system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-11-05 18:23:50 +00:00
Code Issues Projects Releases Packages Wiki Activity

KVM: PPC: Book3S HV: Remove code for PPC970 processors

Browse source 
This removes the code that was added to enable HV KVM to work
on PPC970 processors.  The PPC970 is an old CPU that doesn't
support virtualizing guest memory.  Removing PPC970 support also
lets us remove the code for allocating and managing contiguous
real-mode areas, the code for the !kvm->arch.using_mmu_notifiers
case, the code for pinning pages of guest memory when first
accessed and keeping track of which pages have been pinned, and
the code for handling H_ENTER hypercalls in virtual mode.

Book3S HV KVM is now supported only on POWER7 and POWER8 processors.
The KVM_CAP_PPC_RMA capability now always returns 0.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This commit is contained in:
Paul Mackerras 2014-12-03 13:30:38 +11:00 committed by Alexander Graf
parent 3c78f78af9
commit c17b98cf60
13 changed files with 70 additions and 955 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
arch/powerpc/include/asm/kvm_book3s.h
View file

@ -170,8 +170,6 @@ extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr,
unsigned long *nb_ret);
extern void kvmppc_unpin_guest_page(struct kvm *kvm, void *addr,
unsigned long gpa, bool dirty);
extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
long pte_index, unsigned long pteh, unsigned long ptel);
extern long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
long pte_index, unsigned long pteh, unsigned long ptel,
pgd_t *pgdir, bool realmode, unsigned long *idx_ret);

1
arch/powerpc/include/asm/kvm_book3s_64.h
View file

@ -37,7 +37,6 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
#define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */
extern unsigned long kvm_rma_pages;
#endif
#define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */

14
arch/powerpc/include/asm/kvm_host.h
View file

@ -180,11 +180,6 @@ struct kvmppc_spapr_tce_table {
struct page *pages[0];
};
struct kvm_rma_info {
atomic_t use_count;
unsigned long base_pfn;
};
/* XICS components, defined in book3s_xics.c */
struct kvmppc_xics;
struct kvmppc_icp;
@ -214,16 +209,9 @@ struct revmap_entry {
#define KVMPPC_RMAP_PRESENT 0x100000000ul
#define KVMPPC_RMAP_INDEX 0xfffffffful
/* Low-order bits in memslot->arch.slot_phys[] */
#define KVMPPC_PAGE_ORDER_MASK 0x1f
#define KVMPPC_PAGE_NO_CACHE HPTE_R_I /* 0x20 */
#define KVMPPC_PAGE_WRITETHRU HPTE_R_W /* 0x40 */
#define KVMPPC_GOT_PAGE 0x80
struct kvm_arch_memory_slot {
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
unsigned long *rmap;
unsigned long *slot_phys;
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
};
@ -242,14 +230,12 @@ struct kvm_arch {
struct kvm_rma_info *rma;
unsigned long vrma_slb_v;
int rma_setup_done;
int using_mmu_notifiers;
u32 hpt_order;
atomic_t vcpus_running;
u32 online_vcores;
unsigned long hpt_npte;
unsigned long hpt_mask;
atomic_t hpte_mod_interest;
spinlock_t slot_phys_lock;
cpumask_t need_tlb_flush;
int hpt_cma_alloc;
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */

2
arch/powerpc/include/asm/kvm_ppc.h
View file

@ -170,8 +170,6 @@ extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba, unsigned long tce);
extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba);
extern struct kvm_rma_info *kvm_alloc_rma(void);
extern void kvm_release_rma(struct kvm_rma_info *ri);
extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
extern void kvm_release_hpt(struct page *page, unsigned long nr_pages);
extern int kvmppc_core_init_vm(struct kvm *kvm);

1
arch/powerpc/kernel/asm-offsets.c
View file

@ -489,7 +489,6 @@ int main(void)
DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));

