@@ -1835,6 +1835,7 @@ registers, find a list below:
PPC | KVM_REG_PPC_PID | 64
PPC | KVM_REG_PPC_ACOP | 64
PPC | KVM_REG_PPC_VRSAVE | 32
+ PPC | KVM_REG_PPC_LPCR | 64
PPC | KVM_REG_PPC_TM_GPR0 | 64
...
PPC | KVM_REG_PPC_TM_GPR31 | 64
@@ -172,6 +172,8 @@ extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
unsigned long *hpret);
extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
struct kvm_memory_slot *memslot, unsigned long *map);
+extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr,
+ unsigned long mask);
extern void kvmppc_entry_trampoline(void);
extern void kvmppc_hv_entry_trampoline(void);
@@ -295,6 +295,7 @@ struct kvmppc_vcore {
u64 preempt_tb;
struct kvm_vcpu *runner;
u64 tb_offset; /* guest timebase - host timebase */
+ ulong lpcr;
};
#define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff)
@@ -275,6 +275,7 @@
#define LPCR_ISL (1ul << (63-2))
#define LPCR_VC_SH (63-2)
#define LPCR_DPFD_SH (63-11)
+#define LPCR_DPFD (7ul << LPCR_DPFD_SH)
#define LPCR_VRMASD (0x1ful << (63-16))
#define LPCR_VRMA_L (1ul << (63-12))
#define LPCR_VRMA_LP0 (1ul << (63-15))
@@ -291,6 +292,7 @@
#define LPCR_PECE2 0x00001000 /* machine check etc can cause exit */
#define LPCR_MER 0x00000800 /* Mediated External Exception */
#define LPCR_MER_SH 11
+#define LPCR_TC 0x00000200 /* Translation control */
#define LPCR_LPES 0x0000000c
#define LPCR_LPES0 0x00000008 /* LPAR Env selector 0 */
#define LPCR_LPES1 0x00000004 /* LPAR Env selector 1 */
@@ -412,6 +414,7 @@
#define HID4_RMLS2_SH (63 - 2) /* Real mode limit bottom 2 bits */
#define HID4_LPID5_SH (63 - 6) /* partition ID bottom 4 bits */
#define HID4_RMOR_SH (63 - 22) /* real mode offset (16 bits) */
+#define HID4_RMOR (0xFFFFul << HID4_RMOR_SH)
#define HID4_LPES1 (1 << (63-57)) /* LPAR env. sel. bit 1 */
#define HID4_RMLS0_SH (63 - 58) /* Real mode limit top bit */
#define HID4_LPID1_SH 0 /* partition ID top 2 bits */
@@ -533,6 +533,7 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_ACOP (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
#define KVM_REG_PPC_VRSAVE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+#define KVM_REG_PPC_LPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
@@ -521,6 +521,7 @@ int main(void)
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
+ DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
offsetof(struct kvmppc_vcpu_book3s, vcpu));
DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
@@ -1512,9 +1512,8 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
- lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
- lpcr |= senc << (LPCR_VRMASD_SH - 4);
- kvm->arch.lpcr = lpcr;
+ lpcr = senc << (LPCR_VRMASD_SH - 4);
+ kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
rma_setup = 1;
}
++i;
@@ -195,7 +195,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
pr_err(" ESID = %.16llx VSID = %.16llx\n",
vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
- vcpu->kvm->arch.lpcr, vcpu->kvm->arch.sdr1,
+ vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
vcpu->arch.last_inst);
}
@@ -723,6 +723,21 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
return 0;
}
+static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ u64 mask;
+
+ spin_lock(&vc->lock);
+ /*
+ * Userspace can only modify DPFD (default prefetch depth),
+ * ILE (interrupt little-endian) and TC (translation control).
+ */
+ mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
+ vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
+ spin_unlock(&vc->lock);
+}
+
int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
{
int r = 0;
@@ -805,6 +820,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
case KVM_REG_PPC_TB_OFFSET:
*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
break;
+ case KVM_REG_PPC_LPCR:
+ *val = get_reg_val(id, vcpu->arch.vcore->lpcr);
+ break;
default:
r = -EINVAL;
break;
@@ -909,6 +927,9 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
vcpu->arch.vcore->tb_offset =
ALIGN(set_reg_val(id, *val), 1UL << 24);
break;
+ case KVM_REG_PPC_LPCR:
+ kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
+ break;
default:
r = -EINVAL;
break;
@@ -969,6 +990,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
spin_lock_init(&vcore->lock);
init_waitqueue_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
+ vcore->lpcr = kvm->arch.lpcr;
}
kvm->arch.vcores[core] = vcore;
kvm->arch.online_vcores++;
@@ -1758,6 +1780,32 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
}
}
+/*
+ * Update LPCR values in kvm->arch and in vcores.
+ * Caller must hold kvm->lock.
