aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kvm')
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c10
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c32
-rw-r--r--arch/powerpc/kvm/book3s_64_vio.c57
-rw-r--r--arch/powerpc/kvm/book3s_64_vio_hv.c12
-rw-r--r--arch/powerpc/kvm/book3s_hv.c35
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_mmu.c20
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_xive.c1
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S90
-rw-r--r--arch/powerpc/kvm/book3s_xive.c1
-rw-r--r--arch/powerpc/kvm/book3s_xive_template.c73
-rw-r--r--arch/powerpc/kvm/e500.c8
-rw-r--r--arch/powerpc/kvm/e500_mmu_host.c3
-rw-r--r--arch/powerpc/kvm/e500mc.c4
-rw-r--r--arch/powerpc/kvm/powerpc.c5
14 files changed, 274 insertions, 77 deletions
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 8cb0190e2a73..7c62967d672c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,6 +37,7 @@
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/cputable.h>
+#include <asm/pte-walk.h>
#include "trace_hv.h"
@@ -164,8 +165,10 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
goto out;
}
- if (kvm->arch.hpt.virt)
+ if (kvm->arch.hpt.virt) {
kvmppc_free_hpt(&kvm->arch.hpt);
+ kvmppc_rmap_reset(kvm);
+ }
err = kvmppc_allocate_hpt(&info, order);
if (err < 0)
@@ -597,8 +600,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
* hugepage split and collapse.
*/
local_irq_save(flags);
- ptep = find_linux_pte_or_hugepte(current->mm->pgd,
- hva, NULL, NULL);
+ ptep = find_current_mm_pte(current->mm->pgd,
+ hva, NULL, NULL);
if (ptep) {
pte = kvmppc_read_update_linux_pte(ptep, 1);
if (__pte_write(pte))
@@ -1938,6 +1941,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
if (ret < 0) {
+ kfree(ctx);
kvm_put_kvm(kvm);
return ret;
}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index f6b3e67c5762..c5d7435455f1 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -17,6 +17,7 @@
#include <asm/mmu.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
/*
* Supported radix tree geometry.
@@ -322,13 +323,13 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
gpa = vcpu->arch.fault_gpa & ~0xfffUL;
gpa &= ~0xF000000000000000ul;
gfn = gpa >> PAGE_SHIFT;
- if (!(dsisr & DSISR_PGDIRFAULT))
+ if (!(dsisr & DSISR_PRTABLE_FAULT))
gpa |= ea & 0xfff;
memslot = gfn_to_memslot(kvm, gfn);
/* No memslot means it's an emulated MMIO region */
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
- if (dsisr & (DSISR_PGDIRFAULT | DSISR_BADACCESS |
+ if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
DSISR_SET_RC)) {
/*
* Bad address in guest page table tree, or other
@@ -359,8 +360,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
if (writing)
pgflags |= _PAGE_DIRTY;
local_irq_save(flags);
- ptep = __find_linux_pte_or_hugepte(current->mm->pgd, hva,
- NULL, NULL);
+ ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL);
if (ptep) {
pte = READ_ONCE(*ptep);
if (pte_present(pte) &&
@@ -374,8 +374,12 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
spin_unlock(&kvm->mmu_lock);
return RESUME_GUEST;
}
- ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable,
- gpa, NULL, &shift);
+ /*
+ * We are walking the secondary page table here. We can do this
+ * without disabling irq.
