* [PATCH 00/11] KVM: PPC: Book3S HV: Support KVM guests on POWER9
@ 2016-11-23 0:31 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
This series of patches adds support to HV KVM for running KVM guests
on POWER9 systems. This allows us to run KVM guests that use HPT
(hashed page table) address translation and know about the POWER9
processor. With suitable changes to the user-mode driver, this can
also run guests on POWER9 in POWER8 or POWER7 compatibility mode.
For now we require the host to be in HPT mode (not radix).
This series of patches is based on the ppc-kvm topic branch from the
powerpc tree merged with my current kvm-ppc-next tree.
Paul.
---
Documentation/virtual/kvm/api.txt | 2 +
arch/powerpc/include/asm/kvm_asm.h | 1 +
arch/powerpc/include/asm/kvm_host.h | 3 +
arch/powerpc/include/asm/kvm_ppc.h | 7 +-
arch/powerpc/include/uapi/asm/kvm.h | 4 +
arch/powerpc/kernel/asm-offsets.c | 3 +
arch/powerpc/kvm/book3s_64_mmu_hv.c | 39 ++++--
arch/powerpc/kvm/book3s_hv.c | 203 ++++++++++++++++++++++++++------
arch/powerpc/kvm/book3s_hv_builtin.c | 69 +++++++++--
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 111 +++++++++++------
arch/powerpc/kvm/book3s_hv_rm_xics.c | 23 +++-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 136 ++++++++++++++-------
arch/powerpc/kvm/powerpc.c | 11 +-
13 files changed, 468 insertions(+), 144 deletions(-)
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v2 01/11] KVM: PPC: Book3S HV: Adapt to new HPTE format on POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:31 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
This adapts the KVM-HV hashed page table (HPT) code to read and write
HPT entries in the new format defined in Power ISA v3.00 on POWER9
machines. The new format moves the B (segment size) field from the
first doubleword to the second, and trims some bits from the AVA
(abbreviated virtual address) and ARPN (abbreviated real page number)
fields. As far as possible, the conversion is done when reading or
writing the HPT entries, and the rest of the code continues to use
the old format.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_hv.c | 39 ++++++++++----
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 101 +++++++++++++++++++++++++-----------
2 files changed, 100 insertions(+), 40 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 564ae8a..b795dd1 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -314,7 +314,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_slb *slbe;
unsigned long slb_v;
unsigned long pp, key;
- unsigned long v, gr;
+ unsigned long v, orig_v, gr;
__be64 *hptep;
int index;
int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
@@ -339,10 +339,12 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
return -ENOENT;
}
hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
- v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
+ v = orig_v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ v = hpte_new_to_old_v(v, be64_to_cpu(hptep[1]));
gr = kvm->arch.revmap[index].guest_rpte;
- unlock_hpte(hptep, v);
+ unlock_hpte(hptep, orig_v);
preempt_enable();
gpte->eaddr = eaddr;
@@ -440,6 +442,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
{
struct kvm *kvm = vcpu->kvm;
unsigned long hpte[3], r;
+ unsigned long hnow_v, hnow_r;
__be64 *hptep;
unsigned long mmu_seq, psize, pte_size;
unsigned long gpa_base, gfn_base;
@@ -488,6 +491,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
unlock_hpte(hptep, hpte[0]);
preempt_enable();
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hpte[0] = hpte_new_to_old_v(hpte[0], hpte[1]);
+ hpte[1] = hpte_new_to_old_r(hpte[1]);
+ }
if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
hpte[1] != vcpu->arch.pgfault_hpte[1])
return RESUME_GUEST;
@@ -599,9 +606,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
preempt_disable();
while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
cpu_relax();
- if ((be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK) != hpte[0] ||
- be64_to_cpu(hptep[1]) != hpte[1] ||
- rev->guest_rpte != hpte[2])
+ hnow_v = be64_to_cpu(hptep[0]);
+ hnow_r = be64_to_cpu(hptep[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hnow_v = hpte_new_to_old_v(hnow_v, hnow_r);
+ hnow_r = hpte_new_to_old_r(hnow_r);
+ }
+ if ((hnow_v & ~HPTE_V_HVLOCK) != hpte[0] || hnow_r != 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;
@@ -632,6 +644,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
}
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ r = hpte_old_to_new_r(hpte[0], r);
+ hpte[0] = hpte_old_to_new_v(hpte[0]);
+ }
hptep[1] = cpu_to_be64(r);
eieio();
__unlock_hpte(hptep, hpte[0]);
@@ -1183,7 +1199,7 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
unsigned long *hpte, struct revmap_entry *revp,
int want_valid, int first_pass)
{
- unsigned long v, r;
+ unsigned long v, r, hr;
unsigned long rcbits_unset;
int ok = 1;
int valid, dirty;
@@ -1210,6 +1226,11 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
cpu_relax();
v = be64_to_cpu(hptp[0]);
+ hr = be64_to_cpu(hptp[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, hr);
+ hr = hpte_new_to_old_r(hr);
+ }
/* re-evaluate valid and dirty from synchronized HPTE value */
valid = !!(v & HPTE_V_VALID);
@@ -1217,8 +1238,8 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
/* Harvest R and C into guest view if necessary */
rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
- if (valid && (rcbits_unset & be64_to_cpu(hptp[1]))) {
- revp->guest_rpte |= (be64_to_cpu(hptp[1]) &
+ if (valid && (rcbits_unset & hr)) {
+ revp->guest_rpte |= (hr &
(HPTE_R_R | HPTE_R_C)) | HPTE_GR_MODIFIED;
dirty = 1;
}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 0e7fca4..59d3458 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -365,6 +365,11 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
}
}
+ /* Convert to new format on P9 */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ ptel = hpte_old_to_new_r(pteh, ptel);
+ pteh = hpte_old_to_new_v(pteh);
+ }
hpte[1] = cpu_to_be64(ptel);
/* Write the first HPTE dword, unlocking the HPTE and making it valid */
@@ -446,27 +451,31 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
__be64 *hpte;
unsigned long v, r, rb;
struct revmap_entry *rev;
- u64 pte;
+ u64 pte, orig_pte, pte_r;
if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(hpte[0]);
+ pte = orig_pte = be64_to_cpu(hpte[0]);
+ pte_r = be64_to_cpu(hpte[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ pte = hpte_new_to_old_v(pte, pte_r);
+ pte_r = hpte_new_to_old_r(pte_r);
+ }
if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) ||
((flags & H_ANDCOND) && (pte & avpn) != 0)) {
- __unlock_hpte(hpte, pte);
+ __unlock_hpte(hpte, orig_pte);
return H_NOT_FOUND;
}
rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
v = pte & ~HPTE_V_HVLOCK;
- pte = be64_to_cpu(hpte[1]);
if (v & HPTE_V_VALID) {
hpte[0] &= ~cpu_to_be64(HPTE_V_VALID);
- rb = compute_tlbie_rb(v, be64_to_cpu(hpte[1]), pte_index);
+ rb = compute_tlbie_rb(v, pte_r, pte_index);
do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
/*
* The reference (R) and change (C) bits in a HPT
@@ -484,7 +493,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
note_hpte_modification(kvm, rev);
unlock_hpte(hpte, 0);
- if (is_mmio_hpte(v, pte))
+ if (is_mmio_hpte(v, pte_r))
atomic64_inc(&kvm->arch.mmio_update);
if (v & HPTE_V_ABSENT)
@@ -547,6 +556,10 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
found = 0;
hp0 = be64_to_cpu(hp[0]);
hp1 = be64_to_cpu(hp[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hp0 = hpte_new_to_old_v(hp0, hp1);
+ hp1 = hpte_new_to_old_r(hp1);
+ }
if (hp0 & (HPTE_V_ABSENT | HPTE_V_VALID)) {
switch (flags & 3) {
case 0: /* absolute */
@@ -584,8 +597,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
/* leave it locked */
hp[0] &= ~cpu_to_be64(HPTE_V_VALID);
- tlbrb[n] = compute_tlbie_rb(be64_to_cpu(hp[0]),
- be64_to_cpu(hp[1]), pte_index);
+ tlbrb[n] = compute_tlbie_rb(hp0, hp1, pte_index);
indexes[n] = j;
hptes[n] = hp;
revs[n] = rev;
@@ -623,7 +635,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
__be64 *hpte;
struct revmap_entry *rev;
unsigned long v, r, rb, mask, bits;
- u64 pte;
+ u64 pte_v, pte_r;
if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
@@ -631,15 +643,16 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(hpte[0]);
- if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
- ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) {
- __unlock_hpte(hpte, pte);
+ v = pte_v = be64_to_cpu(hpte[0]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ v = hpte_new_to_old_v(v, be64_to_cpu(hpte[1]));
+ if ((v & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
+ ((flags & H_AVPN) && (v & ~0x7fUL) != avpn)) {
+ __unlock_hpte(hpte, pte_v);
return H_NOT_FOUND;
}
- v = pte;
- pte = be64_to_cpu(hpte[1]);
+ pte_r = be64_to_cpu(hpte[1]);
bits = (flags << 55) & HPTE_R_PP0;
bits |= (flags << 48) & HPTE_R_KEY_HI;
bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
@@ -661,13 +674,13 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
* readonly to writable. If it should be writable, we'll
* take a trap and let the page fault code sort it out.
*/
- r = (pte & ~mask) | bits;
- if (hpte_is_writable(r) && !hpte_is_writable(pte))
+ r = (pte_r & ~mask) | bits;
+ if (hpte_is_writable(r) && !hpte_is_writable(pte_r))
r = hpte_make_readonly(r);
/* If the PTE is changing, invalidate it first */
- if (r != pte) {
+ if (r != pte_r) {
rb = compute_tlbie_rb(v, r, pte_index);
- hpte[0] = cpu_to_be64((v & ~HPTE_V_VALID) |
+ hpte[0] = cpu_to_be64((pte_v & ~HPTE_V_VALID) |
HPTE_V_ABSENT);
do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags),
true);
@@ -676,9 +689,9 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
hpte[1] = cpu_to_be64(r);
}
}
- unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
+ unlock_hpte(hpte, pte_v & ~HPTE_V_HVLOCK);
asm volatile("ptesync" : : : "memory");
- if (is_mmio_hpte(v, pte))
+ if (is_mmio_hpte(v, pte_r))
atomic64_inc(&kvm->arch.mmio_update);
return H_SUCCESS;
@@ -704,6 +717,10 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
r = be64_to_cpu(hpte[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, r);
+ r = hpte_new_to_old_r(r);
+ }
if (v & HPTE_V_ABSENT) {
v &= ~HPTE_V_ABSENT;
v |= HPTE_V_VALID;
@@ -821,10 +838,16 @@ void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
unsigned long pte_index)
{
unsigned long rb;
+ u64 hp0, hp1;
hptep[0] &= ~cpu_to_be64(HPTE_V_VALID);
- rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]),
- pte_index);
+ hp0 = be64_to_cpu(hptep[0]);
+ hp1 = be64_to_cpu(hptep[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hp0 = hpte_new_to_old_v(hp0, hp1);
+ hp1 = hpte_new_to_old_r(hp1);
+ }
+ rb = compute_tlbie_rb(hp0, hp1, pte_index);
do_tlbies(kvm, &rb, 1, 1, true);
}
EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
@@ -834,9 +857,15 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, __be64 *hptep,
{
unsigned long rb;
unsigned char rbyte;
+ u64 hp0, hp1;
- rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]),
- pte_index);
+ hp0 = be64_to_cpu(hptep[0]);
+ hp1 = be64_to_cpu(hptep[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hp0 = hpte_new_to_old_v(hp0, hp1);
+ hp1 = hpte_new_to_old_r(hp1);
+ }
+ rb = compute_tlbie_rb(hp0, hp1, pte_index);
rbyte = (be64_to_cpu(hptep[1]) & ~HPTE_R_R) >> 8;
/* modify only the second-last byte, which contains the ref bit */
*((char *)hptep + 14) = rbyte;
@@ -896,7 +925,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
unsigned long avpn;
__be64 *hpte;
unsigned long mask, val;
- unsigned long v, r;
+ unsigned long v, r, orig_v;
/* Get page shift, work out hash and AVPN etc. */
mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_SECONDARY;
@@ -931,6 +960,8 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
for (i = 0; i < 16; i += 2) {
/* Read the PTE racily */
v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ v = hpte_new_to_old_v(v, be64_to_cpu(hpte[i+1]));
/* Check valid/absent, hash, segment size and AVPN */
if (!(v & valid) || (v & mask) != val)
@@ -939,8 +970,12 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
/* Lock the PTE and read it under the lock */
while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK))
cpu_relax();
- v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
+ v = orig_v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
r = be64_to_cpu(hpte[i+1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, r);
+ r = hpte_new_to_old_r(r);
+ }
/*
* Check the HPTE again, including base page size
@@ -950,7 +985,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
/* Return with the HPTE still locked */
return (hash << 3) + (i >> 1);
- __unlock_hpte(&hpte[i], v);
+ __unlock_hpte(&hpte[i], orig_v);
}
if (val & HPTE_V_SECONDARY)
@@ -978,7 +1013,7 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
{
struct kvm *kvm = vcpu->kvm;
long int index;
- unsigned long v, r, gr;
+ unsigned long v, r, gr, orig_v;
__be64 *hpte;
unsigned long valid;
struct revmap_entry *rev;
@@ -1006,12 +1041,16 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
return 0; /* for prot fault, HPTE disappeared */
}
hpte = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
- v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
+ v = orig_v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
r = be64_to_cpu(hpte[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, r);
+ r = hpte_new_to_old_r(r);
+ }
rev = real_vmalloc_addr(&kvm->arch.revmap[index]);
gr = rev->guest_rpte;
- unlock_hpte(hpte, v);
+ unlock_hpte(hpte, orig_v);
}
/* For not found, if the HPTE is valid by now, retry the instruction */
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 01/11] KVM: PPC: Book3S HV: Adapt to new HPTE format on POWER9
@ 2016-11-23 0:31 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
This adapts the KVM-HV hashed page table (HPT) code to read and write
HPT entries in the new format defined in Power ISA v3.00 on POWER9
machines. The new format moves the B (segment size) field from the
first doubleword to the second, and trims some bits from the AVA
(abbreviated virtual address) and ARPN (abbreviated real page number)
fields. As far as possible, the conversion is done when reading or
writing the HPT entries, and the rest of the code continues to use
the old format.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_hv.c | 39 ++++++++++----
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 101 +++++++++++++++++++++++++-----------
2 files changed, 100 insertions(+), 40 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 564ae8a..b795dd1 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -314,7 +314,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
struct kvmppc_slb *slbe;
unsigned long slb_v;
unsigned long pp, key;
- unsigned long v, gr;
+ unsigned long v, orig_v, gr;
__be64 *hptep;
int index;
int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
@@ -339,10 +339,12 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
return -ENOENT;
}
hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
- v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
+ v = orig_v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ v = hpte_new_to_old_v(v, be64_to_cpu(hptep[1]));
gr = kvm->arch.revmap[index].guest_rpte;
- unlock_hpte(hptep, v);
+ unlock_hpte(hptep, orig_v);
preempt_enable();
gpte->eaddr = eaddr;
@@ -440,6 +442,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
{
struct kvm *kvm = vcpu->kvm;
unsigned long hpte[3], r;
+ unsigned long hnow_v, hnow_r;