200
arch/powerpc/kvm/book3s_64_mmu_hv.c
View file

@ -39,9 +39,6 @@
#include "trace_hv.h"
/* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
#define MAX_LPID_970 63
/* Power architecture requires HPT is at least 256kB */
#define PPC_MIN_HPT_ORDER 18
@ -231,14 +228,9 @@ int kvmppc_mmu_hv_init(void)
if (!cpu_has_feature(CPU_FTR_HVMODE))
return -EINVAL;
/* POWER7 has 10-bit LPIDs, PPC970 and e500mc have 6-bit LPIDs */
if (cpu_has_feature(CPU_FTR_ARCH_206)) {
host_lpid = mfspr(SPRN_LPID); /* POWER7 */
rsvd_lpid = LPID_RSVD;
} else {
host_lpid = 0; /* PPC970 */
rsvd_lpid = MAX_LPID_970;
}
/* POWER7 has 10-bit LPIDs (12-bit in POWER8) */
host_lpid = mfspr(SPRN_LPID);
rsvd_lpid = LPID_RSVD;
kvmppc_init_lpid(rsvd_lpid + 1);
@ -261,130 +253,12 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
kvmppc_set_msr(vcpu, msr);
}
/*
* This is called to get a reference to a guest page if there isn't
* one already in the memslot->arch.slot_phys[] array.
*/
static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
struct kvm_memory_slot *memslot,
unsigned long psize)
{
unsigned long start;
long np, err;
struct page *page, *hpage, *pages[1];
unsigned long s, pgsize;
unsigned long *physp;
unsigned int is_io, got, pgorder;
struct vm_area_struct *vma;
unsigned long pfn, i, npages;
physp = memslot->arch.slot_phys;
if (!physp)
return -EINVAL;
if (physp[gfn - memslot->base_gfn])
return 0;
is_io = 0;
got = 0;
page = NULL;
pgsize = psize;
err = -EINVAL;
start = gfn_to_hva_memslot(memslot, gfn);
/* Instantiate and get the page we want access to */
np = get_user_pages_fast(start, 1, 1, pages);
if (np != 1) {
/* Look up the vma for the page */
down_read(&current->mm->mmap_sem);
vma = find_vma(current->mm, start);
if (!vma || vma->vm_start > start ||
start + psize > vma->vm_end ||
!(vma->vm_flags & VM_PFNMAP))
goto up_err;
is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
pfn = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
/* check alignment of pfn vs. requested page size */
if (psize > PAGE_SIZE && (pfn & ((psize >> PAGE_SHIFT) - 1)))
goto up_err;
up_read(&current->mm->mmap_sem);
} else {
page = pages[0];
got = KVMPPC_GOT_PAGE;
/* See if this is a large page */
s = PAGE_SIZE;
if (PageHuge(page)) {
hpage = compound_head(page);
s <<= compound_order(hpage);
/* Get the whole large page if slot alignment is ok */
if (s > psize && slot_is_aligned(memslot, s) &&
!(memslot->userspace_addr & (s - 1))) {
start &= ~(s - 1);
pgsize = s;
get_page(hpage);
put_page(page);
page = hpage;
}
}
if (s < psize)
goto out;
pfn = page_to_pfn(page);
}
npages = pgsize >> PAGE_SHIFT;
pgorder = __ilog2(npages);
physp += (gfn - memslot->base_gfn) & ~(npages - 1);
spin_lock(&kvm->arch.slot_phys_lock);
for (i = 0; i < npages; ++i) {
if (!physp[i]) {
physp[i] = ((pfn + i) << PAGE_SHIFT) +
got + is_io + pgorder;
got = 0;
}
}
spin_unlock(&kvm->arch.slot_phys_lock);
err = 0;
out:
if (got)
put_page(page);
return err;
up_err:
up_read(&current->mm->mmap_sem);
return err;
}
long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
long pte_index, unsigned long pteh,
unsigned long ptel, unsigned long *pte_idx_ret)
{
unsigned long psize, gpa, gfn;
struct kvm_memory_slot *memslot;
long ret;
if (kvm->arch.using_mmu_notifiers)
goto do_insert;
psize = hpte_page_size(pteh, ptel);
if (!psize)
return H_PARAMETER;
pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
/* Find the memslot (if any) for this address */
gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
gfn = gpa >> PAGE_SHIFT;
memslot = gfn_to_memslot(kvm, gfn);
if (memslot && !(memslot->flags & KVM_MEMSLOT_INVALID)) {
if (!slot_is_aligned(memslot, psize))
return H_PARAMETER;
if (kvmppc_get_guest_page(kvm, gfn, memslot, psize) < 0)
return H_PARAMETER;
}
do_insert:
/* Protect linux PTE lookup from page table destruction */
rcu_read_lock_sched(); /* this disables preemption too */
ret = kvmppc_do_h_enter(kvm, flags, pte_index, pteh, ptel,
@ -399,19 +273,6 @@ long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
}
/*