+ */
+ ptep = __find_linux_pte(kvm->arch.pgtable,
+ gpa, NULL, &shift);
if (ptep && pte_present(*ptep)) {
kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
gpa, shift);
@@ -427,8 +431,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
pgflags |= _PAGE_WRITE;
} else {
local_irq_save(flags);
- ptep = __find_linux_pte_or_hugepte(current->mm->pgd,
- hva, NULL, NULL);
+ ptep = find_current_mm_pte(current->mm->pgd,
+ hva, NULL, NULL);
if (ptep && pte_write(*ptep) && pte_dirty(*ptep))
pgflags |= _PAGE_WRITE;
local_irq_restore(flags);
@@ -499,8 +503,7 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned int shift;
unsigned long old;
- ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
- NULL, &shift);
+ ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep)) {
old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0,
gpa, shift);
@@ -525,8 +528,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned int shift;
int ref = 0;
- ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
- NULL, &shift);
+ ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
gpa, shift);
@@ -545,8 +547,7 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned int shift;
int ref = 0;
- ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
- NULL, &shift);
+ ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep))
ref = 1;
return ref;
@@ -562,8 +563,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
unsigned int shift;
int ret = 0;
- ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
- NULL, &shift);
+ ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
ret = 1;
if (shift)
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index a160c14304eb..8f2da8bba737 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -265,8 +265,11 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
{
struct kvmppc_spapr_tce_table *stt = filp->private_data;
struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+ struct kvm *kvm = stt->kvm;
+ mutex_lock(&kvm->lock);
list_del_rcu(&stt->list);
+ mutex_unlock(&kvm->lock);
list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
WARN_ON(!kref_read(&stit->kref));
@@ -294,6 +297,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args)
{
struct kvmppc_spapr_tce_table *stt = NULL;
+ struct kvmppc_spapr_tce_table *siter;
unsigned long npages, size;
int ret = -ENOMEM;
int i;
@@ -301,25 +305,17 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
if (!args->size)
return -EINVAL;
- /* Check this LIOBN hasn't been previously allocated */
- list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
- if (stt->liobn == args->liobn)
- return -EBUSY;
- }
-
size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
npages = kvmppc_tce_pages(size);
ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
- if (ret) {
- stt = NULL;
- goto fail;
- }
+ if (ret)
+ return ret;
ret = -ENOMEM;
stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
GFP_KERNEL);
if (!stt)
- goto fail;
+ goto fail_acct;
stt->liobn = args->liobn;
stt->page_shift = args->page_shift;
@@ -334,24 +330,39 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
goto fail;
}
- kvm_get_kvm(kvm);
-
mutex_lock(&kvm->lock);
- list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+
+ /* Check this LIOBN hasn't been previously allocated */
+ ret = 0;
+ list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
+ if (siter->liobn == args->liobn) {
+ ret = -EBUSY;
+ break;
+ }
+ }
+
+ if (!ret)
+ ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+ stt, O_RDWR | O_CLOEXEC);
+
+ if (ret >= 0) {
+ list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+ kvm_get_kvm(kvm);
+ }
mutex_unlock(&kvm->lock);
- return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
- stt, O_RDWR | O_CLOEXEC);
+ if (ret >= 0)
+ return ret;
-fail:
- if (stt) {
- for (i = 0; i < npages; i++)
- if (stt->pages[i])
- __free_page(stt->pages[i]);
+ fail:
+ for (i = 0; i < npages; i++)
+ if (stt->pages[i])
+ __free_page(stt->pages[i]);
- kfree(stt);
- }
+ kfree(stt);
+ fail_acct:
+ kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
return ret;
}
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 3adfd2f5301c..c32e9bfe75b1 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -39,6 +39,7 @@
#include <asm/udbg.h>
#include <asm/iommu.h>
#include <asm/tce.h>
+#include <asm/pte-walk.h>
#ifdef CONFIG_BUG
@@ -353,7 +354,16 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
pte_t *ptep, pte;
unsigned shift = 0;
- ptep = __find_linux_pte_or_hugepte(vcpu->arch.pgdir, ua, NULL, &shift);
+ /*
+ * Called in real mode with MSR_EE = 0. We are safe here.
+ * It is ok to do the lookup with arch.pgdir here, because
+ * we are doing this on secondary cpus and current task there
+ * is not the hypervisor. Also this is safe against THP in the
+ * host, because an IPI to primary thread will wait for the secondary
+ * to exit which will agains result in the below page table walk
+ * to finish.
+ */
+ ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift);
if (!ptep || !pte_present(*ptep))
return -ENXIO;
pte = *ptep;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0b436df746fc..73bf1ebfa78f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -181,7 +181,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
struct swait_queue_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
- if (swait_active(wqp)) {
+ if (swq_has_sleeper(wqp)) {
swake_up(wqp);
++vcpu->stat.halt_wakeup;
}
@@ -485,7 +485,13 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
switch (subfunc) {
case H_VPA_REG_VPA: /* register VPA */
- if (len < sizeof(struct lppaca))
+ /*
+ * The size of our lppaca is 1kB because of the way we align
+ * it for the guest to avoid crossing a 4kB boundary. We only
+ * use 640 bytes of the structure though, so we should accept
+ * clients that set a size of 640.