__be64 *hptep;
unsigned long mmu_seq, psize, pte_size;
unsigned long gpa_base, gfn_base;
@@ -488,6 +491,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
unlock_hpte(hptep, hpte[0]);
preempt_enable();
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hpte[0] = hpte_new_to_old_v(hpte[0], hpte[1]);
+ hpte[1] = hpte_new_to_old_r(hpte[1]);
+ }
if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
hpte[1] != vcpu->arch.pgfault_hpte[1])
return RESUME_GUEST;
@@ -599,9 +606,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
preempt_disable();
while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
cpu_relax();
- if ((be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK) != hpte[0] ||
- be64_to_cpu(hptep[1]) != hpte[1] ||
- rev->guest_rpte != hpte[2])
+ hnow_v = be64_to_cpu(hptep[0]);
+ hnow_r = be64_to_cpu(hptep[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hnow_v = hpte_new_to_old_v(hnow_v, hnow_r);
+ hnow_r = hpte_new_to_old_r(hnow_r);
+ }
+ if ((hnow_v & ~HPTE_V_HVLOCK) != hpte[0] || hnow_r != 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;
@@ -632,6 +644,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
}
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ r = hpte_old_to_new_r(hpte[0], r);
+ hpte[0] = hpte_old_to_new_v(hpte[0]);
+ }
hptep[1] = cpu_to_be64(r);
eieio();
__unlock_hpte(hptep, hpte[0]);
@@ -1183,7 +1199,7 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
unsigned long *hpte, struct revmap_entry *revp,
int want_valid, int first_pass)
{
- unsigned long v, r;
+ unsigned long v, r, hr;
unsigned long rcbits_unset;
int ok = 1;
int valid, dirty;
@@ -1210,6 +1226,11 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
cpu_relax();
v = be64_to_cpu(hptp[0]);
+ hr = be64_to_cpu(hptp[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, hr);
+ hr = hpte_new_to_old_r(hr);
+ }
/* re-evaluate valid and dirty from synchronized HPTE value */
valid = !!(v & HPTE_V_VALID);
@@ -1217,8 +1238,8 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
/* Harvest R and C into guest view if necessary */
rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
- if (valid && (rcbits_unset & be64_to_cpu(hptp[1]))) {
- revp->guest_rpte |= (be64_to_cpu(hptp[1]) &
+ if (valid && (rcbits_unset & hr)) {
+ revp->guest_rpte |= (hr &
(HPTE_R_R | HPTE_R_C)) | HPTE_GR_MODIFIED;
dirty = 1;
}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 0e7fca4..59d3458 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -365,6 +365,11 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
}
}
+ /* Convert to new format on P9 */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ ptel = hpte_old_to_new_r(pteh, ptel);
+ pteh = hpte_old_to_new_v(pteh);
+ }
hpte[1] = cpu_to_be64(ptel);
/* Write the first HPTE dword, unlocking the HPTE and making it valid */
@@ -446,27 +451,31 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
__be64 *hpte;
unsigned long v, r, rb;
struct revmap_entry *rev;
- u64 pte;
+ u64 pte, orig_pte, pte_r;
if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(hpte[0]);
+ pte = orig_pte = be64_to_cpu(hpte[0]);
+ pte_r = be64_to_cpu(hpte[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ pte = hpte_new_to_old_v(pte, pte_r);
+ pte_r = hpte_new_to_old_r(pte_r);
+ }
if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) = 0 ||
((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) ||
((flags & H_ANDCOND) && (pte & avpn) != 0)) {
- __unlock_hpte(hpte, pte);
+ __unlock_hpte(hpte, orig_pte);
return H_NOT_FOUND;
}
rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
v = pte & ~HPTE_V_HVLOCK;
- pte = be64_to_cpu(hpte[1]);
if (v & HPTE_V_VALID) {
hpte[0] &= ~cpu_to_be64(HPTE_V_VALID);
- rb = compute_tlbie_rb(v, be64_to_cpu(hpte[1]), pte_index);
+ rb = compute_tlbie_rb(v, pte_r, pte_index);
do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
/*
* The reference (R) and change (C) bits in a HPT
@@ -484,7 +493,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
note_hpte_modification(kvm, rev);
unlock_hpte(hpte, 0);
- if (is_mmio_hpte(v, pte))
+ if (is_mmio_hpte(v, pte_r))
atomic64_inc(&kvm->arch.mmio_update);
if (v & HPTE_V_ABSENT)
@@ -547,6 +556,10 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
found = 0;
hp0 = be64_to_cpu(hp[0]);
hp1 = be64_to_cpu(hp[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hp0 = hpte_new_to_old_v(hp0, hp1);
+ hp1 = hpte_new_to_old_r(hp1);
+ }
if (hp0 & (HPTE_V_ABSENT | HPTE_V_VALID)) {
switch (flags & 3) {
case 0: /* absolute */
@@ -584,8 +597,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
/* leave it locked */
hp[0] &= ~cpu_to_be64(HPTE_V_VALID);
- tlbrb[n] = compute_tlbie_rb(be64_to_cpu(hp[0]),
- be64_to_cpu(hp[1]), pte_index);
+ tlbrb[n] = compute_tlbie_rb(hp0, hp1, pte_index);
indexes[n] = j;
hptes[n] = hp;
revs[n] = rev;
@@ -623,7 +635,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
__be64 *hpte;
struct revmap_entry *rev;
unsigned long v, r, rb, mask, bits;
- u64 pte;
+ u64 pte_v, pte_r;
if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
@@ -631,15 +643,16 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(hpte[0]);
- if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) = 0 ||
- ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) {
- __unlock_hpte(hpte, pte);
+ v = pte_v = be64_to_cpu(hpte[0]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ v = hpte_new_to_old_v(v, be64_to_cpu(hpte[1]));
+ if ((v & (HPTE_V_ABSENT | HPTE_V_VALID)) = 0 ||
+ ((flags & H_AVPN) && (v & ~0x7fUL) != avpn)) {
+ __unlock_hpte(hpte, pte_v);
return H_NOT_FOUND;
}
- v = pte;
- pte = be64_to_cpu(hpte[1]);
+ pte_r = be64_to_cpu(hpte[1]);
bits = (flags << 55) & HPTE_R_PP0;
bits |= (flags << 48) & HPTE_R_KEY_HI;
bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
@@ -661,13 +674,13 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
* readonly to writable. If it should be writable, we'll
* take a trap and let the page fault code sort it out.
*/
- r = (pte & ~mask) | bits;
- if (hpte_is_writable(r) && !hpte_is_writable(pte))
+ r = (pte_r & ~mask) | bits;
+ if (hpte_is_writable(r) && !hpte_is_writable(pte_r))
r = hpte_make_readonly(r);
/* If the PTE is changing, invalidate it first */
- if (r != pte) {
+ if (r != pte_r) {
rb = compute_tlbie_rb(v, r, pte_index);
- hpte[0] = cpu_to_be64((v & ~HPTE_V_VALID) |
+ hpte[0] = cpu_to_be64((pte_v & ~HPTE_V_VALID) |
HPTE_V_ABSENT);
do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags),
true);
@@ -676,9 +689,9 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
hpte[1] = cpu_to_be64(r);
}
}
- unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
+ unlock_hpte(hpte, pte_v & ~HPTE_V_HVLOCK);
asm volatile("ptesync" : : : "memory");
- if (is_mmio_hpte(v, pte))
+ if (is_mmio_hpte(v, pte_r))
atomic64_inc(&kvm->arch.mmio_update);
return H_SUCCESS;
@@ -704,6 +717,10 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
r = be64_to_cpu(hpte[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, r);
+ r = hpte_new_to_old_r(r);
+ }
if (v & HPTE_V_ABSENT) {
v &= ~HPTE_V_ABSENT;
v |= HPTE_V_VALID;
@@ -821,10 +838,16 @@ void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
unsigned long pte_index)
{
unsigned long rb;
+ u64 hp0, hp1;
hptep[0] &= ~cpu_to_be64(HPTE_V_VALID);
- rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]),
- pte_index);
+ hp0 = be64_to_cpu(hptep[0]);
+ hp1 = be64_to_cpu(hptep[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hp0 = hpte_new_to_old_v(hp0, hp1);
+ hp1 = hpte_new_to_old_r(hp1);
+ }
+ rb = compute_tlbie_rb(hp0, hp1, pte_index);
do_tlbies(kvm, &rb, 1, 1, true);
}
EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
@@ -834,9 +857,15 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, __be64 *hptep,
{
unsigned long rb;
unsigned char rbyte;
+ u64 hp0, hp1;
- rb = compute_tlbie_rb(be64_to_cpu(hptep[0]), be64_to_cpu(hptep[1]),
- pte_index);
+ hp0 = be64_to_cpu(hptep[0]);
+ hp1 = be64_to_cpu(hptep[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ hp0 = hpte_new_to_old_v(hp0, hp1);
+ hp1 = hpte_new_to_old_r(hp1);
+ }
+ rb = compute_tlbie_rb(hp0, hp1, pte_index);
rbyte = (be64_to_cpu(hptep[1]) & ~HPTE_R_R) >> 8;
/* modify only the second-last byte, which contains the ref bit */
*((char *)hptep + 14) = rbyte;
@@ -896,7 +925,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
unsigned long avpn;
__be64 *hpte;
unsigned long mask, val;
- unsigned long v, r;
+ unsigned long v, r, orig_v;
/* Get page shift, work out hash and AVPN etc. */
mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_SECONDARY;
@@ -931,6 +960,8 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
for (i = 0; i < 16; i += 2) {
/* Read the PTE racily */
v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ v = hpte_new_to_old_v(v, be64_to_cpu(hpte[i+1]));
/* Check valid/absent, hash, segment size and AVPN */
if (!(v & valid) || (v & mask) != val)
@@ -939,8 +970,12 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
/* Lock the PTE and read it under the lock */
while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK))
cpu_relax();
- v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
+ v = orig_v = be64_to_cpu(hpte[i]) & ~HPTE_V_HVLOCK;
r = be64_to_cpu(hpte[i+1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, r);
+ r = hpte_new_to_old_r(r);
+ }
/*
* Check the HPTE again, including base page size
@@ -950,7 +985,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
/* Return with the HPTE still locked */
return (hash << 3) + (i >> 1);
- __unlock_hpte(&hpte[i], v);
+ __unlock_hpte(&hpte[i], orig_v);
}
if (val & HPTE_V_SECONDARY)
@@ -978,7 +1013,7 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
{
struct kvm *kvm = vcpu->kvm;
long int index;
- unsigned long v, r, gr;
+ unsigned long v, r, gr, orig_v;
__be64 *hpte;
unsigned long valid;
struct revmap_entry *rev;
@@ -1006,12 +1041,16 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
return 0; /* for prot fault, HPTE disappeared */
}
hpte = (__be64 *)(kvm->arch.hpt_virt + (index << 4));
- v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
+ v = orig_v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK;
r = be64_to_cpu(hpte[1]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ v = hpte_new_to_old_v(v, r);
+ r = hpte_new_to_old_r(r);
+ }
rev = real_vmalloc_addr(&kvm->arch.revmap[index]);
gr = rev->guest_rpte;
- unlock_hpte(hpte, v);
+ unlock_hpte(hpte, orig_v);
}
/* For not found, if the HPTE is valid by now, retry the instruction */
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 02/11] KVM: PPC: Book3S HV: Set partition table rather than SDR1 on POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:31 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
On POWER9, the SDR1 register (hashed page table base address) is no
longer used, and instead the hardware reads the HPT base address
and size from the partition table. The partition table entry also
contains the bits that specify the page size for the VRMA mapping,
which were previously in the LPCR. The VPM0 bit of the LPCR is
now reserved; the processor now always uses the VRMA (virtual
real-mode area) mechanism for guest real-mode accesses in HPT mode,
and the RMO (real-mode offset) mechanism has been dropped.
When entering or exiting the guest, we now only have to set the
LPIDR (logical partition ID register), not the SDR1 register.
There is also no requirement now to transition via a reserved
LPID value.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 36 +++++++++++++++++++++++++++------
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 10 ++++++---
2 files changed, 37 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 02f9aed..13b6e61 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -54,6 +54,7 @@
#include <asm/dbell.h>
#include <asm/hmi.h>
#include <asm/pnv-pci.h>
+#include <asm/mmu.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
@@ -3029,6 +3030,22 @@ static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
return;
}
+static void kvmppc_setup_partition_table(struct kvm *kvm)
+{
+ unsigned long dw0, dw1;
+
+ /* PS field - page size for VRMA */
+ dw0 = ((kvm->arch.vrma_slb_v & SLB_VSID_L) >> 1) |
+ ((kvm->arch.vrma_slb_v & SLB_VSID_LP) << 1);
+ /* HTABSIZE and HTABORG fields */
+ dw0 |= kvm->arch.sdr1;
+
+ /* Second dword has GR=0; other fields are unused since UPRT=0 */
+ dw1 = 0;
+
+ mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
+}
+
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
{
int err = 0;
@@ -3080,17 +3097,20 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
psize == 0x1000000))
goto out_srcu;
- /* Update VRMASD field in the LPCR */
senc = slb_pgsize_encoding(psize);
kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
- /* 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);
- kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+ /* Update VRMASD field in the LPCR */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+ /* the -4 is to account for senc values starting at 0x10 */
+ lpcr = senc << (LPCR_VRMASD_SH - 4);
+ kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+ } else {
+ kvmppc_setup_partition_table(kvm);
+ }
/* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */
smp_wmb();
@@ -3240,7 +3260,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
sizeof(kvm->arch.enabled_hcalls));
- kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
/* Init LPCR for virtual RMA mode */
kvm->arch.host_lpid = mfspr(SPRN_LPID);
@@ -3253,6 +3274,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/* On POWER8 turn on online bit to enable PURR/SPURR */
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lpcr |= LPCR_ONL;
+ /* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed) */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ lpcr &= ~LPCR_VPM0;
kvm->arch.lpcr = lpcr;
/*
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6f81adb..b2d107d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -581,12 +581,14 @@ kvmppc_hv_entry:
ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
cmpwi r6,0
bne 10f
- ld r6,KVM_SDR1(r9)
lwz r7,KVM_LPID(r9)
+BEGIN_FTR_SECTION
+ ld r6,KVM_SDR1(r9)
li r0,LPID_RSVD /* switch to reserved LPID */
mtspr SPRN_LPID,r0
ptesync
mtspr SPRN_SDR1,r6 /* switch to partition page table */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
mtspr SPRN_LPID,r7
isync
@@ -1552,12 +1554,14 @@ kvmhv_switch_to_host:
beq 19f
/* Primary thread switches back to host partition */
- ld r6,KVM_HOST_SDR1(r4)
lwz r7,KVM_HOST_LPID(r4)
+BEGIN_FTR_SECTION
+ ld r6,KVM_HOST_SDR1(r4)
li r8,LPID_RSVD /* switch to reserved LPID */
mtspr SPRN_LPID,r8
ptesync
- mtspr SPRN_SDR1,r6 /* switch to partition page table */
+ mtspr SPRN_SDR1,r6 /* switch to host page table */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
mtspr SPRN_LPID,r7
isync
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 02/11] KVM: PPC: Book3S HV: Set partition table rather than SDR1 on POWER9
@ 2016-11-23 0:31 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
On POWER9, the SDR1 register (hashed page table base address) is no
longer used, and instead the hardware reads the HPT base address
and size from the partition table. The partition table entry also
contains the bits that specify the page size for the VRMA mapping,
which were previously in the LPCR. The VPM0 bit of the LPCR is
now reserved; the processor now always uses the VRMA (virtual
real-mode area) mechanism for guest real-mode accesses in HPT mode,
and the RMO (real-mode offset) mechanism has been dropped.
When entering or exiting the guest, we now only have to set the
LPIDR (logical partition ID register), not the SDR1 register.