* We come here on a H_ENTER call from the guest when we are not
* using mmu notifiers and we don't have the requested page pinned
* already.
*/
long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
long pte_index, unsigned long pteh,
unsigned long ptel)
{
return kvmppc_virtmode_do_h_enter(vcpu->kvm, flags, pte_index,
pteh, ptel, &vcpu->arch.gpr[4]);
}
static struct kvmppc_slb *kvmppc_mmu_book3s_hv_find_slbe(struct kvm_vcpu *vcpu,
gva_t eaddr)
{
@ -496,7 +357,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
gpte->may_execute = gpte->may_read && !(gr & (HPTE_R_N | HPTE_R_G));
/* Storage key permission check for POWER7 */
if (data && virtmode && cpu_has_feature(CPU_FTR_ARCH_206)) {
if (data && virtmode) {
int amrfield = hpte_get_skey_perm(gr, vcpu->arch.amr);
if (amrfield & 1)
gpte->may_read = 0;
@ -631,9 +492,6 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
dsisr & DSISR_ISSTORE);
if (!kvm->arch.using_mmu_notifiers)
return -EFAULT; /* should never get here */
/*
* This should never happen, because of the slot_is_aligned()
* check in kvmppc_do_h_enter().
@ -902,8 +760,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel);
if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) &&
hpte_rpn(ptel, psize) == gfn) {
if (kvm->arch.using_mmu_notifiers)
hptep[0] |= cpu_to_be64(HPTE_V_ABSENT);
hptep[0] |= cpu_to_be64(HPTE_V_ABSENT);
kvmppc_invalidate_hpte(kvm, hptep, i);
/* Harvest R and C */
rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C);
@ -921,15 +778,13 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva)
{
if (kvm->arch.using_mmu_notifiers)
kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
return 0;
}
int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end)
{
if (kvm->arch.using_mmu_notifiers)
kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp);
kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp);
return 0;
}
@ -1011,8 +866,6 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, unsigned long end)
{
if (!kvm->arch.using_mmu_notifiers)
return 0;
return kvm_handle_hva_range(kvm, start, end, kvm_age_rmapp);
}
@ -1049,15 +902,11 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva)
{
if (!kvm->arch.using_mmu_notifiers)
return 0;
return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp);
}
void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte)
{
if (!kvm->arch.using_mmu_notifiers)
return;
kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
}
@ -1216,35 +1065,17 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
struct page *page, *pages[1];
int npages;
unsigned long hva, offset;
unsigned long pa;
unsigned long *physp;
int srcu_idx;
srcu_idx = srcu_read_lock(&kvm->srcu);
memslot = gfn_to_memslot(kvm, gfn);
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
goto err;
if (!kvm->arch.using_mmu_notifiers) {
physp = memslot->arch.slot_phys;
if (!physp)
goto err;
physp += gfn - memslot->base_gfn;
pa = *physp;
if (!pa) {
if (kvmppc_get_guest_page(kvm, gfn, memslot,
PAGE_SIZE) < 0)
goto err;
pa = *physp;
}
page = pfn_to_page(pa >> PAGE_SHIFT);
get_page(page);
} else {
hva = gfn_to_hva_memslot(memslot, gfn);
npages = get_user_pages_fast(hva, 1, 1, pages);
if (npages < 1)
goto err;
page = pages[0];
}
hva = gfn_to_hva_memslot(memslot, gfn);
npages = get_user_pages_fast(hva, 1, 1, pages);
if (npages < 1)
goto err;
page = pages[0];
srcu_read_unlock(&kvm->srcu, srcu_idx);
offset = gpa & (PAGE_SIZE - 1);
@ -1268,7 +1099,7 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa,
put_page(page);
if (!dirty || !kvm->arch.using_mmu_notifiers)
if (!dirty)
return;
/* We need to mark this page dirty in the rmap chain */
@ -1668,10 +1499,7 @@ void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
{
struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
if (cpu_has_feature(CPU_FTR_ARCH_206))
vcpu->arch.slb_nr = 32; /* POWER7 */
else
vcpu->arch.slb_nr = 64;
vcpu->arch.slb_nr = 32; /* POWER7/POWER8 */
mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate;
mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr;