+ */
+void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
+{
+ long int i;
+ u32 cores_done = 0;
+
+ if ((kvm->arch.lpcr & mask) == lpcr)
+ return;
+
+ kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;
+
+ for (i = 0; i < KVM_MAX_VCORES; ++i) {
+ struct kvmppc_vcore *vc = kvm->arch.vcores[i];
+ if (!vc)
+ continue;
+ spin_lock(&vc->lock);
+ vc->lpcr = (vc->lpcr & ~mask) | lpcr;
+ spin_unlock(&vc->lock);
+ if (++cores_done >= kvm->arch.online_vcores)
+ break;
+ }
+}
+
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
{
int err = 0;
@@ -1766,7 +1814,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
unsigned long hva;
struct kvm_memory_slot *memslot;
struct vm_area_struct *vma;
- unsigned long lpcr, senc;
+ unsigned long lpcr = 0, senc;
+ unsigned long lpcr_mask = 0;
unsigned long psize, porder;
unsigned long rma_size;
unsigned long rmls;
@@ -1831,9 +1880,9 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
senc = slb_pgsize_encoding(psize);
kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
- lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
- lpcr |= senc << (LPCR_VRMASD_SH - 4);
- kvm->arch.lpcr = lpcr;
+ lpcr_mask = LPCR_VRMASD;
+ /* the -4 is to account for senc values starting at 0x10 */
+ lpcr = senc << (LPCR_VRMASD_SH - 4);
/* Create HPTEs in the hash page table for the VRMA */
kvmppc_map_vrma(vcpu, memslot, porder);
@@ -1854,23 +1903,21 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
kvm->arch.rma = ri;
/* Update LPCR and RMOR */
- lpcr = kvm->arch.lpcr;
if (cpu_has_feature(CPU_FTR_ARCH_201)) {
/* PPC970; insert RMLS value (split field) in HID4 */
- lpcr &= ~((1ul << HID4_RMLS0_SH) |
- (3ul << HID4_RMLS2_SH));
- lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) |
+ lpcr_mask = (1ul << HID4_RMLS0_SH) |
+ (3ul << HID4_RMLS2_SH) | HID4_RMOR;
+ lpcr = ((rmls >> 2) << HID4_RMLS0_SH) |
((rmls & 3) << HID4_RMLS2_SH);
/* RMOR is also in HID4 */
lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff)
<< HID4_RMOR_SH;
} else {
/* POWER7 */
- lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
- lpcr |= rmls << LPCR_RMLS_SH;
+ lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS;
+ lpcr = rmls << LPCR_RMLS_SH;
kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
}
- kvm->arch.lpcr = lpcr;
pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
@@ -1889,6 +1936,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
}
}
+ kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
+
/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
smp_wmb();
kvm->arch.rma_setup_done = 1;
@@ -505,7 +505,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
beq 20b
/* Set LPCR and RMOR. */
-10: ld r8,KVM_LPCR(r9)
+10: ld r8,VCORE_LPCR(r5)
mtspr SPRN_LPCR,r8
ld r8,KVM_RMOR(r9)
mtspr SPRN_RMOR,r8
@@ -563,7 +563,8 @@ toc_tlbie_lock:
bne 24b
isync
- ld r7,KVM_LPCR(r9) /* use kvm->arch.lpcr to store HID4 */
+ ld r5,HSTATE_KVM_VCORE(r13)
+ ld r7,VCORE_LPCR(r5) /* use vcore->lpcr to store HID4 */
li r0,0x18f
rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */
or r0,r7,r0
This adds the ability to have a separate LPCR (Logical Partitioning Control Register) value relating to a guest for each virtual core, rather than only having a single value for the whole VM. This corresponds to what real POWER hardware does, where there is a LPCR per CPU thread but most of the fields are required to have the same value on all active threads in a core. The per-virtual-core LPCR can be read and written using the GET/SET_ONE_REG interface. Userspace can can only modify the following fields of the LPCR value: DPFD Default prefetch depth ILE Interrupt little-endian TC Translation control (secondary HPT hash group search disable) We still maintain a per-VM default LPCR value in kvm->arch.lpcr, which contains bits relating to memory management, i.e. the Virtualized Partition Memory (VPM) bits and the bits relating to guest real mode. When this default value is updated, the update needs to be propagated to the per-vcore values, so we add a kvmppc_update_lpcr() helper to do that. Signed-off-by: Paul Mackerras <paulus@samba.org> --- Documentation/virtual/kvm/api.txt | 1 + arch/powerpc/include/asm/kvm_book3s.h | 2 + arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/include/asm/reg.h | 3 ++ arch/powerpc/include/uapi/asm/kvm.h | 1 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kvm/book3s_64_mmu_hv.c | 5 +-- arch/powerpc/kvm/book3s_hv.c | 73 +++++++++++++++++++++++++++------ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 5 ++- 9 files changed, 75 insertions(+), 17 deletions(-)