There is also no requirement now to transition via a reserved
LPID value.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 36 +++++++++++++++++++++++++++------
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 10 ++++++---
2 files changed, 37 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 02f9aed..13b6e61 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -54,6 +54,7 @@
#include <asm/dbell.h>
#include <asm/hmi.h>
#include <asm/pnv-pci.h>
+#include <asm/mmu.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
@@ -3029,6 +3030,22 @@ static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
return;
}
+static void kvmppc_setup_partition_table(struct kvm *kvm)
+{
+ unsigned long dw0, dw1;
+
+ /* PS field - page size for VRMA */
+ dw0 = ((kvm->arch.vrma_slb_v & SLB_VSID_L) >> 1) |
+ ((kvm->arch.vrma_slb_v & SLB_VSID_LP) << 1);
+ /* HTABSIZE and HTABORG fields */
+ dw0 |= kvm->arch.sdr1;
+
+ /* Second dword has GR=0; other fields are unused since UPRT=0 */
+ dw1 = 0;
+
+ mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
+}
+
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
{
int err = 0;
@@ -3080,17 +3097,20 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
psize = 0x1000000))
goto out_srcu;
- /* Update VRMASD field in the LPCR */
senc = slb_pgsize_encoding(psize);
kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
- /* 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);
- kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+ /* Update VRMASD field in the LPCR */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+ /* the -4 is to account for senc values starting at 0x10 */
+ lpcr = senc << (LPCR_VRMASD_SH - 4);
+ kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
+ } else {
+ kvmppc_setup_partition_table(kvm);
+ }
/* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */
smp_wmb();
@@ -3240,7 +3260,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
sizeof(kvm->arch.enabled_hcalls));
- kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
/* Init LPCR for virtual RMA mode */
kvm->arch.host_lpid = mfspr(SPRN_LPID);
@@ -3253,6 +3274,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/* On POWER8 turn on online bit to enable PURR/SPURR */
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lpcr |= LPCR_ONL;
+ /* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed) */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ lpcr &= ~LPCR_VPM0;
kvm->arch.lpcr = lpcr;
/*
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6f81adb..b2d107d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -581,12 +581,14 @@ kvmppc_hv_entry:
ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
cmpwi r6,0
bne 10f
- ld r6,KVM_SDR1(r9)
lwz r7,KVM_LPID(r9)
+BEGIN_FTR_SECTION
+ ld r6,KVM_SDR1(r9)
li r0,LPID_RSVD /* switch to reserved LPID */
mtspr SPRN_LPID,r0
ptesync
mtspr SPRN_SDR1,r6 /* switch to partition page table */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
mtspr SPRN_LPID,r7
isync
@@ -1552,12 +1554,14 @@ kvmhv_switch_to_host:
beq 19f
/* Primary thread switches back to host partition */
- ld r6,KVM_HOST_SDR1(r4)
lwz r7,KVM_HOST_LPID(r4)
+BEGIN_FTR_SECTION
+ ld r6,KVM_HOST_SDR1(r4)
li r8,LPID_RSVD /* switch to reserved LPID */
mtspr SPRN_LPID,r8
ptesync
- mtspr SPRN_SDR1,r6 /* switch to partition page table */
+ mtspr SPRN_SDR1,r6 /* switch to host page table */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
mtspr SPRN_LPID,r7
isync
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 03/11] KVM: PPC: Book3S HV: Adjust host/guest context switch for POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:31 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
Some special-purpose registers that were present and accessible
by guests on POWER8 no longer exist on POWER9, so this adds
feature sections to ensure that we don't try to context-switch
them when going into or out of a guest on POWER9. These are
all relatively obscure, rarely-used registers, but we had to
context-switch them on POWER8 to avoid creating a covert channel.
They are: SPMC1, SPMC2, MMCRS, CSIGR, TACR, TCSCR, and ACOP.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 50 ++++++++++++++++++++-------------
1 file changed, 30 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b2d107d..c7dd251 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -752,14 +752,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
BEGIN_FTR_SECTION
ld r5, VCPU_MMCR + 24(r4)
ld r6, VCPU_SIER(r4)
+ mtspr SPRN_MMCR2, r5
+ mtspr SPRN_SIER, r6
+BEGIN_FTR_SECTION_NESTED(96)
lwz r7, VCPU_PMC + 24(r4)
lwz r8, VCPU_PMC + 28(r4)
ld r9, VCPU_MMCR + 32(r4)
- mtspr SPRN_MMCR2, r5
- mtspr SPRN_SIER, r6
mtspr SPRN_SPMC1, r7
mtspr SPRN_SPMC2, r8
mtspr SPRN_MMCRS, r9
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_MMCR0, r3
isync
@@ -815,20 +817,22 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_EBBHR, r8
ld r5, VCPU_EBBRR(r4)
ld r6, VCPU_BESCR(r4)
- ld r7, VCPU_CSIGR(r4)
- ld r8, VCPU_TACR(r4)
+ lwz r7, VCPU_GUEST_PID(r4)
+ ld r8, VCPU_WORT(r4)
mtspr SPRN_EBBRR, r5
mtspr SPRN_BESCR, r6
- mtspr SPRN_CSIGR, r7
- mtspr SPRN_TACR, r8
+ mtspr SPRN_PID, r7
+ mtspr SPRN_WORT, r8
+BEGIN_FTR_SECTION
ld r5, VCPU_TCSCR(r4)
ld r6, VCPU_ACOP(r4)
- lwz r7, VCPU_GUEST_PID(r4)
- ld r8, VCPU_WORT(r4)
+ ld r7, VCPU_CSIGR(r4)
+ ld r8, VCPU_TACR(r4)
mtspr SPRN_TCSCR, r5
mtspr SPRN_ACOP, r6
- mtspr SPRN_PID, r7
- mtspr SPRN_WORT, r8
+ mtspr SPRN_CSIGR, r7
+ mtspr SPRN_TACR, r8
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
8:
/*
@@ -1343,20 +1347,22 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
std r8, VCPU_EBBHR(r9)
mfspr r5, SPRN_EBBRR
mfspr r6, SPRN_BESCR
- mfspr r7, SPRN_CSIGR
- mfspr r8, SPRN_TACR
+ mfspr r7, SPRN_PID
+ mfspr r8, SPRN_WORT
std r5, VCPU_EBBRR(r9)
std r6, VCPU_BESCR(r9)
- std r7, VCPU_CSIGR(r9)
- std r8, VCPU_TACR(r9)
+ stw r7, VCPU_GUEST_PID(r9)
+ std r8, VCPU_WORT(r9)
+BEGIN_FTR_SECTION
mfspr r5, SPRN_TCSCR
mfspr r6, SPRN_ACOP
- mfspr r7, SPRN_PID
- mfspr r8, SPRN_WORT
+ mfspr r7, SPRN_CSIGR
+ mfspr r8, SPRN_TACR
std r5, VCPU_TCSCR(r9)
std r6, VCPU_ACOP(r9)
- stw r7, VCPU_GUEST_PID(r9)
- std r8, VCPU_WORT(r9)
+ std r7, VCPU_CSIGR(r9)
+ std r8, VCPU_TACR(r9)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
/*
* Restore various registers to 0, where non-zero values
* set by the guest could disrupt the host.
@@ -1365,12 +1371,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_IAMR, r0
mtspr SPRN_CIABR, r0
mtspr SPRN_DAWRX, r0
- mtspr SPRN_TCSCR, r0
mtspr SPRN_WORT, r0
+BEGIN_FTR_SECTION
+ mtspr SPRN_TCSCR, r0
/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
li r0, 1
sldi r0, r0, 31
mtspr SPRN_MMCRS, r0
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
8:
/* Save and reset AMR and UAMOR before turning on the MMU */
@@ -1504,15 +1512,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
stw r8, VCPU_PMC + 20(r9)
BEGIN_FTR_SECTION
mfspr r5, SPRN_SIER
+ std r5, VCPU_SIER(r9)
+BEGIN_FTR_SECTION_NESTED(96)
mfspr r6, SPRN_SPMC1
mfspr r7, SPRN_SPMC2
mfspr r8, SPRN_MMCRS
- std r5, VCPU_SIER(r9)
stw r6, VCPU_PMC + 24(r9)
stw r7, VCPU_PMC + 28(r9)
std r8, VCPU_MMCR + 32(r9)
lis r4, 0x8000
mtspr SPRN_MMCRS, r4
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
22:
/* Clear out SLB */
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 03/11] KVM: PPC: Book3S HV: Adjust host/guest context switch for POWER9
@ 2016-11-23 0:31 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
Some special-purpose registers that were present and accessible
by guests on POWER8 no longer exist on POWER9, so this adds
feature sections to ensure that we don't try to context-switch
them when going into or out of a guest on POWER9. These are
all relatively obscure, rarely-used registers, but we had to
context-switch them on POWER8 to avoid creating a covert channel.
They are: SPMC1, SPMC2, MMCRS, CSIGR, TACR, TCSCR, and ACOP.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 50 ++++++++++++++++++++-------------
1 file changed, 30 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b2d107d..c7dd251 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -752,14 +752,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
BEGIN_FTR_SECTION
ld r5, VCPU_MMCR + 24(r4)
ld r6, VCPU_SIER(r4)
+ mtspr SPRN_MMCR2, r5
+ mtspr SPRN_SIER, r6
+BEGIN_FTR_SECTION_NESTED(96)
lwz r7, VCPU_PMC + 24(r4)
lwz r8, VCPU_PMC + 28(r4)
ld r9, VCPU_MMCR + 32(r4)
- mtspr SPRN_MMCR2, r5
- mtspr SPRN_SIER, r6
mtspr SPRN_SPMC1, r7
mtspr SPRN_SPMC2, r8
mtspr SPRN_MMCRS, r9
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_MMCR0, r3
isync
@@ -815,20 +817,22 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_EBBHR, r8
ld r5, VCPU_EBBRR(r4)
ld r6, VCPU_BESCR(r4)
- ld r7, VCPU_CSIGR(r4)
- ld r8, VCPU_TACR(r4)
+ lwz r7, VCPU_GUEST_PID(r4)
+ ld r8, VCPU_WORT(r4)
mtspr SPRN_EBBRR, r5
mtspr SPRN_BESCR, r6
- mtspr SPRN_CSIGR, r7
- mtspr SPRN_TACR, r8
+ mtspr SPRN_PID, r7
+ mtspr SPRN_WORT, r8
+BEGIN_FTR_SECTION
ld r5, VCPU_TCSCR(r4)
ld r6, VCPU_ACOP(r4)
- lwz r7, VCPU_GUEST_PID(r4)
- ld r8, VCPU_WORT(r4)
+ ld r7, VCPU_CSIGR(r4)
+ ld r8, VCPU_TACR(r4)
mtspr SPRN_TCSCR, r5
mtspr SPRN_ACOP, r6
- mtspr SPRN_PID, r7
- mtspr SPRN_WORT, r8
+ mtspr SPRN_CSIGR, r7
+ mtspr SPRN_TACR, r8
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
8:
/*
@@ -1343,20 +1347,22 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
std r8, VCPU_EBBHR(r9)
mfspr r5, SPRN_EBBRR
mfspr r6, SPRN_BESCR
- mfspr r7, SPRN_CSIGR
- mfspr r8, SPRN_TACR
+ mfspr r7, SPRN_PID
+ mfspr r8, SPRN_WORT
std r5, VCPU_EBBRR(r9)
std r6, VCPU_BESCR(r9)
- std r7, VCPU_CSIGR(r9)
- std r8, VCPU_TACR(r9)
+ stw r7, VCPU_GUEST_PID(r9)
+ std r8, VCPU_WORT(r9)
+BEGIN_FTR_SECTION
mfspr r5, SPRN_TCSCR
mfspr r6, SPRN_ACOP
- mfspr r7, SPRN_PID
- mfspr r8, SPRN_WORT
+ mfspr r7, SPRN_CSIGR
+ mfspr r8, SPRN_TACR
std r5, VCPU_TCSCR(r9)
std r6, VCPU_ACOP(r9)
- stw r7, VCPU_GUEST_PID(r9)
- std r8, VCPU_WORT(r9)
+ std r7, VCPU_CSIGR(r9)
+ std r8, VCPU_TACR(r9)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
/*
* Restore various registers to 0, where non-zero values
* set by the guest could disrupt the host.
@@ -1365,12 +1371,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_IAMR, r0
mtspr SPRN_CIABR, r0
mtspr SPRN_DAWRX, r0
- mtspr SPRN_TCSCR, r0
mtspr SPRN_WORT, r0
+BEGIN_FTR_SECTION
+ mtspr SPRN_TCSCR, r0
/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
li r0, 1
sldi r0, r0, 31
mtspr SPRN_MMCRS, r0
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
8:
/* Save and reset AMR and UAMOR before turning on the MMU */
@@ -1504,15 +1512,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
stw r8, VCPU_PMC + 20(r9)
BEGIN_FTR_SECTION
mfspr r5, SPRN_SIER
+ std r5, VCPU_SIER(r9)
+BEGIN_FTR_SECTION_NESTED(96)
mfspr r6, SPRN_SPMC1
mfspr r7, SPRN_SPMC2
mfspr r8, SPRN_MMCRS
- std r5, VCPU_SIER(r9)
stw r6, VCPU_PMC + 24(r9)
stw r7, VCPU_PMC + 28(r9)
std r8, VCPU_MMCR + 32(r9)
lis r4, 0x8000
mtspr SPRN_MMCRS, r4
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
22:
/* Clear out SLB */
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 04/11] KVM: PPC: Book3S HV: Add new POWER9 guest-accessible SPRs
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:31 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
This adds code to handle two new guest-accessible special-purpose
registers on POWER9: TIDR (thread ID register) and PSSCR (processor
stop status and control register). They are context-switched
between host and guest, and the guest values can be read and set
via the one_reg interface.
The PSSCR contains some fields which are guest-accessible and some
which are only accessible in hypervisor mode. We only allow the
guest-accessible fields to be read or set by userspace.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
Documentation/virtual/kvm/api.txt | 2 ++
arch/powerpc/include/asm/kvm_host.h | 2 ++
arch/powerpc/include/uapi/asm/kvm.h | 4 ++++
arch/powerpc/kernel/asm-offsets.c | 2 ++
arch/powerpc/kvm/book3s_hv.c | 12 ++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 39 +++++++++++++++++++++++++++++++--
6 files changed, 59 insertions(+), 2 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a7596e9..8a5ebd1 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2023,6 +2023,8 @@ registers, find a list below:
PPC | KVM_REG_PPC_WORT | 64
PPC | KVM_REG_PPC_SPRG9 | 64
PPC | KVM_REG_PPC_DBSR | 32
+ PPC | KVM_REG_PPC_TIDR | 64
+ PPC | KVM_REG_PPC_PSSCR | 64
PPC | KVM_REG_PPC_TM_GPR0 | 64
...