292
arch/powerpc/kvm/book3s_hv.c
View file

@ -205,9 +205,6 @@ int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
struct kvmppc_vcore *vc = vcpu->arch.vcore;
if (arch_compat) {
if (!cpu_has_feature(CPU_FTR_ARCH_206))
return -EINVAL; /* 970 has no compat mode support */
switch (arch_compat) {
case PVR_ARCH_205:
/*
@ -622,14 +619,6 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
return RESUME_HOST;
switch (req) {
case H_ENTER:
idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
kvmppc_get_gpr(vcpu, 6),
kvmppc_get_gpr(vcpu, 7));
srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
case H_CEDE:
break;
case H_PROD:
@ -2003,7 +1992,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
/* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
smp_mb();
/* On the first time here, set up HTAB and VRMA or RMA */
/* On the first time here, set up HTAB and VRMA */
if (!vcpu->kvm->arch.rma_setup_done) {
r = kvmppc_hv_setup_htab_rma(vcpu);
if (r)
@ -2040,98 +2029,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
return r;
}
/* Work out RMLS (real mode limit selector) field value for a given RMA size.
Assumes POWER7 or PPC970. */
static inline int lpcr_rmls(unsigned long rma_size)
{
switch (rma_size) {
case 32ul << 20: /* 32 MB */
if (cpu_has_feature(CPU_FTR_ARCH_206))
return 8; /* only supported on POWER7 */
return -1;
case 64ul << 20: /* 64 MB */
return 3;
case 128ul << 20: /* 128 MB */
return 7;
case 256ul << 20: /* 256 MB */
return 4;
case 1ul << 30: /* 1 GB */
return 2;
case 16ul << 30: /* 16 GB */
return 1;
case 256ul << 30: /* 256 GB */
return 0;
default:
return -1;
}
}
static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page;
struct kvm_rma_info *ri = vma->vm_file->private_data;
if (vmf->pgoff >= kvm_rma_pages)
return VM_FAULT_SIGBUS;
page = pfn_to_page(ri->base_pfn + vmf->pgoff);
get_page(page);
vmf->page = page;
return 0;
}
static const struct vm_operations_struct kvm_rma_vm_ops = {
.fault = kvm_rma_fault,
};
static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
{
vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
vma->vm_ops = &kvm_rma_vm_ops;
return 0;
}
static int kvm_rma_release(struct inode *inode, struct file *filp)
{
struct kvm_rma_info *ri = filp->private_data;
kvm_release_rma(ri);
return 0;
}
static const struct file_operations kvm_rma_fops = {
.mmap = kvm_rma_mmap,
.release = kvm_rma_release,
};
static long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
struct kvm_allocate_rma *ret)
{
long fd;
struct kvm_rma_info *ri;
/*
* Only do this on PPC970 in HV mode
*/
if (!cpu_has_feature(CPU_FTR_HVMODE) ||
!cpu_has_feature(CPU_FTR_ARCH_201))
return -EINVAL;
if (!kvm_rma_pages)
return -EINVAL;
ri = kvm_alloc_rma();
if (!ri)
return -ENOMEM;
fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR | O_CLOEXEC);
if (fd < 0)
kvm_release_rma(ri);
ret->rma_size = kvm_rma_pages << PAGE_SHIFT;
return fd;
}
static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
int linux_psize)
{
@ -2210,26 +2107,6 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
return r;
}
static void unpin_slot(struct kvm_memory_slot *memslot)
{
unsigned long *physp;
unsigned long j, npages, pfn;
struct page *page;
physp = memslot->arch.slot_phys;
npages = memslot->npages;
if (!physp)
return;
for (j = 0; j < npages; j++) {
if (!(physp[j] & KVMPPC_GOT_PAGE))
continue;
pfn = physp[j] >> PAGE_SHIFT;
page = pfn_to_page(pfn);
SetPageDirty(page);
put_page(page);
}
}
static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
@ -2237,11 +2114,6 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
vfree(free->arch.rmap);
free->arch.rmap = NULL;
}
if (!dont || free->arch.slot_phys != dont->arch.slot_phys) {
unpin_slot(free);
vfree(free->arch.slot_phys);
free->arch.slot_phys = NULL;
}
}
static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
@ -2250,7 +2122,6 @@ static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
if (!slot->arch.rmap)
return -ENOMEM;
slot->arch.slot_phys = NULL;
return 0;
}
@ -2259,17 +2130,6 @@ static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem)
{
unsigned long *phys;
/* Allocate a slot_phys array if needed */
phys = memslot->arch.slot_phys;
if (!kvm->arch.using_mmu_notifiers && !phys && memslot->npages) {
phys = vzalloc(memslot->npages * sizeof(unsigned long));
if (!phys)
return -ENOMEM;
memslot->arch.slot_phys = phys;
}
return 0;
}
@ -2327,17 +2187,11 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
{
int err = 0;
struct kvm *kvm = vcpu->kvm;
struct kvm_rma_info *ri = NULL;
unsigned long hva;
struct kvm_memory_slot *memslot;
struct vm_area_struct *vma;
unsigned long lpcr = 0, senc;
unsigned long lpcr_mask = 0;
unsigned long psize, porder;
unsigned long rma_size;
unsigned long rmls;
unsigned long *physp;
unsigned long i, npages;
int srcu_idx;
mutex_lock(&kvm->lock);
@ -2372,88 +2226,25 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