+ */
+ if (len < 640)
break;
vpap = &tvcpu->arch.vpa;
err = 0;
@@ -2111,6 +2117,15 @@ static int kvmppc_grab_hwthread(int cpu)
struct paca_struct *tpaca;
long timeout = 10000;
+ /*
+ * ISA v3.0 idle routines do not set hwthread_state or test
+ * hwthread_req, so they can not grab idle threads.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ WARN(1, "KVM: can not control sibling threads\n");
+ return -EBUSY;
+ }
+
tpaca = &paca[cpu];
/* Ensure the thread won't go into the kernel if it wakes */
@@ -2145,10 +2160,12 @@ static void kvmppc_release_hwthread(int cpu)
struct paca_struct *tpaca;
tpaca = &paca[cpu];
- tpaca->kvm_hstate.hwthread_req = 0;
tpaca->kvm_hstate.kvm_vcpu = NULL;
tpaca->kvm_hstate.kvm_vcore = NULL;
tpaca->kvm_hstate.kvm_split_mode = NULL;
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ tpaca->kvm_hstate.hwthread_req = 0;
+
}
static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
@@ -3211,6 +3228,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
run->fail_entry.hardware_entry_failure_reason = 0;
return -EINVAL;
}
+ /* Enable TM so we can read the TM SPRs */
+ mtmsr(mfmsr() | MSR_TM);
current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
current->thread.tm_texasr = mfspr(SPRN_TEXASR);
@@ -3323,6 +3342,14 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
if (radix_enabled())
return -EINVAL;
+ /*
+ * POWER7, POWER8 and POWER9 all support 32 storage keys for data.
+ * POWER7 doesn't support keys for instruction accesses,
+ * POWER8 and POWER9 do.
+ */
+ info->data_keys = 32;
+ info->instr_keys = cpu_has_feature(CPU_FTR_ARCH_207S) ? 32 : 0;
+
info->flags = KVM_PPC_PAGE_SIZES_REAL;
if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
info->flags |= KVM_PPC_1T_SEGMENTS;
@@ -4185,11 +4212,13 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
if ((cfg->process_table & PRTS_MASK) > 24)
return -EINVAL;
+ mutex_lock(&kvm->lock);
kvm->arch.process_table = cfg->process_table;
kvmppc_setup_partition_table(kvm);
lpcr = (cfg->flags & KVM_PPC_MMUV3_GTSE) ? LPCR_GTSE : 0;
kvmppc_update_lpcr(kvm, lpcr, LPCR_GTSE);
+ mutex_unlock(&kvm->lock);
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 584c74c8119f..4efe364f1188 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -22,6 +22,7 @@
#include <asm/hvcall.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
+#include <asm/pte-walk.h>
/* Translate address of a vmalloc'd thing to a linear map address */
static void *real_vmalloc_addr(void *x)
@@ -31,9 +32,9 @@ static void *real_vmalloc_addr(void *x)
/*
* assume we don't have huge pages in vmalloc space...
* So don't worry about THP collapse/split. Called
- * Only in realmode, hence won't need irq_save/restore.
+ * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore.
*/
- p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL, NULL);
+ p = find_init_mm_pte(addr, NULL);
if (!p || !pte_present(*p))
return NULL;
addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
@@ -230,14 +231,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
* If we had a page table table change after lookup, we would
* retry via mmu_notifier_retry.
*/
- if (realmode)
- ptep = __find_linux_pte_or_hugepte(pgdir, hva, NULL,
- &hpage_shift);
- else {
+ if (!realmode)
local_irq_save(irq_flags);
- ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL,
- &hpage_shift);
- }
+ /*
+ * If called in real mode we have MSR_EE = 0. Otherwise
+ * we disable irq above.