PPC | KVM_REG_PPC_TM_GPR31 | 64
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 0e584ee..9556de6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -517,6 +517,8 @@ struct kvm_vcpu_arch {
ulong tcscr;
ulong acop;
ulong wort;
+ ulong tid;
+ ulong psscr;
ulong shadow_srr1;
#endif
u32 vrsave; /* also USPRG0 */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 0fb1326..3603b6f 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -573,6 +573,10 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
#define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c833d88..a4f6d5e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -548,6 +548,8 @@ int main(void)
DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
+ DEFINE(VCPU_TID, offsetof(struct kvm_vcpu, arch.tid));
+ DEFINE(VCPU_PSSCR, offsetof(struct kvm_vcpu, arch.psscr));
DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 13b6e61..14eeacc 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1230,6 +1230,12 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_WORT:
*val = get_reg_val(id, vcpu->arch.wort);
break;
+ case KVM_REG_PPC_TIDR:
+ *val = get_reg_val(id, vcpu->arch.tid);
+ break;
+ case KVM_REG_PPC_PSSCR:
+ *val = get_reg_val(id, vcpu->arch.psscr);
+ break;
case KVM_REG_PPC_VPA_ADDR:
spin_lock(&vcpu->arch.vpa_update_lock);
*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
@@ -1431,6 +1437,12 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_WORT:
vcpu->arch.wort = set_reg_val(id, *val);
break;
+ case KVM_REG_PPC_TIDR:
+ vcpu->arch.tid = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_PSSCR:
+ vcpu->arch.psscr = set_reg_val(id, *val) & PSSCR_GUEST_VIS;
+ break;
case KVM_REG_PPC_VPA_ADDR:
addr = set_reg_val(id, *val);
r = -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c7dd251..499be60 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -523,6 +523,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
* *
*****************************************************************************/
+/* Stack frame offsets */
+#define STACK_SLOT_TID (112-16)
+#define STACK_SLOT_PSSCR (112-24)
+
.global kvmppc_hv_entry
kvmppc_hv_entry:
@@ -700,6 +704,14 @@ kvmppc_got_guest:
mtspr SPRN_PURR,r7
mtspr SPRN_SPURR,r8
+ /* Save host values of some registers */
+BEGIN_FTR_SECTION
+ mfspr r5, SPRN_TIDR
+ mfspr r6, SPRN_PSSCR
+ std r5, STACK_SLOT_TID(r1)
+ std r6, STACK_SLOT_PSSCR(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
BEGIN_FTR_SECTION
/* Set partition DABR */
/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -824,6 +836,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_PID, r7
mtspr SPRN_WORT, r8
BEGIN_FTR_SECTION
+ /* POWER8-only registers */
ld r5, VCPU_TCSCR(r4)
ld r6, VCPU_ACOP(r4)
ld r7, VCPU_CSIGR(r4)
@@ -832,7 +845,14 @@ BEGIN_FTR_SECTION
mtspr SPRN_ACOP, r6
mtspr SPRN_CSIGR, r7
mtspr SPRN_TACR, r8
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+ /* POWER9-only registers */
+ ld r5, VCPU_TID(r4)
+ ld r6, VCPU_PSSCR(r4)
+ oris r6, r6, PSSCR_EC@h /* This makes stop trap to HV */
+ mtspr SPRN_TIDR, r5
+ mtspr SPRN_PSSCR, r6
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
8:
/*
@@ -1362,7 +1382,14 @@ BEGIN_FTR_SECTION
std r6, VCPU_ACOP(r9)
std r7, VCPU_CSIGR(r9)
std r8, VCPU_TACR(r9)
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+ mfspr r5, SPRN_TIDR
+ mfspr r6, SPRN_PSSCR
+ std r5, VCPU_TID(r9)
+ rldicl r6, r6, 4, 50 /* r6 &= PSSCR_GUEST_VIS */
+ rotldi r6, r6, 60
+ std r6, VCPU_PSSCR(r9)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
/*
* Restore various registers to 0, where non-zero values
* set by the guest could disrupt the host.
@@ -1531,6 +1558,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
+ /* Restore host values of some registers */
+BEGIN_FTR_SECTION
+ ld r5, STACK_SLOT_TID(r1)
+ ld r6, STACK_SLOT_PSSCR(r1)
+ mtspr SPRN_TIDR, r5
+ mtspr SPRN_PSSCR, r6
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 04/11] KVM: PPC: Book3S HV: Add new POWER9 guest-accessible SPRs
@ 2016-11-23 0:31 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
This adds code to handle two new guest-accessible special-purpose
registers on POWER9: TIDR (thread ID register) and PSSCR (processor
stop status and control register). They are context-switched
between host and guest, and the guest values can be read and set
via the one_reg interface.
The PSSCR contains some fields which are guest-accessible and some
which are only accessible in hypervisor mode. We only allow the
guest-accessible fields to be read or set by userspace.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
Documentation/virtual/kvm/api.txt | 2 ++
arch/powerpc/include/asm/kvm_host.h | 2 ++
arch/powerpc/include/uapi/asm/kvm.h | 4 ++++
arch/powerpc/kernel/asm-offsets.c | 2 ++
arch/powerpc/kvm/book3s_hv.c | 12 ++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 39 +++++++++++++++++++++++++++++++--
6 files changed, 59 insertions(+), 2 deletions(-)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a7596e9..8a5ebd1 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2023,6 +2023,8 @@ registers, find a list below:
PPC | KVM_REG_PPC_WORT | 64
PPC | KVM_REG_PPC_SPRG9 | 64
PPC | KVM_REG_PPC_DBSR | 32
+ PPC | KVM_REG_PPC_TIDR | 64
+ PPC | KVM_REG_PPC_PSSCR | 64
PPC | KVM_REG_PPC_TM_GPR0 | 64
...
PPC | KVM_REG_PPC_TM_GPR31 | 64
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 0e584ee..9556de6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -517,6 +517,8 @@ struct kvm_vcpu_arch {
ulong tcscr;
ulong acop;
ulong wort;
+ ulong tid;
+ ulong psscr;
ulong shadow_srr1;
#endif
u32 vrsave; /* also USPRG0 */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 0fb1326..3603b6f 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -573,6 +573,10 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
#define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c833d88..a4f6d5e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -548,6 +548,8 @@ int main(void)
DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
+ DEFINE(VCPU_TID, offsetof(struct kvm_vcpu, arch.tid));
+ DEFINE(VCPU_PSSCR, offsetof(struct kvm_vcpu, arch.psscr));
DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 13b6e61..14eeacc 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1230,6 +1230,12 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_WORT:
*val = get_reg_val(id, vcpu->arch.wort);
break;
+ case KVM_REG_PPC_TIDR:
+ *val = get_reg_val(id, vcpu->arch.tid);
+ break;
+ case KVM_REG_PPC_PSSCR:
+ *val = get_reg_val(id, vcpu->arch.psscr);
+ break;
case KVM_REG_PPC_VPA_ADDR:
spin_lock(&vcpu->arch.vpa_update_lock);
*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
@@ -1431,6 +1437,12 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_WORT:
vcpu->arch.wort = set_reg_val(id, *val);
break;
+ case KVM_REG_PPC_TIDR:
+ vcpu->arch.tid = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_PSSCR:
+ vcpu->arch.psscr = set_reg_val(id, *val) & PSSCR_GUEST_VIS;
+ break;
case KVM_REG_PPC_VPA_ADDR:
addr = set_reg_val(id, *val);
r = -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c7dd251..499be60 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -523,6 +523,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
* *
*****************************************************************************/
+/* Stack frame offsets */
+#define STACK_SLOT_TID (112-16)
+#define STACK_SLOT_PSSCR (112-24)
+
.global kvmppc_hv_entry
kvmppc_hv_entry:
@@ -700,6 +704,14 @@ kvmppc_got_guest:
mtspr SPRN_PURR,r7
mtspr SPRN_SPURR,r8
+ /* Save host values of some registers */
+BEGIN_FTR_SECTION
+ mfspr r5, SPRN_TIDR
+ mfspr r6, SPRN_PSSCR
+ std r5, STACK_SLOT_TID(r1)
+ std r6, STACK_SLOT_PSSCR(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
BEGIN_FTR_SECTION
/* Set partition DABR */
/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -824,6 +836,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_PID, r7
mtspr SPRN_WORT, r8
BEGIN_FTR_SECTION
+ /* POWER8-only registers */
ld r5, VCPU_TCSCR(r4)
ld r6, VCPU_ACOP(r4)
ld r7, VCPU_CSIGR(r4)
@@ -832,7 +845,14 @@ BEGIN_FTR_SECTION
mtspr SPRN_ACOP, r6
mtspr SPRN_CSIGR, r7
mtspr SPRN_TACR, r8
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+ /* POWER9-only registers */
+ ld r5, VCPU_TID(r4)
+ ld r6, VCPU_PSSCR(r4)
+ oris r6, r6, PSSCR_EC@h /* This makes stop trap to HV */
+ mtspr SPRN_TIDR, r5
+ mtspr SPRN_PSSCR, r6
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
8:
/*
@@ -1362,7 +1382,14 @@ BEGIN_FTR_SECTION
std r6, VCPU_ACOP(r9)
std r7, VCPU_CSIGR(r9)
std r8, VCPU_TACR(r9)
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+ mfspr r5, SPRN_TIDR
+ mfspr r6, SPRN_PSSCR
+ std r5, VCPU_TID(r9)
+ rldicl r6, r6, 4, 50 /* r6 &= PSSCR_GUEST_VIS */
+ rotldi r6, r6, 60
+ std r6, VCPU_PSSCR(r9)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
/*
* Restore various registers to 0, where non-zero values
* set by the guest could disrupt the host.
@@ -1531,6 +1558,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
+ /* Restore host values of some registers */
+BEGIN_FTR_SECTION
+ ld r5, STACK_SLOT_TID(r1)
+ ld r6, STACK_SLOT_PSSCR(r1)
+ mtspr SPRN_TIDR, r5
+ mtspr SPRN_PSSCR, r6
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 05/11] KVM: PPC: Book3S HV: Adapt TLB invalidations to work on POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:31 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
POWER9 adds new capabilities to the tlbie (TLB invalidate entry)
and tlbiel (local tlbie) instructions. Both instructions get a
set of new parameters (RIC, PRS and R) which appear as bits in the
instruction word. The tlbiel instruction now has a second register
operand, which contains a PID and/or LPID value if needed, and
should otherwise contain 0.
This adapts KVM-HV's usage of tlbie and tlbiel to work on POWER9
as well as older processors. Since we only handle HPT guests so
far, we need RIC=0 PRS=0 R=0, which ends up with the same instruction
word as on previous processors, so we don't need to conditionally
execute different instructions depending on the processor.
The local flush on first entry to a guest in book3s_hv_rmhandlers.S
is a loop which depends on the number of TLB sets. Rather than
using feature sections to set the number of iterations based on
which CPU we're on, we now work out this number at VM creation time
and store it in the kvm_arch struct. That will make it possible to
get the number from the device tree in future, which will help with
compatibility with future processors.
Since mmu_partition_table_set_entry() does a global flush of the
whole LPID, we don't need to do the TLB flush on first entry to the
guest on each processor. Therefore we don't set all bits in the
tlb_need_flush bitmap on VM startup on POWER9.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_host.h | 1 +
arch/powerpc/kernel/asm-offsets.c | 1 +
arch/powerpc/kvm/book3s_hv.c | 17 ++++++++++++++++-
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 10 ++++++++--
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 ++------
5 files changed, 28 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9556de6..f15713a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -244,6 +244,7 @@ struct kvm_arch_memory_slot {
struct kvm_arch {
unsigned int lpid;
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ unsigned int tlb_sets;
unsigned long hpt_virt;
struct revmap_entry *revmap;
atomic64_t mmio_update;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index a4f6d5e..195a9fc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -487,6 +487,7 @@ int main(void)
/* book3s */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ DEFINE(KVM_TLB_SETS, offsetof(struct kvm, arch.tlb_sets));
DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 14eeacc..0a90fa4 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3265,8 +3265,11 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
* Since we don't flush the TLB when tearing down a VM,
* and this lpid might have previously been used,
* make sure we flush on each core before running the new VM.
+ * On POWER9, the tlbie in mmu_partition_table_set_entry()
+ * does this flush for us.
*/
- cpumask_setall(&kvm->arch.need_tlb_flush);
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ cpumask_setall(&kvm->arch.need_tlb_flush);
/* Start out with the default set of hcalls enabled */
memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
@@ -3292,6 +3295,17 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
kvm->arch.lpcr = lpcr;
/*
+ * Work out how many sets the TLB has, for the use of
+ * the TLB invalidation loop in book3s_hv_rmhandlers.S.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH; /* 256 */
+ else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ kvm->arch.tlb_sets = POWER8_TLB_SETS; /* 512 */
+ else
+ kvm->arch.tlb_sets = POWER7_TLB_SETS; /* 128 */
+
+ /*
* Track that we now have a HV mode VM active. This blocks secondary
* CPU threads from coming online.
*/
@@ -3733,3 +3747,4 @@ module_exit(kvmppc_book3s_exit_hv);
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");
+
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 59d3458..378b962 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -425,13 +425,18 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
{
long i;
+ /*
+ * We use the POWER9 5-operand versions of tlbie and tlbiel here.
+ * Since we are using RIC=0 PRS=0 R=0, and P7/P8 tlbiel ignores
+ * the RS field, this is backwards-compatible with P7 and P8.
+ */
if (global) {
while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
cpu_relax();
if (need_sync)
asm volatile("ptesync" : : : "memory");
for (i = 0; i < npages; ++i)
- asm volatile(PPC_TLBIE(%1,%0) : :
+ asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
"r" (rbvalues[i]), "r" (kvm->arch.lpid));
asm volatile("eieio; tlbsync; ptesync" : : : "memory");
kvm->arch.tlbie_lock = 0;
@@ -439,7 +444,8 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
if (need_sync)
asm volatile("ptesync" : : : "memory");
for (i = 0; i < npages; ++i)
- asm volatile("tlbiel %0" : : "r" (rbvalues[i]));
+ asm volatile(PPC_TLBIEL(%0,%1,0,0,0) : :
+ "r" (rbvalues[i]), "r" (0));
asm volatile("ptesync" : : : "memory");
}
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 499be60..598d828 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -613,12 +613,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
stdcx. r7,0,r6
bne 23b
/* Flush the TLB of any entries for this LPID */
- /* use arch 2.07S as a proxy for POWER8 */
-BEGIN_FTR_SECTION
- li r6,512 /* POWER8 has 512 sets */
-FTR_SECTION_ELSE
- li r6,128 /* POWER7 has 128 sets */
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
+ lwz r6,KVM_TLB_SETS(r9)
+ li r0,0 /* RS for P9 version of tlbiel */
mtctr r6
li r7,0x800 /* IS field = 0b10 */
ptesync
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 05/11] KVM: PPC: Book3S HV: Adapt TLB invalidations to work on POWER9
@ 2016-11-23 0:31 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:31 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
POWER9 adds new capabilities to the tlbie (TLB invalidate entry)
and tlbiel (local tlbie) instructions. Both instructions get a
set of new parameters (RIC, PRS and R) which appear as bits in the
instruction word. The tlbiel instruction now has a second register
operand, which contains a PID and/or LPID value if needed, and
should otherwise contain 0.
This adapts KVM-HV's usage of tlbie and tlbiel to work on POWER9
as well as older processors. Since we only handle HPT guests so
far, we need RIC=0 PRS=0 R=0, which ends up with the same instruction
word as on previous processors, so we don't need to conditionally
execute different instructions depending on the processor.
The local flush on first entry to a guest in book3s_hv_rmhandlers.S
is a loop which depends on the number of TLB sets. Rather than
using feature sections to set the number of iterations based on
which CPU we're on, we now work out this number at VM creation time
and store it in the kvm_arch struct. That will make it possible to
get the number from the device tree in future, which will help with
compatibility with future processors.
Since mmu_partition_table_set_entry() does a global flush of the
whole LPID, we don't need to do the TLB flush on first entry to the
guest on each processor. Therefore we don't set all bits in the
tlb_need_flush bitmap on VM startup on POWER9.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_host.h | 1 +
arch/powerpc/kernel/asm-offsets.c | 1 +
arch/powerpc/kvm/book3s_hv.c | 17 ++++++++++++++++-
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 10 ++++++++--
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 ++------
5 files changed, 28 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9556de6..f15713a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -244,6 +244,7 @@ struct kvm_arch_memory_slot {
struct kvm_arch {
unsigned int lpid;
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ unsigned int tlb_sets;
unsigned long hpt_virt;
struct revmap_entry *revmap;
atomic64_t mmio_update;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index a4f6d5e..195a9fc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -487,6 +487,7 @@ int main(void)
/* book3s */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ DEFINE(KVM_TLB_SETS, offsetof(struct kvm, arch.tlb_sets));
DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 14eeacc..0a90fa4 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3265,8 +3265,11 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
* Since we don't flush the TLB when tearing down a VM,
* and this lpid might have previously been used,
* make sure we flush on each core before running the new VM.