psize = vma_kernel_pagesize(vma);
porder = __ilog2(psize);
/* Is this one of our preallocated RMAs? */
if (vma->vm_file && vma->vm_file->f_op == &kvm_rma_fops &&
hva == vma->vm_start)
ri = vma->vm_file->private_data;
up_read(&current->mm->mmap_sem);
if (!ri) {
/* On POWER7, use VRMA; on PPC970, give up */
err = -EPERM;
if (cpu_has_feature(CPU_FTR_ARCH_201)) {
pr_err("KVM: CPU requires an RMO\n");
goto out_srcu;
}
/* We can handle 4k, 64k or 16M pages in the VRMA */
err = -EINVAL;
if (!(psize == 0x1000 || psize == 0x10000 ||
psize == 0x1000000))
goto out_srcu;
/* We can handle 4k, 64k or 16M pages in the VRMA */
err = -EINVAL;
if (!(psize == 0x1000 || psize == 0x10000 ||
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);
/* 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);
lpcr_mask = LPCR_VRMASD;
/* the -4 is to account for senc values starting at 0x10 */
lpcr = senc << (LPCR_VRMASD_SH - 4);
/* Create HPTEs in the hash page table for the VRMA */
kvmppc_map_vrma(vcpu, memslot, porder);
/* Create HPTEs in the hash page table for the VRMA */
kvmppc_map_vrma(vcpu, memslot, porder);
} else {
/* Set up to use an RMO region */
rma_size = kvm_rma_pages;
if (rma_size > memslot->npages)
rma_size = memslot->npages;
rma_size <<= PAGE_SHIFT;
rmls = lpcr_rmls(rma_size);
err = -EINVAL;
if ((long)rmls < 0) {
pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
goto out_srcu;
}
atomic_inc(&ri->use_count);
kvm->arch.rma = ri;
/* Update LPCR and RMOR */
if (cpu_has_feature(CPU_FTR_ARCH_201)) {
/* PPC970; insert RMLS value (split field) in HID4 */
lpcr_mask = (1ul << HID4_RMLS0_SH) |
(3ul << HID4_RMLS2_SH) | HID4_RMOR;
lpcr = ((rmls >> 2) << HID4_RMLS0_SH) |
((rmls & 3) << HID4_RMLS2_SH);
/* RMOR is also in HID4 */
lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff)
<< HID4_RMOR_SH;
} else {
/* POWER7 */
lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS;
lpcr = rmls << LPCR_RMLS_SH;
kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
}
pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
/* Initialize phys addrs of pages in RMO */
npages = kvm_rma_pages;
porder = __ilog2(npages);
physp = memslot->arch.slot_phys;
if (physp) {
if (npages > memslot->npages)
npages = memslot->npages;
spin_lock(&kvm->arch.slot_phys_lock);
for (i = 0; i < npages; ++i)
physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) +
porder;
spin_unlock(&kvm->arch.slot_phys_lock);
}
}
kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
smp_wmb();
@ -2492,35 +2283,21 @@ 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.rma = NULL;
kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
if (cpu_has_feature(CPU_FTR_ARCH_201)) {
/* PPC970; HID4 is effectively the LPCR */
kvm->arch.host_lpid = 0;
kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4);
lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH));
lpcr |= ((lpid >> 4) << HID4_LPID1_SH) |
((lpid & 0xf) << HID4_LPID5_SH);
} else {
/* POWER7; init LPCR for virtual RMA mode */
kvm->arch.host_lpid = mfspr(SPRN_LPID);
kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
lpcr &= LPCR_PECE | LPCR_LPES;
lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
LPCR_VPM0 | LPCR_VPM1;
kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
/* On POWER8 turn on online bit to enable PURR/SPURR */
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lpcr |= LPCR_ONL;
}
/* Init LPCR for virtual RMA mode */
kvm->arch.host_lpid = mfspr(SPRN_LPID);
kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
lpcr &= LPCR_PECE | LPCR_LPES;
lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
LPCR_VPM0 | LPCR_VPM1;
kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
/* On POWER8 turn on online bit to enable PURR/SPURR */
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lpcr |= LPCR_ONL;
kvm->arch.lpcr = lpcr;
kvm->arch.using_mmu_notifiers = !!cpu_has_feature(CPU_FTR_ARCH_206);
spin_lock_init(&kvm->arch.slot_phys_lock);
/*
* Track that we now have a HV mode VM active. This blocks secondary
* CPU threads from coming online.
@ -2550,10 +2327,6 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
kvm_hv_vm_deactivated();
kvmppc_free_vcores(kvm);
if (kvm->arch.rma) {
kvm_release_rma(kvm->arch.rma);
kvm->arch.rma = NULL;
}
kvmppc_free_hpt(kvm);
}
@ -2579,7 +2352,8 @@ static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
static int kvmppc_core_check_processor_compat_hv(void)
{
if (!cpu_has_feature(CPU_FTR_HVMODE))
if (!cpu_has_feature(CPU_FTR_HVMODE) ||
!cpu_has_feature(CPU_FTR_ARCH_206))
return -EIO;
return 0;
}
@ -2593,16 +2367,6 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
switch (ioctl) {
case KVM_ALLOCATE_RMA: {
struct kvm_allocate_rma rma;
struct kvm *kvm = filp->private_data;
r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma)))
r = -EFAULT;
break;
}
case KVM_PPC_ALLOCATE_HTAB: {
u32 htab_order;