+ */
+ ptep = __find_linux_pte(pgdir, hva, NULL, &hpage_shift);
if (ptep) {
pte_t pte;
unsigned int host_pte_size;
@@ -269,7 +269,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
if (!realmode)
local_irq_restore(irq_flags);
- ptel &= ~(HPTE_R_PP0 - psize);
+ ptel &= HPTE_R_KEY | HPTE_R_PP0 | (psize-1);
ptel |= pa;
if (pa)
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xive.c b/arch/powerpc/kvm/book3s_hv_rm_xive.c
index abf5f01b6eb1..5b81a807d742 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xive.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xive.c
@@ -38,7 +38,6 @@ static inline void __iomem *get_tima_phys(void)
#define __x_tima get_tima_phys()
#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_page))
#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_page))
-#define __x_readb __raw_rm_readb
#define __x_writeb __raw_rm_writeb
#define __x_readw __raw_rm_readw
#define __x_readq __raw_rm_readq
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index cb44065e2946..17936f82d3c7 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -149,9 +149,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
subf r4, r4, r3
mtspr SPRN_DEC, r4
+BEGIN_FTR_SECTION
/* hwthread_req may have got set by cede or no vcpu, so clear it */
li r0, 0
stb r0, HSTATE_HWTHREAD_REQ(r13)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
/*
* For external interrupts we need to call the Linux
@@ -314,6 +316,7 @@ kvm_novcpu_exit:
* Relocation is off and most register values are lost.
* r13 points to the PACA.
* r3 contains the SRR1 wakeup value, SRR1 is trashed.
+ * This is not used by ISAv3.0B processors.
*/
.globl kvm_start_guest
kvm_start_guest:
@@ -432,6 +435,9 @@ kvm_secondary_got_guest:
* While waiting we also need to check if we get given a vcpu to run.
*/
kvm_no_guest:
+BEGIN_FTR_SECTION
+ twi 31,0,0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
lbz r3, HSTATE_HWTHREAD_REQ(r13)
cmpwi r3, 0
bne 53f
@@ -765,6 +771,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
+ /*
+ * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+ */
bl kvmppc_restore_tm
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
@@ -976,7 +985,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
#ifdef CONFIG_KVM_XICS
/* We are entering the guest on that thread, push VCPU to XIVE */
ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
- cmpldi cr0, r10, r0
+ cmpldi cr0, r10, 0
beq no_xive
ld r11, VCPU_XIVE_SAVED_STATE(r4)
li r9, TM_QW1_OS
@@ -1280,7 +1289,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
bne 2f
mfspr r3,SPRN_HDEC
- cmpwi r3,0
+ EXTEND_HDEC(r3)
+ cmpdi r3,0
mr r4,r9
bge fast_guest_return
2:
@@ -1291,6 +1301,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* Hypervisor doorbell - exit only if host IPI flag set */
cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL
bne 3f
+BEGIN_FTR_SECTION
+ PPC_MSGSYNC
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
lbz r0, HSTATE_HOST_IPI(r13)
cmpwi r0, 0
beq 4f
@@ -1443,12 +1456,14 @@ mc_cont:
ori r6,r6,1
mtspr SPRN_CTRLT,r6
4:
- /* Read the guest SLB and save it away */
+ /* Check if we are running hash or radix and store it in cr2 */
ld r5, VCPU_KVM(r9)
lbz r0, KVM_RADIX(r5)
- cmpwi r0, 0
+ cmpwi cr2,r0,0
+
+ /* Read the guest SLB and save it away */
li r5, 0
- bne 3f /* for radix, save 0 entries */
+ bne cr2, 3f /* for radix, save 0 entries */
lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */
mtctr r0
li r6,0
@@ -1618,6 +1633,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
+ /*
+ * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+ */
bl kvmppc_save_tm
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
@@ -1712,11 +1730,6 @@ BEGIN_FTR_SECTION_NESTED(96)
END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
22:
- /* Clear out SLB */
- li r5,0
- slbmte r5,r5
- slbia
- ptesync
/* Restore host values of some registers */
BEGIN_FTR_SECTION
@@ -1737,10 +1750,59 @@ BEGIN_FTR_SECTION
mtspr SPRN_PID, r7
mtspr SPRN_IAMR, r8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+#ifdef CONFIG_PPC_RADIX_MMU
+ /*
+ * Are we running hash or radix ?
+ */
+ ld r5, VCPU_KVM(r9)
+ lbz r0, KVM_RADIX(r5)
+ cmpwi cr2, r0, 0
+ beq cr2, 3f
+
+ /* Radix: Handle the case where the guest used an illegal PID */
+ LOAD_REG_ADDR(r4, mmu_base_pid)
+ lwz r3, VCPU_GUEST_PID(r9)
+ lwz r5, 0(r4)
+ cmpw cr0,r3,r5
+ blt 2f
+
+ /*
+ * Illegal PID, the HW might have prefetched and cached in the TLB
+ * some translations for the LPID 0 / guest PID combination which
+ * Linux doesn't know about, so we need to flush that PID out of
+ * the TLB. First we need to set LPIDR to 0 so tlbiel applies to
+ * the right context.
