r6, 0
beq- 1f
lwzcix r0, r6, r7
- rlwinm. r3, r0, 0, 0xffffff
+ /*
+ * Save XIRR for later. Since we get in in reverse endian on LE
+ * systems, save it byte reversed and fetch it back in host endian.
+ */
+ li r3, HSTATE_SAVED_XIRR
+ STWX_BE r0, r3, r13
+ #ifdef __LITTLE_ENDIAN__
+ lwz r3, HSTATE_SAVED_XIRR(r13)
+ #else
+ mr r3, r0
+ #endif
+ rlwinm. r3, r3, 0, 0xffffff
sync
beq 1f /* if nothing pending in the ICP */
li r3, -1
1: blr
- 42: /* It's not an IPI and it's for the host, stash it in the PACA
- * before exit, it will be picked up by the host ICP driver
+ 42: /* It's not an IPI and it's for the host. We saved a copy of XIRR in
+ * the PACA earlier, it will be picked up by the host ICP driver
*/
- stw r0, HSTATE_SAVED_XIRR(r13)
li r3, 1
b 1b
mtmsrd r8
isync
addi r3,r3,VCPU_FPRS
- bl .store_fp_state
+ bl store_fp_state
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
addi r3,r31,VCPU_VRS
- bl .store_vr_state
+ bl store_vr_state
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
mfspr r6,SPRN_VRSAVE
mtmsrd r8
isync
addi r3,r4,VCPU_FPRS
- bl .load_fp_state
+ bl load_fp_state
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
addi r3,r31,VCPU_VRS
- bl .load_vr_state
+ bl load_vr_state
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
lwz r7,VCPU_VRSAVE(r31)
u32 shift;
} clock;
- /* open coded 'struct timespec' */
- u64 monotonic_time_snsec;
- time_t monotonic_time_sec;
+ u64 boot_ns;
+ u64 nsec_base;
};
static struct pvclock_gtod_data pvclock_gtod_data;
static void update_pvclock_gtod(struct timekeeper *tk)
{
struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
+ u64 boot_ns;
+
+ boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot));
write_seqcount_begin(&vdata->seq);
/* copy pvclock gtod data */
- vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode;
- vdata->clock.cycle_last = tk->clock->cycle_last;
- vdata->clock.mask = tk->clock->mask;
- vdata->clock.mult = tk->mult;
- vdata->clock.shift = tk->shift;
-
- vdata->monotonic_time_sec = tk->xtime_sec
- + tk->wall_to_monotonic.tv_sec;
- vdata->monotonic_time_snsec = tk->xtime_nsec
- + (tk->wall_to_monotonic.tv_nsec
- << tk->shift);
- while (vdata->monotonic_time_snsec >=
- (((u64)NSEC_PER_SEC) << tk->shift)) {
- vdata->monotonic_time_snsec -=
- ((u64)NSEC_PER_SEC) << tk->shift;
- vdata->monotonic_time_sec++;
- }
+ vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode;
+ vdata->clock.cycle_last = tk->tkr.cycle_last;
+ vdata->clock.mask = tk->tkr.mask;
+ vdata->clock.mult = tk->tkr.mult;
+ vdata->clock.shift = tk->tkr.shift;
+
+ vdata->boot_ns = boot_ns;
+ vdata->nsec_base = tk->tkr.xtime_nsec;
write_seqcount_end(&vdata->seq);
}
static inline u64 get_kernel_ns(void)
{
- struct timespec ts;
-
- ktime_get_ts(&ts);
- monotonic_to_bootbased(&ts);
- return timespec_to_ns(&ts);
+ return ktime_get_boot_ns();
}
#ifdef CONFIG_X86_64
return v * gtod->clock.mult;
}
-static int do_monotonic(struct timespec *ts, cycle_t *cycle_now)
+static int do_monotonic_boot(s64 *t, cycle_t *cycle_now)
{
+ struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
unsigned long seq;
- u64 ns;
int mode;
- struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+ u64 ns;
- ts->tv_nsec = 0;
do {
seq = read_seqcount_begin(>od->seq);
mode = gtod->clock.vclock_mode;
- ts->tv_sec = gtod->monotonic_time_sec;
- ns = gtod->monotonic_time_snsec;
+ ns = gtod->nsec_base;
ns += vgettsc(cycle_now);
ns >>= gtod->clock.shift;
+ ns += gtod->boot_ns;
} while (unlikely(read_seqcount_retry(>od->seq, seq)));
- timespec_add_ns(ts, ns);
+ *t = ns;
return mode;
}
/* returns true if host is using tsc clocksource */
static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
{
- struct timespec ts;
-
/* checked again under seqlock below */
if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
return false;
- if (do_monotonic(&ts, cycle_now) != VCLOCK_TSC)
- return false;
-
- monotonic_to_bootbased(&ts);
- *kernel_ns = timespec_to_ns(&ts);
-
- return true;
+ return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
}
#endif
return r;
}
- int kvm_dev_ioctl_check_extension(long ext)
+ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;