104
arch/powerpc/kvm/book3s_hv_builtin.c
View file

@ -33,95 +33,9 @@
* By default we reserve 5% of memory for hash pagetable allocation.
*/
static unsigned long kvm_cma_resv_ratio = 5;
/*
* We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area.
* Each RMA has to be physically contiguous and of a size that the
* hardware supports. PPC970 and POWER7 support 64MB, 128MB and 256MB,
* and other larger sizes. Since we are unlikely to be allocate that
* much physically contiguous memory after the system is up and running,
* we preallocate a set of RMAs in early boot using CMA.
* should be power of 2.
*/
unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT; /* 128MB */
EXPORT_SYMBOL_GPL(kvm_rma_pages);
static struct cma *kvm_cma;
/* Work out RMLS (real mode limit selector) field value for a given RMA size.
Assumes POWER7 or PPC970. */
static inline int lpcr_rmls(unsigned long rma_size)
{
switch (rma_size) {
case 32ul << 20: /* 32 MB */
if (cpu_has_feature(CPU_FTR_ARCH_206))
return 8; /* only supported on POWER7 */
return -1;
case 64ul << 20: /* 64 MB */
return 3;
case 128ul << 20: /* 128 MB */
return 7;
case 256ul << 20: /* 256 MB */
return 4;
case 1ul << 30: /* 1 GB */
return 2;
case 16ul << 30: /* 16 GB */
return 1;
case 256ul << 30: /* 256 GB */
return 0;
default:
return -1;
}
}
static int __init early_parse_rma_size(char *p)
{
unsigned long kvm_rma_size;
pr_debug("%s(%s)\n", __func__, p);
if (!p)
return -EINVAL;
kvm_rma_size = memparse(p, &p);
/*
* Check that the requested size is one supported in hardware
*/
if (lpcr_rmls(kvm_rma_size) < 0) {
pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
return -EINVAL;
}
kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT;
return 0;
}
early_param("kvm_rma_size", early_parse_rma_size);
struct kvm_rma_info *kvm_alloc_rma()
{
struct page *page;
struct kvm_rma_info *ri;
ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
if (!ri)
return NULL;
page = cma_alloc(kvm_cma, kvm_rma_pages, order_base_2(kvm_rma_pages));
if (!page)
goto err_out;
atomic_set(&ri->use_count, 1);
ri->base_pfn = page_to_pfn(page);
return ri;
err_out:
kfree(ri);
return NULL;
}
EXPORT_SYMBOL_GPL(kvm_alloc_rma);
void kvm_release_rma(struct kvm_rma_info *ri)
{
if (atomic_dec_and_test(&ri->use_count)) {
cma_release(kvm_cma, pfn_to_page(ri->base_pfn), kvm_rma_pages);
kfree(ri);
}
}
EXPORT_SYMBOL_GPL(kvm_release_rma);
static int __init early_parse_kvm_cma_resv(char *p)
{
pr_debug("%s(%s)\n", __func__, p);
@ -133,14 +47,9 @@ early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv);
struct page *kvm_alloc_hpt(unsigned long nr_pages)
{
unsigned long align_pages = HPT_ALIGN_PAGES;
VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
/* Old CPUs require HPT aligned on a multiple of its size */
if (!cpu_has_feature(CPU_FTR_ARCH_206))
align_pages = nr_pages;
return cma_alloc(kvm_cma, nr_pages, order_base_2(align_pages));
return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES));