+ * On POWER9, the tlbie in mmu_partition_table_set_entry()
+ * does this flush for us.
*/
- cpumask_setall(&kvm->arch.need_tlb_flush);
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ cpumask_setall(&kvm->arch.need_tlb_flush);
/* Start out with the default set of hcalls enabled */
memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls,
@@ -3292,6 +3295,17 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
kvm->arch.lpcr = lpcr;
/*
+ * Work out how many sets the TLB has, for the use of
+ * the TLB invalidation loop in book3s_hv_rmhandlers.S.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH; /* 256 */
+ else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ kvm->arch.tlb_sets = POWER8_TLB_SETS; /* 512 */
+ else
+ kvm->arch.tlb_sets = POWER7_TLB_SETS; /* 128 */
+
+ /*
* Track that we now have a HV mode VM active. This blocks secondary
* CPU threads from coming online.
*/
@@ -3733,3 +3747,4 @@ module_exit(kvmppc_book3s_exit_hv);
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");
+
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 59d3458..378b962 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -425,13 +425,18 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
{
long i;
+ /*
+ * We use the POWER9 5-operand versions of tlbie and tlbiel here.
+ * Since we are using RIC=0 PRS=0 R=0, and P7/P8 tlbiel ignores
+ * the RS field, this is backwards-compatible with P7 and P8.
+ */
if (global) {
while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
cpu_relax();
if (need_sync)
asm volatile("ptesync" : : : "memory");
for (i = 0; i < npages; ++i)
- asm volatile(PPC_TLBIE(%1,%0) : :
+ asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
"r" (rbvalues[i]), "r" (kvm->arch.lpid));
asm volatile("eieio; tlbsync; ptesync" : : : "memory");
kvm->arch.tlbie_lock = 0;
@@ -439,7 +444,8 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
if (need_sync)
asm volatile("ptesync" : : : "memory");
for (i = 0; i < npages; ++i)
- asm volatile("tlbiel %0" : : "r" (rbvalues[i]));
+ asm volatile(PPC_TLBIEL(%0,%1,0,0,0) : :
+ "r" (rbvalues[i]), "r" (0));
asm volatile("ptesync" : : : "memory");
}
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 499be60..598d828 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -613,12 +613,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
stdcx. r7,0,r6
bne 23b
/* Flush the TLB of any entries for this LPID */
- /* use arch 2.07S as a proxy for POWER8 */
-BEGIN_FTR_SECTION
- li r6,512 /* POWER8 has 512 sets */
-FTR_SECTION_ELSE
- li r6,128 /* POWER7 has 128 sets */
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
+ lwz r6,KVM_TLB_SETS(r9)
+ li r0,0 /* RS for P9 version of tlbiel */
mtctr r6
li r7,0x800 /* IS field = 0b10 */
ptesync
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 06/11] KVM: PPC: Book3S HV: Use msgsnd for IPIs to other cores on POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:32 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
On POWER9, the msgsnd instruction is able to send interrupts to
other cores, as well as other threads on the local core. Since
msgsnd is generally simpler and faster than sending an IPI via the
XICS, we use msgsnd for all IPIs sent by KVM on POWER9.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 11 ++++++++++-
arch/powerpc/kvm/book3s_hv_builtin.c | 10 ++++++++--
2 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0a90fa4..7a6a00a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -147,12 +147,21 @@ static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
static bool kvmppc_ipi_thread(int cpu)
{
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+
+ /* On POWER9 we can use msgsnd to IPI any cpu */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ msg |= get_hard_smp_processor_id(cpu);
+ smp_mb();
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ return true;
+ }
+
/* On POWER8 for IPIs to threads in the same core, use msgsnd */
if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
preempt_disable();
if (cpu_first_thread_sibling(cpu) ==
cpu_first_thread_sibling(smp_processor_id())) {
- unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
msg |= cpu_thread_in_core(cpu);
smp_mb();
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 90a0b27..e1e1ead 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -206,12 +206,18 @@ static inline void rm_writeb(unsigned long paddr, u8 val)
void kvmhv_rm_send_ipi(int cpu)
{
unsigned long xics_phys;
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
- /* On POWER8 for IPIs to threads in the same core, use msgsnd */
+ /* On POWER9 we can use msgsnd for any destination cpu. */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ msg |= get_hard_smp_processor_id(cpu);
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ return;
+ }
+ /* On POWER8 for IPIs to threads in the same core, use msgsnd. */
if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
cpu_first_thread_sibling(cpu) ==
cpu_first_thread_sibling(raw_smp_processor_id())) {
- unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
msg |= cpu_thread_in_core(cpu);
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
return;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 06/11] KVM: PPC: Book3S HV: Use msgsnd for IPIs to other cores on POWER9
@ 2016-11-23 0:32 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
On POWER9, the msgsnd instruction is able to send interrupts to
other cores, as well as other threads on the local core. Since
msgsnd is generally simpler and faster than sending an IPI via the
XICS, we use msgsnd for all IPIs sent by KVM on POWER9.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 11 ++++++++++-
arch/powerpc/kvm/book3s_hv_builtin.c | 10 ++++++++--
2 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0a90fa4..7a6a00a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -147,12 +147,21 @@ static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
static bool kvmppc_ipi_thread(int cpu)
{
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+
+ /* On POWER9 we can use msgsnd to IPI any cpu */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ msg |= get_hard_smp_processor_id(cpu);
+ smp_mb();
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ return true;
+ }
+
/* On POWER8 for IPIs to threads in the same core, use msgsnd */
if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
preempt_disable();
if (cpu_first_thread_sibling(cpu) =
cpu_first_thread_sibling(smp_processor_id())) {
- unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
msg |= cpu_thread_in_core(cpu);
smp_mb();
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 90a0b27..e1e1ead 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -206,12 +206,18 @@ static inline void rm_writeb(unsigned long paddr, u8 val)
void kvmhv_rm_send_ipi(int cpu)
{
unsigned long xics_phys;
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
- /* On POWER8 for IPIs to threads in the same core, use msgsnd */
+ /* On POWER9 we can use msgsnd for any destination cpu. */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ msg |= get_hard_smp_processor_id(cpu);
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ return;
+ }
+ /* On POWER8 for IPIs to threads in the same core, use msgsnd. */
if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
cpu_first_thread_sibling(cpu) =
cpu_first_thread_sibling(raw_smp_processor_id())) {
- unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
msg |= cpu_thread_in_core(cpu);
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
return;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 07/11] KVM: PPC: Book3S HV: Use OPAL XICS emulation on POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:32 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
POWER9 includes a new interrupt controller, called XIVE, which is
quite different from the XICS interrupt controller on POWER7 and
POWER8 machines. KVM-HV accesses the XICS directly in several places
in order to send and clear IPIs and handle interrupts from PCI
devices being passed through to the guest.
In order to make the transition to XIVE easier, OPAL firmware will
include an emulation of XICS on top of XIVE. Access to the emulated
XICS is via OPAL calls. The one complication is that the EOI
(end-of-interrupt) function can now return a value indicating that
another interrupt is pending; in this case, the XIVE will not signal
an interrupt in hardware to the CPU, and software is supposed to
acknowledge the new interrupt without waiting for another interrupt
to be delivered in hardware.
This adapts KVM-HV to use the OPAL calls on machines where there is
no XICS hardware. When there is no XICS, we look for a device-tree
node with "ibm,opal-intc" in its compatible property, which is how
OPAL indicates that it provides XICS emulation.
In order to handle the EOI return value, kvmppc_read_intr() has
become kvmppc_read_one_intr(), with a boolean variable passed by
reference which can be set by the EOI functions to indicate that
another interrupt is pending. The new kvmppc_read_intr() keeps
calling kvmppc_read_one_intr() until there are no more interrupts
to process. The return value from kvmppc_read_intr() is the
largest non-zero value of the returns from kvmppc_read_one_intr().
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_ppc.h | 7 +++--
arch/powerpc/kvm/book3s_hv.c | 28 +++++++++++++++--
arch/powerpc/kvm/book3s_hv_builtin.c | 59 ++++++++++++++++++++++++++++++------
arch/powerpc/kvm/book3s_hv_rm_xics.c | 23 ++++++++++----
4 files changed, 96 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index f6e4964..a5b94be 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -483,9 +483,10 @@ extern void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long guest_irq,
unsigned long host_irq);
extern void kvmppc_xics_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
unsigned long host_irq);
-extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, u32 xirr,
- struct kvmppc_irq_map *irq_map,
- struct kvmppc_passthru_irqmap *pimap);
+extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, __be32 xirr,
+ struct kvmppc_irq_map *irq_map,
+ struct kvmppc_passthru_irqmap *pimap,
+ bool *again);
extern int h_ipi_redirect;
#else
static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap(
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7a6a00a..aca9fbf 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -55,6 +55,8 @@
#include <asm/hmi.h>
#include <asm/pnv-pci.h>
#include <asm/mmu.h>
+#include <asm/opal.h>
+#include <asm/xics.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
@@ -63,6 +65,7 @@
#include <linux/irqbypass.h>
#include <linux/module.h>
#include <linux/compiler.h>
+#include <linux/of.h>
#include "book3s.h"
@@ -172,8 +175,12 @@ static bool kvmppc_ipi_thread(int cpu)
}
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
- if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
- xics_wake_cpu(cpu);
+ if (cpu >= 0 && cpu < nr_cpu_ids) {
+ if (paca[cpu].kvm_hstate.xics_phys) {
+ xics_wake_cpu(cpu);
+ return true;
+ }
+ opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
return true;
}
#endif
@@ -3734,6 +3741,23 @@ static int kvmppc_book3s_init_hv(void)
if (r)
return r;
+ /*
+ * We need a way of accessing the XICS interrupt controller,
+ * either directly, via paca[cpu].kvm_hstate.xics_phys, or
+ * indirectly, via OPAL.
+ */
+#ifdef CONFIG_SMP
+ if (!get_paca()->kvm_hstate.xics_phys) {
+ struct device_node *np;
+
+ np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
+ if (!np) {
+ pr_err("KVM-HV: Cannot determine method for accessing XICS\n");
+ return -ENODEV;
+ }
+ }
+#endif
+
kvm_ops_hv.owner = THIS_MODULE;
kvmppc_hv_ops = &kvm_ops_hv;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index e1e1ead..9e1223a 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -27,6 +27,7 @@
#include <asm/cputhreads.h>
#include <asm/io.h>
#include <asm/asm-prototypes.h>
+#include <asm/opal.h>
#define KVM_CMA_CHUNK_ORDER 18
@@ -225,7 +226,11 @@ void kvmhv_rm_send_ipi(int cpu)
/* Else poke the target with an IPI */
xics_phys = paca[cpu].kvm_hstate.xics_phys;
- rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ if (xics_phys)
+ rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ else
+ opal_rm_int_set_mfrr(get_hard_smp_processor_id(cpu),
+ IPI_PRIORITY);
}
/*
@@ -336,7 +341,7 @@ static struct kvmppc_irq_map *get_irqmap(struct kvmppc_passthru_irqmap *pimap,
* saved a copy of the XIRR in the PACA, it will be picked up by
* the host ICP driver.
*/
-static int kvmppc_check_passthru(u32 xisr, __be32 xirr)
+static int kvmppc_check_passthru(u32 xisr, __be32 xirr, bool *again)
{
struct kvmppc_passthru_irqmap *pimap;
struct kvmppc_irq_map *irq_map;
@@ -355,7 +360,7 @@ static int kvmppc_check_passthru(u32 xisr, __be32 xirr)
/* We're handling this interrupt, generic code doesn't need to */
local_paca->kvm_hstate.saved_xirr = 0;
- return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap);
+ return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap, again);
}
#else
@@ -374,14 +379,31 @@ static inline int kvmppc_check_passthru(u32 xisr, __be32 xirr)
* -1 if there was a guest wakeup IPI (which has now been cleared)
* -2 if there is PCI passthrough external interrupt that was handled
*/
+static long kvmppc_read_one_intr(bool *again);
long kvmppc_read_intr(void)
{
+ long ret = 0;
+ long rc;
+ bool again;
+
+ do {
+ again = false;
+ rc = kvmppc_read_one_intr(&again);
+ if (rc && (ret == 0 || rc > ret))
+ ret = rc;
+ } while (again);
+ return ret;
+}
+
+static long kvmppc_read_one_intr(bool *again)
+{
unsigned long xics_phys;
u32 h_xirr;
__be32 xirr;
u32 xisr;
u8 host_ipi;
+ int64_t rc;
/* see if a host IPI is pending */
host_ipi = local_paca->kvm_hstate.host_ipi;
@@ -390,8 +412,14 @@ long kvmppc_read_intr(void)
/* Now read the interrupt from the ICP */
xics_phys = local_paca->kvm_hstate.xics_phys;
- if (unlikely(!xics_phys))
- return 1;
+ if (!xics_phys) {
+ /* Use OPAL to read the XIRR */
+ rc = opal_rm_int_get_xirr(&xirr, false);
+ if (rc < 0)
+ return 1;
+ } else {
+ xirr = _lwzcix(xics_phys + XICS_XIRR);
+ }
/*
* Save XIRR for later. Since we get control in reverse endian
@@ -399,7 +427,6 @@ long kvmppc_read_intr(void)
* host endian. Note that xirr is the value read from the
* XIRR register, while h_xirr is the host endian version.
*/
- xirr = _lwzcix(xics_phys + XICS_XIRR);
h_xirr = be32_to_cpu(xirr);
local_paca->kvm_hstate.saved_xirr = h_xirr;
xisr = h_xirr & 0xffffff;
@@ -418,8 +445,16 @@ long kvmppc_read_intr(void)
* If it is an IPI, clear the MFRR and EOI it.
*/
if (xisr == XICS_IPI) {
- _stbcix(xics_phys + XICS_MFRR, 0xff);
- _stwcix(xics_phys + XICS_XIRR, xirr);
+ if (xics_phys) {
+ _stbcix(xics_phys + XICS_MFRR, 0xff);
+ _stwcix(xics_phys + XICS_XIRR, xirr);
+ } else {
+ opal_rm_int_set_mfrr(hard_smp_processor_id(), 0xff);
+ rc = opal_rm_int_eoi(h_xirr);
+ /* If rc > 0, there is another interrupt pending */
+ *again = rc > 0;
+ }
+
/*
* Need to ensure side effects of above stores
* complete before proceeding.