+ */
+ li r0,0
+ mtspr SPRN_LPID,r0
+ isync
+
+ /* Then do a congruence class local flush */
+ ld r6,VCPU_KVM(r9)
+ lwz r0,KVM_TLB_SETS(r6)
+ mtctr r0
+ li r7,0x400 /* IS field = 0b01 */
+ ptesync
+ sldi r0,r3,32 /* RS has PID */
+1: PPC_TLBIEL(7,0,2,1,1) /* RIC=2, PRS=1, R=1 */
+ addi r7,r7,0x1000
+ bdnz 1b
+ ptesync
+
+2: /* Flush the ERAT on radix P9 DD1 guest exit */
BEGIN_FTR_SECTION
PPC_INVALIDATE_ERAT
END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
+ b 4f
+#endif /* CONFIG_PPC_RADIX_MMU */
+ /* Hash: clear out SLB */
+3: li r5,0
+ slbmte r5,r5
+ slbia
+ ptesync
+4:
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
@@ -2413,6 +2475,9 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
+ /*
+ * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+ */
ld r9, HSTATE_KVM_VCPU(r13)
bl kvmppc_save_tm
END_FTR_SECTION_IFSET(CPU_FTR_TM)
@@ -2466,8 +2531,10 @@ kvm_do_nap:
clrrdi r0, r0, 1
mtspr SPRN_CTRLT, r0
+BEGIN_FTR_SECTION
li r0,1
stb r0,HSTATE_HWTHREAD_REQ(r13)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
mfspr r5,SPRN_LPCR
ori r5,r5,LPCR_PECE0 | LPCR_PECE1
BEGIN_FTR_SECTION
@@ -2523,6 +2590,9 @@ kvm_end_cede:
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
+ /*
+ * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+ */
bl kvmppc_restore_tm
END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 08b200a0bbce..13304622ab1c 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -48,7 +48,6 @@
#define __x_tima xive_tima
#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_mmio))
#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_mmio))
-#define __x_readb __raw_readb
#define __x_writeb __raw_writeb
#define __x_readw __raw_readw
#define __x_readq __raw_readq
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index 4636ca6e7d38..c7a5deadd1cc 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -16,7 +16,23 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
u8 cppr;
u16 ack;
- /* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */
+ /*
+ * Ensure any previous store to CPPR is ordered vs.
+ * the subsequent loads from PIPR or ACK.
+ */
+ eieio();
+
+ /*
+ * DD1 bug workaround: If PIPR is less favored than CPPR
+ * ignore the interrupt or we might incorrectly lose an IPB
+ * bit.
+ */
+ if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
+ __be64 qw1 = __x_readq(__x_tima + TM_QW1_OS);
+ u8 pipr = be64_to_cpu(qw1) & 0xff;
+ if (pipr >= xc->hw_cppr)
+ return;
+ }
/* Perform the acknowledge OS to register cycle. */
ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
@@ -235,6 +251,11 @@ skip_ipi:
/*
* If we found an interrupt, adjust what the guest CPPR should
* be as if we had just fetched that interrupt from HW.
+ *
+ * Note: This can only make xc->cppr smaller as the previous
+ * loop will only exit with hirq != 0 if prio is lower than
+ * the current xc->cppr. Thus we don't need to re-check xc->mfrr
+ * for pending IPIs.
*/
if (hirq)
xc->cppr = prio;
@@ -316,7 +337,6 @@ X_STATIC unsigned long GLUE(X_PFX,h_ipoll)(struct kvm_vcpu *vcpu, unsigned long
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
u8 pending = xc->pending;
u32 hirq;
- u8 pipr;
pr_devel("H_IPOLL(server=%ld)\n", server);
@@ -333,7 +353,8 @@ X_STATIC unsigned long GLUE(X_PFX,h_ipoll)(struct kvm_vcpu *vcpu, unsigned long
pending = 0xff;
} else {
/* Grab pending interrupt if any */
- pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR);
+ __be64 qw1 = __x_readq(__x_tima + TM_QW1_OS);
+ u8 pipr = be64_to_cpu(qw1) & 0xff;
if (pipr < 8)
pending |= 1 << pipr;
}
@@ -381,6 +402,12 @@ X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
xc->cppr = cppr;
/*
+ * Order the above update of xc->cppr with the subsequent
+ * read of xc->mfrr inside push_pending_to_hw()
+ */
+ smp_mb();
+
+ /*
* We are masking less, we need to look for pending things
* to deliver and set VP pending bits accordingly to trigger
* a new interrupt otherwise we might miss MFRR changes for
@@ -420,21 +447,37 @@ X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr)
* used to signal MFRR changes is EOId when fetched from
* the queue.