}
EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
@ -181,16 +90,7 @@ void __init kvm_cma_reserve(void)
if (selected_size) {
pr_debug("%s: reserving %ld MiB for global area\n", __func__,
(unsigned long)selected_size / SZ_1M);
/*
* Old CPUs require HPT aligned on a multiple of its size. So for them
* make the alignment as max size we could request.
*/
if (!cpu_has_feature(CPU_FTR_ARCH_206))
align_size = __rounddown_pow_of_two(selected_size);
else
align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
cma_declare_contiguous(0, selected_size, 0, align_size,
KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma);
}

39
arch/powerpc/kvm/book3s_hv_interrupts.S
View file

@ -52,10 +52,8 @@ _GLOBAL(__kvmppc_vcore_entry)
std r3, _CCR(r1)
/* Save host DSCR */
BEGIN_FTR_SECTION
mfspr r3, SPRN_DSCR
std r3, HSTATE_DSCR(r13)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
BEGIN_FTR_SECTION
/* Save host DABR */
@ -84,11 +82,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mfspr r7, SPRN_MMCR0 /* save MMCR0 */
mtspr SPRN_MMCR0, r3 /* freeze all counters, disable interrupts */
mfspr r6, SPRN_MMCRA
BEGIN_FTR_SECTION
/* On P7, clear MMCRA in order to disable SDAR updates */
/* Clear MMCRA in order to disable SDAR updates */
li r5, 0
mtspr SPRN_MMCRA, r5
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
isync
ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */
lbz r5, LPPACA_PMCINUSE(r3)
@ -113,20 +109,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mfspr r7, SPRN_PMC4
mfspr r8, SPRN_PMC5
mfspr r9, SPRN_PMC6
BEGIN_FTR_SECTION
mfspr r10, SPRN_PMC7
mfspr r11, SPRN_PMC8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
stw r3, HSTATE_PMC(r13)
stw r5, HSTATE_PMC + 4(r13)
stw r6, HSTATE_PMC + 8(r13)
stw r7, HSTATE_PMC + 12(r13)
stw r8, HSTATE_PMC + 16(r13)
stw r9, HSTATE_PMC + 20(r13)
BEGIN_FTR_SECTION
stw r10, HSTATE_PMC + 24(r13)
stw r11, HSTATE_PMC + 28(r13)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
31:
/*
@ -140,31 +128,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
add r8,r8,r7
std r8,HSTATE_DECEXP(r13)
#ifdef CONFIG_SMP
/*
* On PPC970, if the guest vcpu has an external interrupt pending,
* send ourselves an IPI so as to interrupt the guest once it
* enables interrupts. (It must have interrupts disabled,
* otherwise we would already have delivered the interrupt.)
*
* XXX If this is a UP build, smp_send_reschedule is not available,
* so the interrupt will be delayed until the next time the vcpu
* enters the guest with interrupts enabled.
*/
BEGIN_FTR_SECTION
ld r4, HSTATE_KVM_VCPU(r13)
ld r0, VCPU_PENDING_EXC(r4)
li r7, (1 << BOOK3S_IRQPRIO_EXTERNAL)
oris r7, r7, (1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
and. r0, r0, r7
beq 32f
lhz r3, PACAPACAINDEX(r13)
bl smp_send_reschedule
nop
32:
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
#endif /* CONFIG_SMP */
/* Jump to partition switch code */
bl kvmppc_hv_entry_trampoline
nop