@@ -436,7 +471,11 @@ long kvmppc_read_intr(void)
/* We raced with the host,
* we need to resend that IPI, bummer
*/
- _stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ if (xics_phys)
+ _stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ else
+ opal_rm_int_set_mfrr(hard_smp_processor_id(),
+ IPI_PRIORITY);
/* Let side effects complete */
smp_mb();
return 1;
@@ -447,5 +486,5 @@ long kvmppc_read_intr(void)
return -1;
}
- return kvmppc_check_passthru(xisr, xirr);
+ return kvmppc_check_passthru(xisr, xirr, again);
}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index f2d4487..6a4c4d75 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -71,7 +71,11 @@ static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu)
hcpu = hcore << threads_shift;
kvmppc_host_rm_ops_hv->rm_core[hcore].rm_data = vcpu;
smp_muxed_ipi_set_message(hcpu, PPC_MSG_RM_HOST_ACTION);
- icp_native_cause_ipi_rm(hcpu);
+ if (paca[hcpu].kvm_hstate.xics_phys)
+ icp_native_cause_ipi_rm(hcpu);
+ else
+ opal_rm_int_set_mfrr(get_hard_smp_processor_id(hcpu),
+ IPI_PRIORITY);
}
#else
static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu) { }
@@ -738,7 +742,7 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
unsigned long eoi_rc;
-static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr)
+static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
{
unsigned long xics_phys;
int64_t rc;
@@ -752,7 +756,12 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr)
/* EOI it */
xics_phys = local_paca->kvm_hstate.xics_phys;
- _stwcix(xics_phys + XICS_XIRR, xirr);
+ if (xics_phys) {
+ _stwcix(xics_phys + XICS_XIRR, xirr);
+ } else {
+ rc = opal_rm_int_eoi(be32_to_cpu(xirr));
+ *again = rc > 0;
+ }
}
static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu)
@@ -810,9 +819,10 @@ static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc)
}
long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
- u32 xirr,
+ __be32 xirr,
struct kvmppc_irq_map *irq_map,
- struct kvmppc_passthru_irqmap *pimap)
+ struct kvmppc_passthru_irqmap *pimap,
+ bool *again)
{
struct kvmppc_xics *xics;
struct kvmppc_icp *icp;
@@ -826,7 +836,8 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
icp_rm_deliver_irq(xics, icp, irq);
/* EOI the interrupt */
- icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr);
+ icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr,
+ again);
if (check_too_hard(xics, icp) == H_TOO_HARD)
return 2;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 07/11] KVM: PPC: Book3S HV: Use OPAL XICS emulation on POWER9
@ 2016-11-23 0:32 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
POWER9 includes a new interrupt controller, called XIVE, which is
quite different from the XICS interrupt controller on POWER7 and
POWER8 machines. KVM-HV accesses the XICS directly in several places
in order to send and clear IPIs and handle interrupts from PCI
devices being passed through to the guest.
In order to make the transition to XIVE easier, OPAL firmware will
include an emulation of XICS on top of XIVE. Access to the emulated
XICS is via OPAL calls. The one complication is that the EOI
(end-of-interrupt) function can now return a value indicating that
another interrupt is pending; in this case, the XIVE will not signal
an interrupt in hardware to the CPU, and software is supposed to
acknowledge the new interrupt without waiting for another interrupt
to be delivered in hardware.
This adapts KVM-HV to use the OPAL calls on machines where there is
no XICS hardware. When there is no XICS, we look for a device-tree
node with "ibm,opal-intc" in its compatible property, which is how
OPAL indicates that it provides XICS emulation.
In order to handle the EOI return value, kvmppc_read_intr() has
become kvmppc_read_one_intr(), with a boolean variable passed by
reference which can be set by the EOI functions to indicate that
another interrupt is pending. The new kvmppc_read_intr() keeps
calling kvmppc_read_one_intr() until there are no more interrupts
to process. The return value from kvmppc_read_intr() is the
largest non-zero value of the returns from kvmppc_read_one_intr().
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_ppc.h | 7 +++--
arch/powerpc/kvm/book3s_hv.c | 28 +++++++++++++++--
arch/powerpc/kvm/book3s_hv_builtin.c | 59 ++++++++++++++++++++++++++++++------
arch/powerpc/kvm/book3s_hv_rm_xics.c | 23 ++++++++++----
4 files changed, 96 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index f6e4964..a5b94be 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -483,9 +483,10 @@ extern void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long guest_irq,
unsigned long host_irq);
extern void kvmppc_xics_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
unsigned long host_irq);
-extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, u32 xirr,
- struct kvmppc_irq_map *irq_map,
- struct kvmppc_passthru_irqmap *pimap);
+extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, __be32 xirr,
+ struct kvmppc_irq_map *irq_map,
+ struct kvmppc_passthru_irqmap *pimap,
+ bool *again);
extern int h_ipi_redirect;
#else
static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap(
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7a6a00a..aca9fbf 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -55,6 +55,8 @@
#include <asm/hmi.h>
#include <asm/pnv-pci.h>
#include <asm/mmu.h>
+#include <asm/opal.h>
+#include <asm/xics.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
@@ -63,6 +65,7 @@
#include <linux/irqbypass.h>
#include <linux/module.h>
#include <linux/compiler.h>
+#include <linux/of.h>
#include "book3s.h"
@@ -172,8 +175,12 @@ static bool kvmppc_ipi_thread(int cpu)
}
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
- if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
- xics_wake_cpu(cpu);
+ if (cpu >= 0 && cpu < nr_cpu_ids) {
+ if (paca[cpu].kvm_hstate.xics_phys) {
+ xics_wake_cpu(cpu);
+ return true;
+ }
+ opal_int_set_mfrr(get_hard_smp_processor_id(cpu), IPI_PRIORITY);
return true;
}
#endif
@@ -3734,6 +3741,23 @@ static int kvmppc_book3s_init_hv(void)
if (r)
return r;
+ /*
+ * We need a way of accessing the XICS interrupt controller,
+ * either directly, via paca[cpu].kvm_hstate.xics_phys, or
+ * indirectly, via OPAL.
+ */
+#ifdef CONFIG_SMP
+ if (!get_paca()->kvm_hstate.xics_phys) {
+ struct device_node *np;
+
+ np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
+ if (!np) {
+ pr_err("KVM-HV: Cannot determine method for accessing XICS\n");
+ return -ENODEV;
+ }
+ }
+#endif
+
kvm_ops_hv.owner = THIS_MODULE;
kvmppc_hv_ops = &kvm_ops_hv;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index e1e1ead..9e1223a 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -27,6 +27,7 @@
#include <asm/cputhreads.h>
#include <asm/io.h>
#include <asm/asm-prototypes.h>
+#include <asm/opal.h>
#define KVM_CMA_CHUNK_ORDER 18
@@ -225,7 +226,11 @@ void kvmhv_rm_send_ipi(int cpu)
/* Else poke the target with an IPI */
xics_phys = paca[cpu].kvm_hstate.xics_phys;
- rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ if (xics_phys)
+ rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ else
+ opal_rm_int_set_mfrr(get_hard_smp_processor_id(cpu),
+ IPI_PRIORITY);
}
/*
@@ -336,7 +341,7 @@ static struct kvmppc_irq_map *get_irqmap(struct kvmppc_passthru_irqmap *pimap,
* saved a copy of the XIRR in the PACA, it will be picked up by
* the host ICP driver.
*/
-static int kvmppc_check_passthru(u32 xisr, __be32 xirr)
+static int kvmppc_check_passthru(u32 xisr, __be32 xirr, bool *again)
{
struct kvmppc_passthru_irqmap *pimap;
struct kvmppc_irq_map *irq_map;
@@ -355,7 +360,7 @@ static int kvmppc_check_passthru(u32 xisr, __be32 xirr)
/* We're handling this interrupt, generic code doesn't need to */
local_paca->kvm_hstate.saved_xirr = 0;
- return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap);
+ return kvmppc_deliver_irq_passthru(vcpu, xirr, irq_map, pimap, again);
}
#else
@@ -374,14 +379,31 @@ static inline int kvmppc_check_passthru(u32 xisr, __be32 xirr)
* -1 if there was a guest wakeup IPI (which has now been cleared)
* -2 if there is PCI passthrough external interrupt that was handled
*/
+static long kvmppc_read_one_intr(bool *again);
long kvmppc_read_intr(void)
{
+ long ret = 0;
+ long rc;
+ bool again;
+
+ do {
+ again = false;
+ rc = kvmppc_read_one_intr(&again);
+ if (rc && (ret = 0 || rc > ret))
+ ret = rc;
+ } while (again);
+ return ret;
+}
+
+static long kvmppc_read_one_intr(bool *again)
+{
unsigned long xics_phys;
u32 h_xirr;
__be32 xirr;
u32 xisr;
u8 host_ipi;
+ int64_t rc;
/* see if a host IPI is pending */
host_ipi = local_paca->kvm_hstate.host_ipi;
@@ -390,8 +412,14 @@ long kvmppc_read_intr(void)
/* Now read the interrupt from the ICP */
xics_phys = local_paca->kvm_hstate.xics_phys;
- if (unlikely(!xics_phys))
- return 1;
+ if (!xics_phys) {
+ /* Use OPAL to read the XIRR */
+ rc = opal_rm_int_get_xirr(&xirr, false);
+ if (rc < 0)
+ return 1;
+ } else {
+ xirr = _lwzcix(xics_phys + XICS_XIRR);
+ }
/*
* Save XIRR for later. Since we get control in reverse endian
@@ -399,7 +427,6 @@ long kvmppc_read_intr(void)
* host endian. Note that xirr is the value read from the
* XIRR register, while h_xirr is the host endian version.
*/
- xirr = _lwzcix(xics_phys + XICS_XIRR);
h_xirr = be32_to_cpu(xirr);
local_paca->kvm_hstate.saved_xirr = h_xirr;
xisr = h_xirr & 0xffffff;
@@ -418,8 +445,16 @@ long kvmppc_read_intr(void)
* If it is an IPI, clear the MFRR and EOI it.
*/
if (xisr = XICS_IPI) {
- _stbcix(xics_phys + XICS_MFRR, 0xff);
- _stwcix(xics_phys + XICS_XIRR, xirr);
+ if (xics_phys) {
+ _stbcix(xics_phys + XICS_MFRR, 0xff);
+ _stwcix(xics_phys + XICS_XIRR, xirr);
+ } else {
+ opal_rm_int_set_mfrr(hard_smp_processor_id(), 0xff);
+ rc = opal_rm_int_eoi(h_xirr);
+ /* If rc > 0, there is another interrupt pending */
+ *again = rc > 0;
+ }
+
/*
* Need to ensure side effects of above stores
* complete before proceeding.
@@ -436,7 +471,11 @@ long kvmppc_read_intr(void)
/* We raced with the host,
* we need to resend that IPI, bummer
*/
- _stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ if (xics_phys)
+ _stbcix(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ else
+ opal_rm_int_set_mfrr(hard_smp_processor_id(),
+ IPI_PRIORITY);
/* Let side effects complete */
smp_mb();
return 1;
@@ -447,5 +486,5 @@ long kvmppc_read_intr(void)
return -1;
}
- return kvmppc_check_passthru(xisr, xirr);
+ return kvmppc_check_passthru(xisr, xirr, again);
}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index f2d4487..6a4c4d75 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -71,7 +71,11 @@ static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu)
hcpu = hcore << threads_shift;
kvmppc_host_rm_ops_hv->rm_core[hcore].rm_data = vcpu;
smp_muxed_ipi_set_message(hcpu, PPC_MSG_RM_HOST_ACTION);
- icp_native_cause_ipi_rm(hcpu);
+ if (paca[hcpu].kvm_hstate.xics_phys)
+ icp_native_cause_ipi_rm(hcpu);
+ else
+ opal_rm_int_set_mfrr(get_hard_smp_processor_id(hcpu),
+ IPI_PRIORITY);
}
#else
static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu) { }
@@ -738,7 +742,7 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
unsigned long eoi_rc;
-static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr)
+static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
{
unsigned long xics_phys;
int64_t rc;
@@ -752,7 +756,12 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, u32 xirr)
/* EOI it */
xics_phys = local_paca->kvm_hstate.xics_phys;
- _stwcix(xics_phys + XICS_XIRR, xirr);
+ if (xics_phys) {
+ _stwcix(xics_phys + XICS_XIRR, xirr);
+ } else {
+ rc = opal_rm_int_eoi(be32_to_cpu(xirr));
+ *again = rc > 0;
+ }
}
static int xics_opal_rm_set_server(unsigned int hw_irq, int server_cpu)
@@ -810,9 +819,10 @@ static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc)
}
long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
- u32 xirr,
+ __be32 xirr,
struct kvmppc_irq_map *irq_map,
- struct kvmppc_passthru_irqmap *pimap)
+ struct kvmppc_passthru_irqmap *pimap,
+ bool *again)
{
struct kvmppc_xics *xics;
struct kvmppc_icp *icp;
@@ -826,7 +836,8 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu,
icp_rm_deliver_irq(xics, icp, irq);
/* EOI the interrupt */
- icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr);
+ icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr,
+ again);
if (check_too_hard(xics, icp) = H_TOO_HARD)
return 2;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 08/11] KVM: PPC: Book3S HV: Use stop instruction rather than nap on POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:32 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
POWER9 replaces the various power-saving mode instructions on POWER8
(doze, nap, sleep and rvwinkle) with a single "stop" instruction, plus
a register, PSSCR, which controls the depth of the power-saving mode.
This replaces the use of the nap instruction when threads are idle
during guest execution with the stop instruction, and adds code to
set PSSCR to a value which will allow an SMT mode switch while the
thread is idle (given that the core as a whole won't be idle in these
cases).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 33 ++++++++++++++++++++++-----------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 598d828..9338a81 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -501,17 +501,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
cmpwi r0, 0
beq 57f
li r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
- mfspr r4, SPRN_LPCR
- rlwimi r4, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
- mtspr SPRN_LPCR, r4
- isync
- std r0, HSTATE_SCRATCH0(r13)
- ptesync
- ld r0, HSTATE_SCRATCH0(r13)
-1: cmpd r0, r0
- bne 1b
- nap
- b .
+ mfspr r5, SPRN_LPCR
+ rlwimi r5, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
+ b kvm_nap_sequence
57: li r0, 0
stbx r0, r3, r4
@@ -2256,6 +2248,21 @@ BEGIN_FTR_SECTION
ori r5, r5, LPCR_PECEDH
rlwimi r5, r3, 0, LPCR_PECEDP
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
+kvm_nap_sequence: /* desired LPCR value in r5 */
+BEGIN_FTR_SECTION
+ /*
+ * PSSCR bits: exit criterion = 1 (wakeup based on LPCR at sreset)
+ * enable state loss = 1 (allow SMT mode switch)
+ * requested level = 0 (just stop dispatching)
+ */
+ lis r3, (PSSCR_EC | PSSCR_ESL)@h
+ mtspr SPRN_PSSCR, r3
+ /* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
+ li r4, LPCR_PECE_HVEE@higher
+ sldi r4, r4, 32
+ or r5, r5, r4
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
mtspr SPRN_LPCR,r5
isync
li r0, 0
@@ -2264,7 +2271,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
ld r0, HSTATE_SCRATCH0(r13)
1: cmpd r0, r0
bne 1b
+BEGIN_FTR_SECTION
nap
+FTR_SECTION_ELSE
+ PPC_STOP
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
b .
33: mr r4, r3
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 08/11] KVM: PPC: Book3S HV: Use stop instruction rather than nap on POWER9
@ 2016-11-23 0:32 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
POWER9 replaces the various power-saving mode instructions on POWER8
(doze, nap, sleep and rvwinkle) with a single "stop" instruction, plus
a register, PSSCR, which controls the depth of the power-saving mode.
This replaces the use of the nap instruction when threads are idle
during guest execution with the stop instruction, and adds code to
set PSSCR to a value which will allow an SMT mode switch while the
thread is idle (given that the core as a whole won't be idle in these
cases).
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 33 ++++++++++++++++++++++-----------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 598d828..9338a81 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -501,17 +501,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
cmpwi r0, 0
beq 57f
li r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
- mfspr r4, SPRN_LPCR
- rlwimi r4, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
- mtspr SPRN_LPCR, r4
- isync
- std r0, HSTATE_SCRATCH0(r13)
- ptesync
- ld r0, HSTATE_SCRATCH0(r13)
-1: cmpd r0, r0
- bne 1b
- nap
- b .