*/
- if (irq == XICS_IPI || irq == 0)
+ if (irq == XICS_IPI || irq == 0) {
+ /*
+ * This barrier orders the setting of xc->cppr vs.
+ * subsquent test of xc->mfrr done inside
+ * scan_interrupts and push_pending_to_hw
+ */
+ smp_mb();
goto bail;
+ }
/* Find interrupt source */
sb = kvmppc_xive_find_source(xive, irq, &src);
if (!sb) {
pr_devel(" source not found !\n");
rc = H_PARAMETER;
+ /* Same as above */
+ smp_mb();
goto bail;
}
state = &sb->irq_state[src];
kvmppc_xive_select_irq(state, &hw_num, &xd);
state->in_eoi = true;
- mb();
+
+ /*
+ * This barrier orders both setting of in_eoi above vs,
+ * subsequent test of guest_priority, and the setting
+ * of xc->cppr vs. subsquent test of xc->mfrr done inside
+ * scan_interrupts and push_pending_to_hw
+ */
+ smp_mb();
again:
if (state->guest_priority == MASKED) {
@@ -461,6 +504,14 @@ again:
}
+ /*
+ * This barrier orders the above guest_priority check
+ * and spin_lock/unlock with clearing in_eoi below.
+ *
+ * It also has to be a full mb() as it must ensure
+ * the MMIOs done in source_eoi() are completed before
+ * state->in_eoi is visible.
+ */
mb();
state->in_eoi = false;
bail:
@@ -495,6 +546,18 @@ X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
/* Locklessly write over MFRR */
xc->mfrr = mfrr;
+ /*
+ * The load of xc->cppr below and the subsequent MMIO store
+ * to the IPI must happen after the above mfrr update is
+ * globally visible so that:
+ *
+ * - Synchronize with another CPU doing an H_EOI or a H_CPPR
+ * updating xc->cppr then reading xc->mfrr.
+ *
+ * - The target of the IPI sees the xc->mfrr update
+ */
+ mb();
+
/* Shoot the IPI if most favored than target cppr */
if (mfrr < xc->cppr)
__x_writeq(0, __x_trig_page(&xc->vp_ipi_data));
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 32fdab57d604..f9f6468f4171 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -455,16 +455,20 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
if (err)
goto free_vcpu;
- if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+ if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL) {
+ err = -ENOMEM;
goto uninit_vcpu;
+ }
err = kvmppc_e500_tlb_init(vcpu_e500);
if (err)
goto uninit_id;
vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
- if (!vcpu->arch.shared)
+ if (!vcpu->arch.shared) {
+ err = -ENOMEM;
goto uninit_tlb;
+ }
return vcpu;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 77fd043b3ecc..c6c734424c70 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -30,6 +30,7 @@
#include <linux/vmalloc.h>
#include <linux/hugetlb.h>
#include <asm/kvm_ppc.h>
+#include <asm/pte-walk.h>
#include "e500.h"
#include "timing.h"
@@ -476,7 +477,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
* can't run hence pfn won't change.
*/
local_irq_save(flags);
- ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL, NULL);
+ ptep = find_linux_pte(pgdir, hva, NULL, NULL);
if (ptep) {
pte_t pte = READ_ONCE(*ptep);
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index f48a0c22e8f9..d0b6b5788afc 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -331,8 +331,10 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
goto uninit_vcpu;
vcpu->arch.shared = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
- if (!vcpu->arch.shared)
+ if (!vcpu->arch.shared) {
+ err = -ENOMEM;
goto uninit_tlb;
+ }
return vcpu;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1a75c0b5f4ca..3480faaf1ef8 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -58,6 +58,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
}
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return 1;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.