+ mfspr r5, SPRN_LPCR
+ rlwimi r5, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
+ b kvm_nap_sequence
57: li r0, 0
stbx r0, r3, r4
@@ -2256,6 +2248,21 @@ BEGIN_FTR_SECTION
ori r5, r5, LPCR_PECEDH
rlwimi r5, r3, 0, LPCR_PECEDP
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
+kvm_nap_sequence: /* desired LPCR value in r5 */
+BEGIN_FTR_SECTION
+ /*
+ * PSSCR bits: exit criterion = 1 (wakeup based on LPCR at sreset)
+ * enable state loss = 1 (allow SMT mode switch)
+ * requested level = 0 (just stop dispatching)
+ */
+ lis r3, (PSSCR_EC | PSSCR_ESL)@h
+ mtspr SPRN_PSSCR, r3
+ /* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
+ li r4, LPCR_PECE_HVEE@higher
+ sldi r4, r4, 32
+ or r5, r5, r4
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
mtspr SPRN_LPCR,r5
isync
li r0, 0
@@ -2264,7 +2271,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
ld r0, HSTATE_SCRATCH0(r13)
1: cmpd r0, r0
bne 1b
+BEGIN_FTR_SECTION
nap
+FTR_SECTION_ELSE
+ PPC_STOP
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
b .
33: mr r4, r3
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 09/11] KVM: PPC: Book3S HV: Enable hypervisor virtualization interrupts while in guest
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:32 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
The new XIVE interrupt controller on POWER9 can direct external
interrupts to the hypervisor or the guest. The interrupts directed to
the hypervisor are controlled by an LPCR bit called LPCR_HVICE, and
come in as a "hypervisor virtualization interrupt". This sets the
LPCR bit so that hypervisor virtualization interrupts can occur while
we are in the guest. We then also need to cope with exiting the guest
because of a hypervisor virtualization interrupt.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_asm.h | 1 +
arch/powerpc/kvm/book3s_hv.c | 11 +++++++++--
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 05cabed..09a802b 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -99,6 +99,7 @@
#define BOOK3S_INTERRUPT_H_EMUL_ASSIST 0xe40
#define BOOK3S_INTERRUPT_HMI 0xe60
#define BOOK3S_INTERRUPT_H_DOORBELL 0xe80
+#define BOOK3S_INTERRUPT_H_VIRT 0xea0
#define BOOK3S_INTERRUPT_PERFMON 0xf00
#define BOOK3S_INTERRUPT_ALTIVEC 0xf20
#define BOOK3S_INTERRUPT_VSX 0xf40
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index aca9fbf..b6bc867 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -962,6 +962,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
break;
case BOOK3S_INTERRUPT_EXTERNAL:
case BOOK3S_INTERRUPT_H_DOORBELL:
+ case BOOK3S_INTERRUPT_H_VIRT:
vcpu->stat.ext_intr_exits++;
r = RESUME_GUEST;
break;
@@ -3305,9 +3306,15 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/* On POWER8 turn on online bit to enable PURR/SPURR */
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lpcr |= LPCR_ONL;
- /* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed) */
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ /*
+ * On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
+ * Set HVICE bit to enable hypervisor virtualization interrupts.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
lpcr &= ~LPCR_VPM0;
+ lpcr |= LPCR_HVICE;
+ }
+
kvm->arch.lpcr = lpcr;
/*
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 09/11] KVM: PPC: Book3S HV: Enable hypervisor virtualization interrupts while in guest
@ 2016-11-23 0:32 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
The new XIVE interrupt controller on POWER9 can direct external
interrupts to the hypervisor or the guest. The interrupts directed to
the hypervisor are controlled by an LPCR bit called LPCR_HVICE, and
come in as a "hypervisor virtualization interrupt". This sets the
LPCR bit so that hypervisor virtualization interrupts can occur while
we are in the guest. We then also need to cope with exiting the guest
because of a hypervisor virtualization interrupt.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_asm.h | 1 +
arch/powerpc/kvm/book3s_hv.c | 11 +++++++++--
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 05cabed..09a802b 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -99,6 +99,7 @@
#define BOOK3S_INTERRUPT_H_EMUL_ASSIST 0xe40
#define BOOK3S_INTERRUPT_HMI 0xe60
#define BOOK3S_INTERRUPT_H_DOORBELL 0xe80
+#define BOOK3S_INTERRUPT_H_VIRT 0xea0
#define BOOK3S_INTERRUPT_PERFMON 0xf00
#define BOOK3S_INTERRUPT_ALTIVEC 0xf20
#define BOOK3S_INTERRUPT_VSX 0xf40
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index aca9fbf..b6bc867 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -962,6 +962,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
break;
case BOOK3S_INTERRUPT_EXTERNAL:
case BOOK3S_INTERRUPT_H_DOORBELL:
+ case BOOK3S_INTERRUPT_H_VIRT:
vcpu->stat.ext_intr_exits++;
r = RESUME_GUEST;
break;
@@ -3305,9 +3306,15 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/* On POWER8 turn on online bit to enable PURR/SPURR */
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lpcr |= LPCR_ONL;
- /* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed) */
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ /*
+ * On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
+ * Set HVICE bit to enable hypervisor virtualization interrupts.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
lpcr &= ~LPCR_VPM0;
+ lpcr |= LPCR_HVICE;
+ }
+
kvm->arch.lpcr = lpcr;
/*
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 10/11] KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:32 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 49 +++++++++++++++++++++++++++++++++-----------
arch/powerpc/kvm/powerpc.c | 11 ++++++----
2 files changed, 44 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index b6bc867..94294c3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1576,6 +1576,20 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
return r;
}
+/*
+ * On POWER9, threads are independent and can be in different partitions.
+ * Therefore we consider each thread to be a subcore.
+ * There is a restriction that all threads have to be in the same
+ * MMU mode (radix or HPT), unfortunately, but since we only support
+ * HPT guests on a HPT host so far, that isn't an impediment yet.
+ */
+static int threads_per_vcore(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ return 1;
+ return threads_per_subcore;
+}
+
static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
{
struct kvmppc_vcore *vcore;
@@ -1590,7 +1604,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
init_swait_queue_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
- vcore->first_vcpuid = core * threads_per_subcore;
+ vcore->first_vcpuid = core * threads_per_vcore();
vcore->kvm = kvm;
INIT_LIST_HEAD(&vcore->preempt_list);
@@ -1753,7 +1767,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
int core;
struct kvmppc_vcore *vcore;
- core = id / threads_per_subcore;
+ core = id / threads_per_vcore();
if (core >= KVM_MAX_VCORES)
goto out;
@@ -1971,7 +1985,10 @@ static void kvmppc_wait_for_nap(void)
{
int cpu = smp_processor_id();
int i, loops;
+ int n_threads = threads_per_vcore();
+ if (n_threads <= 1)
+ return;
for (loops = 0; loops < 1000000; ++loops) {
/*
* Check if all threads are finished.
@@ -1979,17 +1996,17 @@ static void kvmppc_wait_for_nap(void)
* and the thread clears it when finished, so we look
* for any threads that still have a non-NULL vcore ptr.
*/
- for (i = 1; i < threads_per_subcore; ++i)
+ for (i = 1; i < n_threads; ++i)
if (paca[cpu + i].kvm_hstate.kvm_vcore)
break;
- if (i == threads_per_subcore) {
+ if (i == n_threads) {
HMT_medium();
return;
}
HMT_low();
}
HMT_medium();
- for (i = 1; i < threads_per_subcore; ++i)
+ for (i = 1; i < n_threads; ++i)
if (paca[cpu + i].kvm_hstate.kvm_vcore)
pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}
@@ -2055,7 +2072,7 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc)
vc->vcore_state = VCORE_PREEMPT;
vc->pcpu = smp_processor_id();
- if (vc->num_threads < threads_per_subcore) {
+ if (vc->num_threads < threads_per_vcore()) {
spin_lock(&lp->lock);
list_add_tail(&vc->preempt_list, &lp->list);
spin_unlock(&lp->lock);
@@ -2342,6 +2359,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
unsigned long cmd_bit, stat_bit;
int pcpu, thr;
int target_threads;
+ int controlled_threads;
/*
* Remove from the list any threads that have a signal pending
@@ -2360,11 +2378,18 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
vc->preempt_tb = TB_NIL;
/*
+ * Number of threads that we will be controlling: the same as
+ * the number of threads per subcore, except on POWER9,
+ * where it's 1 because the threads are (mostly) independent.
+ */
+ controlled_threads = threads_per_vcore();
+
+ /*
* Make sure we are running on primary threads, and that secondary
* threads are offline. Also check if the number of threads in this
* guest are greater than the current system threads per guest.
*/
- if ((threads_per_core > 1) &&
+ if ((controlled_threads > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
for_each_runnable_thread(i, vcpu, vc) {
vcpu->arch.ret = -EBUSY;
@@ -2380,7 +2405,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
*/
init_core_info(&core_info, vc);
pcpu = smp_processor_id();
- target_threads = threads_per_subcore;
+ target_threads = controlled_threads;
if (target_smt_mode && target_smt_mode < target_threads)
target_threads = target_smt_mode;
if (vc->num_threads < target_threads)
@@ -2416,7 +2441,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
smp_wmb();
}
pcpu = smp_processor_id();
- for (thr = 0; thr < threads_per_subcore; ++thr)
+ for (thr = 0; thr < controlled_threads; ++thr)
paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
/* Initiate micro-threading (split-core) if required */
@@ -2526,7 +2551,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
}
/* Let secondaries go back to the offline loop */
- for (i = 0; i < threads_per_subcore; ++i) {
+ for (i = 0; i < controlled_threads; ++i) {
kvmppc_release_hwthread(pcpu + i);
if (sip && sip->napped[i])
kvmppc_ipi_thread(pcpu + i);
@@ -3392,9 +3417,9 @@ static int kvmppc_core_check_processor_compat_hv(void)
!cpu_has_feature(CPU_FTR_ARCH_206))
return -EIO;
/*
- * Disable KVM for Power9, untill the required bits merged.
+ * Disable KVM for Power9 in radix mode.
*/
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
return -EIO;
return 0;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 70963c8..b5e4705 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -548,10 +548,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
case KVM_CAP_PPC_SMT:
- if (hv_enabled)
- r = threads_per_subcore;
- else
- r = 0;
+ r = 0;
+ if (hv_enabled) {
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ r = 1;
+ else
+ r = threads_per_subcore;
+ }
break;
case KVM_CAP_PPC_RMA:
r = 0;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 10/11] KVM: PPC: Book3S HV: Treat POWER9 CPU threads as independent subcores
@ 2016-11-23 0:32 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
With POWER9, each CPU thread has its own MMU context and can be
in the host or a guest independently of the other threads; there is
still however a restriction that all threads must use the same type
of address translation, either radix tree or hashed page table (HPT).
Since we only support HPT guests on a HPT host at this point, we
can treat the threads as being independent, and avoid all of the
work of coordinating the CPU threads. To make this simpler, we
introduce a new threads_per_vcore() function that returns 1 on
POWER9 and threads_per_subcore on POWER7/8, and use that instead
of threads_per_subcore or threads_per_core in various places.
This also changes the value of the KVM_CAP_PPC_SMT capability on
POWER9 systems from 4 to 1, so that userspace will not try to
create VMs with multiple vcpus per vcore. (If userspace did create
a VM that thought it was in an SMT mode, the VM might try to use
the msgsndp instruction, which will not work as expected. In
future it may be possible to trap and emulate msgsndp in order to
allow VMs to think they are in an SMT mode, if only for the purpose
of allowing migration from POWER8 systems.)
With all this, we can now run guests on POWER9 as long as the host
is running with HPT translation. Since userspace currently has no
way to request radix tree translation for the guest, the guest has
no choice but to use HPT translation.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 49 +++++++++++++++++++++++++++++++++-----------
arch/powerpc/kvm/powerpc.c | 11 ++++++----
2 files changed, 44 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index b6bc867..94294c3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1576,6 +1576,20 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
return r;
}
+/*
+ * On POWER9, threads are independent and can be in different partitions.
+ * Therefore we consider each thread to be a subcore.
+ * There is a restriction that all threads have to be in the same
+ * MMU mode (radix or HPT), unfortunately, but since we only support
+ * HPT guests on a HPT host so far, that isn't an impediment yet.
+ */
+static int threads_per_vcore(void)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ return 1;
+ return threads_per_subcore;
+}
+
static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
{
struct kvmppc_vcore *vcore;
@@ -1590,7 +1604,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
init_swait_queue_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
- vcore->first_vcpuid = core * threads_per_subcore;
+ vcore->first_vcpuid = core * threads_per_vcore();
vcore->kvm = kvm;
INIT_LIST_HEAD(&vcore->preempt_list);
@@ -1753,7 +1767,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
int core;
struct kvmppc_vcore *vcore;
- core = id / threads_per_subcore;
+ core = id / threads_per_vcore();
if (core >= KVM_MAX_VCORES)
goto out;
@@ -1971,7 +1985,10 @@ static void kvmppc_wait_for_nap(void)
{
int cpu = smp_processor_id();
int i, loops;
+ int n_threads = threads_per_vcore();
+ if (n_threads <= 1)
+ return;
for (loops = 0; loops < 1000000; ++loops) {
/*
* Check if all threads are finished.
@@ -1979,17 +1996,17 @@ static void kvmppc_wait_for_nap(void)
* and the thread clears it when finished, so we look
* for any threads that still have a non-NULL vcore ptr.
*/
- for (i = 1; i < threads_per_subcore; ++i)
+ for (i = 1; i < n_threads; ++i)
if (paca[cpu + i].kvm_hstate.kvm_vcore)
break;
- if (i = threads_per_subcore) {
+ if (i = n_threads) {
HMT_medium();
return;
}
HMT_low();
}
HMT_medium();
- for (i = 1; i < threads_per_subcore; ++i)
+ for (i = 1; i < n_threads; ++i)
if (paca[cpu + i].kvm_hstate.kvm_vcore)
pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}
@@ -2055,7 +2072,7 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc)
vc->vcore_state = VCORE_PREEMPT;
vc->pcpu = smp_processor_id();
- if (vc->num_threads < threads_per_subcore) {
+ if (vc->num_threads < threads_per_vcore()) {
spin_lock(&lp->lock);
list_add_tail(&vc->preempt_list, &lp->list);
spin_unlock(&lp->lock);
@@ -2342,6 +2359,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
unsigned long cmd_bit, stat_bit;
int pcpu, thr;
int target_threads;
+ int controlled_threads;
/*
* Remove from the list any threads that have a signal pending
@@ -2360,11 +2378,18 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
vc->preempt_tb = TB_NIL;
/*
+ * Number of threads that we will be controlling: the same as
+ * the number of threads per subcore, except on POWER9,
+ * where it's 1 because the threads are (mostly) independent.
+ */
+ controlled_threads = threads_per_vcore();
+
+ /*
* Make sure we are running on primary threads, and that secondary
* threads are offline. Also check if the number of threads in this
* guest are greater than the current system threads per guest.
*/
- if ((threads_per_core > 1) &&
+ if ((controlled_threads > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
for_each_runnable_thread(i, vcpu, vc) {
vcpu->arch.ret = -EBUSY;
@@ -2380,7 +2405,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
*/
init_core_info(&core_info, vc);
pcpu = smp_processor_id();
- target_threads = threads_per_subcore;
+ target_threads = controlled_threads;
if (target_smt_mode && target_smt_mode < target_threads)
target_threads = target_smt_mode;
if (vc->num_threads < target_threads)
@@ -2416,7 +2441,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
smp_wmb();
}
pcpu = smp_processor_id();
- for (thr = 0; thr < threads_per_subcore; ++thr)
+ for (thr = 0; thr < controlled_threads; ++thr)
paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
/* Initiate micro-threading (split-core) if required */
@@ -2526,7 +2551,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
}
/* Let secondaries go back to the offline loop */
- for (i = 0; i < threads_per_subcore; ++i) {
+ for (i = 0; i < controlled_threads; ++i) {
kvmppc_release_hwthread(pcpu + i);
if (sip && sip->napped[i])
kvmppc_ipi_thread(pcpu + i);
@@ -3392,9 +3417,9 @@ static int kvmppc_core_check_processor_compat_hv(void)
!cpu_has_feature(CPU_FTR_ARCH_206))
return -EIO;
/*
- * Disable KVM for Power9, untill the required bits merged.
+ * Disable KVM for Power9 in radix mode.
*/
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
return -EIO;
return 0;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 70963c8..b5e4705 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -548,10 +548,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
case KVM_CAP_PPC_SMT:
- if (hv_enabled)
- r = threads_per_subcore;
- else
- r = 0;
+ r = 0;
+ if (hv_enabled) {
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ r = 1;
+ else
+ r = threads_per_subcore;
+ }
break;
case KVM_CAP_PPC_RMA:
r = 0;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread
* [PATCH v2 11/11] KVM: PPC: Book3S HV: Update kvmppc_set_arch_compat() for ISA v3.00
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 0:32 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
The function kvmppc_set_arch_compat() is used to determine the value of the
processor compatibility register (PCR) for a guest running in a given
compatibility mode. There is currently no support for v3.00 of the ISA.
Add support for v3.00 of the ISA which adds an ISA v2.07 compatilibity mode
to the PCR.
We also add a check to ensure the processor we are running on is capable of
emulating the chosen processor (for example a POWER7 cannot emulate a
POWER8, similarly with a POWER8 and a POWER9).
Based on work by: Paul Mackerras <paulus@ozlabs.org>
[paulus@ozlabs.org - moved dummy PCR_ARCH_300 definition here; set
guest_pcr_bit when arch_compat == 0, added comment.]
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 43 ++++++++++++++++++++++++++++---------------
1 file changed, 28 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 94294c3..7ee77fe 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -316,41 +316,54 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
vcpu->arch.pvr = pvr;
}
+/* Dummy value used in computing PCR value below */
+#define PCR_ARCH_300 (PCR_ARCH_207 << 1)
+
static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
{
- unsigned long pcr = 0;
+ unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ /* We can (emulate) our own architecture version and anything older */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ host_pcr_bit = PCR_ARCH_300;
+ else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ host_pcr_bit = PCR_ARCH_207;
+ else if (cpu_has_feature(CPU_FTR_ARCH_206))
+ host_pcr_bit = PCR_ARCH_206;
+ else
+ host_pcr_bit = PCR_ARCH_205;
+
+ /* Determine lowest PCR bit needed to run guest in given PVR level */
+ guest_pcr_bit = host_pcr_bit;
if (arch_compat) {
switch (arch_compat) {
case PVR_ARCH_205:
- /*
- * If an arch bit is set in PCR, all the defined
- * higher-order arch bits also have to be set.
- */
- pcr = PCR_ARCH_206 | PCR_ARCH_205;
+ guest_pcr_bit = PCR_ARCH_205;
break;
case PVR_ARCH_206:
case PVR_ARCH_206p:
- pcr = PCR_ARCH_206;
+ guest_pcr_bit = PCR_ARCH_206;
break;
case PVR_ARCH_207:
+ guest_pcr_bit = PCR_ARCH_207;
+ break;
+ case PVR_ARCH_300:
+ guest_pcr_bit = PCR_ARCH_300;
break;
default:
return -EINVAL;
}
-
- if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
- /* POWER7 can't emulate POWER8 */
- if (!(pcr & PCR_ARCH_206))
- return -EINVAL;
- pcr &= ~PCR_ARCH_206;
- }
}
+ /* Check requested PCR bits don't exceed our capabilities */
+ if (guest_pcr_bit > host_pcr_bit)
+ return -EINVAL;
+
spin_lock(&vc->lock);
vc->arch_compat = arch_compat;
- vc->pcr = pcr;
+ /* Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit */
+ vc->pcr = host_pcr_bit - guest_pcr_bit;
spin_unlock(&vc->lock);
return 0;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* [PATCH v2 11/11] KVM: PPC: Book3S HV: Update kvmppc_set_arch_compat() for ISA v3.00
@ 2016-11-23 0:32 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 0:32 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
The function kvmppc_set_arch_compat() is used to determine the value of the
processor compatibility register (PCR) for a guest running in a given
compatibility mode. There is currently no support for v3.00 of the ISA.
Add support for v3.00 of the ISA which adds an ISA v2.07 compatilibity mode
to the PCR.
We also add a check to ensure the processor we are running on is capable of
emulating the chosen processor (for example a POWER7 cannot emulate a
POWER8, similarly with a POWER8 and a POWER9).
Based on work by: Paul Mackerras <paulus@ozlabs.org>
[paulus@ozlabs.org - moved dummy PCR_ARCH_300 definition here; set
guest_pcr_bit when arch_compat = 0, added comment.]
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 43 ++++++++++++++++++++++++++++---------------
1 file changed, 28 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 94294c3..7ee77fe 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -316,41 +316,54 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
vcpu->arch.pvr = pvr;
}
+/* Dummy value used in computing PCR value below */
+#define PCR_ARCH_300 (PCR_ARCH_207 << 1)
+
static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
{
- unsigned long pcr = 0;
+ unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ /* We can (emulate) our own architecture version and anything older */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ host_pcr_bit = PCR_ARCH_300;
+ else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ host_pcr_bit = PCR_ARCH_207;
+ else if (cpu_has_feature(CPU_FTR_ARCH_206))
+ host_pcr_bit = PCR_ARCH_206;
+ else
+ host_pcr_bit = PCR_ARCH_205;
+
+ /* Determine lowest PCR bit needed to run guest in given PVR level */
+ guest_pcr_bit = host_pcr_bit;
if (arch_compat) {
switch (arch_compat) {
case PVR_ARCH_205:
- /*
- * If an arch bit is set in PCR, all the defined
- * higher-order arch bits also have to be set.
- */
- pcr = PCR_ARCH_206 | PCR_ARCH_205;
+ guest_pcr_bit = PCR_ARCH_205;
break;
case PVR_ARCH_206:
case PVR_ARCH_206p:
- pcr = PCR_ARCH_206;
+ guest_pcr_bit = PCR_ARCH_206;
break;
case PVR_ARCH_207:
+ guest_pcr_bit = PCR_ARCH_207;
+ break;
+ case PVR_ARCH_300:
+ guest_pcr_bit = PCR_ARCH_300;
break;
default:
return -EINVAL;
}
-
- if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
- /* POWER7 can't emulate POWER8 */
- if (!(pcr & PCR_ARCH_206))
- return -EINVAL;
- pcr &= ~PCR_ARCH_206;
- }
}
+ /* Check requested PCR bits don't exceed our capabilities */
+ if (guest_pcr_bit > host_pcr_bit)
+ return -EINVAL;
+
spin_lock(&vc->lock);
vc->arch_compat = arch_compat;
- vc->pcr = pcr;
+ /* Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit */
+ vc->pcr = host_pcr_bit - guest_pcr_bit;
spin_unlock(&vc->lock);
return 0;
--
2.7.4
^ permalink raw reply related [flat|nested] 28+ messages in thread* Re: [PATCH v2 11/11] KVM: PPC: Book3S HV: Update kvmppc_set_arch_compat() for ISA v3.00
2016-11-23 0:32 ` Paul Mackerras
@ 2016-11-23 6:26 ` kbuild test robot
-1 siblings, 0 replies; 28+ messages in thread
From: kbuild test robot @ 2016-11-23 6:26 UTC (permalink / raw)
To: Paul Mackerras; +Cc: kbuild-all, kvm-ppc, kvm, linuxppc-dev
[-- Attachment #1: Type: text/plain, Size: 3346 bytes --]
Hi Suraj,
[auto build test WARNING on next-20161122]
[cannot apply to kvm-ppc/kvm-ppc-next powerpc/next kvm/linux-next v4.9-rc6 v4.9-rc5 v4.9-rc4 v4.9-rc6]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Paul-Mackerras/KVM-PPC-Book3S-HV-Support-KVM-guests-on-POWER9/20161123-124441
config: powerpc-allmodconfig (attached as .config)
compiler: powerpc64-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
wget https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=powerpc
All warnings (new ones prefixed by >>):
arch/powerpc/kvm/book3s_hv.c: In function 'kvmppc_set_arch_compat':
arch/powerpc/kvm/book3s_hv.c:320:23: error: 'PCR_ARCH_207' undeclared (first use in this function)
#define PCR_ARCH_300 (PCR_ARCH_207 << 1)
^
>> arch/powerpc/kvm/book3s_hv.c:329:18: note: in expansion of macro 'PCR_ARCH_300'
host_pcr_bit = PCR_ARCH_300;
^~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c:320:23: note: each undeclared identifier is reported only once for each function it appears in
#define PCR_ARCH_300 (PCR_ARCH_207 << 1)
^
>> arch/powerpc/kvm/book3s_hv.c:329:18: note: in expansion of macro 'PCR_ARCH_300'
host_pcr_bit = PCR_ARCH_300;
^~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c:351:8: error: 'PVR_ARCH_300' undeclared (first use in this function)
case PVR_ARCH_300:
^~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c: In function 'kvmppc_set_one_reg_hv':
arch/powerpc/kvm/book3s_hv.c:1474:46: error: 'PSSCR_GUEST_VIS' undeclared (first use in this function)
vcpu->arch.psscr = set_reg_val(id, *val) & PSSCR_GUEST_VIS;
^~~~~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c: In function 'kvmppc_setup_partition_table':
arch/powerpc/kvm/book3s_hv.c:3113:2: error: implicit declaration of function 'mmu_partition_table_set_entry' [-Werror=implicit-function-declaration]
mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: some warnings being treated as errors
vim +/PCR_ARCH_300 +329 arch/powerpc/kvm/book3s_hv.c
314 static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
315 {
316 vcpu->arch.pvr = pvr;
317 }
318
319 /* Dummy value used in computing PCR value below */
> 320 #define PCR_ARCH_300 (PCR_ARCH_207 << 1)
321
322 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
323 {
324 unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
325 struct kvmppc_vcore *vc = vcpu->arch.vcore;
326
327 /* We can (emulate) our own architecture version and anything older */
328 if (cpu_has_feature(CPU_FTR_ARCH_300))
> 329 host_pcr_bit = PCR_ARCH_300;
330 else if (cpu_has_feature(CPU_FTR_ARCH_207S))
331 host_pcr_bit = PCR_ARCH_207;
332 else if (cpu_has_feature(CPU_FTR_ARCH_206))
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 51512 bytes --]
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v2 11/11] KVM: PPC: Book3S HV: Update kvmppc_set_arch_compat() for ISA v3.00
@ 2016-11-23 6:26 ` kbuild test robot
0 siblings, 0 replies; 28+ messages in thread
From: kbuild test robot @ 2016-11-23 6:26 UTC (permalink / raw)
To: kvm-ppc
[-- Attachment #1: Type: text/plain, Size: 3346 bytes --]
Hi Suraj,
[auto build test WARNING on next-20161122]
[cannot apply to kvm-ppc/kvm-ppc-next powerpc/next kvm/linux-next v4.9-rc6 v4.9-rc5 v4.9-rc4 v4.9-rc6]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Paul-Mackerras/KVM-PPC-Book3S-HV-Support-KVM-guests-on-POWER9/20161123-124441
config: powerpc-allmodconfig (attached as .config)
compiler: powerpc64-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
wget https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=powerpc
All warnings (new ones prefixed by >>):
arch/powerpc/kvm/book3s_hv.c: In function 'kvmppc_set_arch_compat':
arch/powerpc/kvm/book3s_hv.c:320:23: error: 'PCR_ARCH_207' undeclared (first use in this function)
#define PCR_ARCH_300 (PCR_ARCH_207 << 1)
^
>> arch/powerpc/kvm/book3s_hv.c:329:18: note: in expansion of macro 'PCR_ARCH_300'
host_pcr_bit = PCR_ARCH_300;
^~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c:320:23: note: each undeclared identifier is reported only once for each function it appears in
#define PCR_ARCH_300 (PCR_ARCH_207 << 1)
^
>> arch/powerpc/kvm/book3s_hv.c:329:18: note: in expansion of macro 'PCR_ARCH_300'
host_pcr_bit = PCR_ARCH_300;
^~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c:351:8: error: 'PVR_ARCH_300' undeclared (first use in this function)
case PVR_ARCH_300:
^~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c: In function 'kvmppc_set_one_reg_hv':
arch/powerpc/kvm/book3s_hv.c:1474:46: error: 'PSSCR_GUEST_VIS' undeclared (first use in this function)
vcpu->arch.psscr = set_reg_val(id, *val) & PSSCR_GUEST_VIS;
^~~~~~~~~~~~~~~
arch/powerpc/kvm/book3s_hv.c: In function 'kvmppc_setup_partition_table':
arch/powerpc/kvm/book3s_hv.c:3113:2: error: implicit declaration of function 'mmu_partition_table_set_entry' [-Werror=implicit-function-declaration]
mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: some warnings being treated as errors
vim +/PCR_ARCH_300 +329 arch/powerpc/kvm/book3s_hv.c
314 static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
315 {
316 vcpu->arch.pvr = pvr;
317 }
318
319 /* Dummy value used in computing PCR value below */
> 320 #define PCR_ARCH_300 (PCR_ARCH_207 << 1)
321
322 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
323 {
324 unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
325 struct kvmppc_vcore *vc = vcpu->arch.vcore;
326
327 /* We can (emulate) our own architecture version and anything older */
328 if (cpu_has_feature(CPU_FTR_ARCH_300))
> 329 host_pcr_bit = PCR_ARCH_300;
330 else if (cpu_has_feature(CPU_FTR_ARCH_207S))
331 host_pcr_bit = PCR_ARCH_207;
332 else if (cpu_has_feature(CPU_FTR_ARCH_206))
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 51512 bytes --]
^ permalink raw reply [flat|nested] 28+ messages in thread
* Re: [PATCH 00/11] KVM: PPC: Book3S HV: Support KVM guests on POWER9
2016-11-23 0:31 ` Paul Mackerras
@ 2016-11-23 23:03 ` Paul Mackerras
-1 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 23:03 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
On Wed, Nov 23, 2016 at 11:31:54AM +1100, Paul Mackerras wrote:
> This series of patches adds support to HV KVM for running KVM guests
> on POWER9 systems. This allows us to run KVM guests that use HPT
> (hashed page table) address translation and know about the POWER9
> processor. With suitable changes to the user-mode driver, this can
> also run guests on POWER9 in POWER8 or POWER7 compatibility mode.
>
> For now we require the host to be in HPT mode (not radix).
>
> This series of patches is based on the ppc-kvm topic branch from the
> powerpc tree merged with my current kvm-ppc-next tree.
I have pushed the merge plus this series to my kvm-ppc-next branch.
Paul.
^ permalink raw reply [flat|nested] 28+ messages in thread
* Re: [PATCH 00/11] KVM: PPC: Book3S HV: Support KVM guests on POWER9
@ 2016-11-23 23:03 ` Paul Mackerras
0 siblings, 0 replies; 28+ messages in thread
From: Paul Mackerras @ 2016-11-23 23:03 UTC (permalink / raw)
To: kvm-ppc, kvm, linuxppc-dev
On Wed, Nov 23, 2016 at 11:31:54AM +1100, Paul Mackerras wrote:
> This series of patches adds support to HV KVM for running KVM guests
> on POWER9 systems. This allows us to run KVM guests that use HPT
> (hashed page table) address translation and know about the POWER9
> processor. With suitable changes to the user-mode driver, this can
> also run guests on POWER9 in POWER8 or POWER7 compatibility mode.
>
> For now we require the host to be in HPT mode (not radix).
>
> This series of patches is based on the ppc-kvm topic branch from the
> powerpc tree merged with my current kvm-ppc-next tree.
I have pushed the merge plus this series to my kvm-ppc-next branch.
Paul.
^ permalink raw reply [flat|nested] 28+ messages in thread