5
arch/powerpc/kvm/book3s_hv_ras.c
View file

@ -138,8 +138,5 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
{
if (cpu_has_feature(CPU_FTR_ARCH_206))
return kvmppc_realmode_mc_power7(vcpu);
return 0;
return kvmppc_realmode_mc_power7(vcpu);
}

110
arch/powerpc/kvm/book3s_hv_rm_mmu.c
View file

@ -45,16 +45,12 @@ static int global_invalidates(struct kvm *kvm, unsigned long flags)
* as indicated by local_paca->kvm_hstate.kvm_vcpu being set,
* we can use tlbiel as long as we mark all other physical
* cores as potentially having stale TLB entries for this lpid.
* If we're not using MMU notifiers, we never take pages away
* from the guest, so we can use tlbiel if requested.
* Otherwise, don't use tlbiel.
*/
if (kvm->arch.online_vcores == 1 && local_paca->kvm_hstate.kvm_vcpu)
global = 0;
else if (kvm->arch.using_mmu_notifiers)
global = 1;
else
global = !(flags & H_LOCAL);
global = 1;
if (!global) {
/* any other core might now have stale TLB entries... */
@ -170,7 +166,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
struct revmap_entry *rev;
unsigned long g_ptel;
struct kvm_memory_slot *memslot;
unsigned long *physp, pte_size;
unsigned long pte_size;
unsigned long is_io;
unsigned long *rmap;
pte_t pte;
@ -198,9 +194,6 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
is_io = ~0ul;
rmap = NULL;
if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID))) {
/* PPC970 can't do emulated MMIO */
if (!cpu_has_feature(CPU_FTR_ARCH_206))
return H_PARAMETER;
/* Emulated MMIO - mark this with key=31 */
pteh |= HPTE_V_ABSENT;
ptel |= HPTE_R_KEY_HI | HPTE_R_KEY_LO;
@ -213,37 +206,20 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
slot_fn = gfn - memslot->base_gfn;
rmap = &memslot->arch.rmap[slot_fn];
if (!kvm->arch.using_mmu_notifiers) {
physp = memslot->arch.slot_phys;
if (!physp)
return H_PARAMETER;
physp += slot_fn;
if (realmode)
physp = real_vmalloc_addr(physp);
pa = *physp;
if (!pa)
return H_TOO_HARD;
is_io = pa & (HPTE_R_I | HPTE_R_W);
pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
pa &= PAGE_MASK;
pa |= gpa & ~PAGE_MASK;
} else {
/* Translate to host virtual address */
hva = __gfn_to_hva_memslot(memslot, gfn);
/* Translate to host virtual address */
hva = __gfn_to_hva_memslot(memslot, gfn);
/* Look up the Linux PTE for the backing page */
pte_size = psize;
pte = lookup_linux_pte_and_update(pgdir, hva, writing,
&pte_size);
if (pte_present(pte) && !pte_numa(pte)) {
if (writing && !pte_write(pte))
/* make the actual HPTE be read-only */
ptel = hpte_make_readonly(ptel);
is_io = hpte_cache_bits(pte_val(pte));
pa = pte_pfn(pte) << PAGE_SHIFT;
pa |= hva & (pte_size - 1);
pa |= gpa & ~PAGE_MASK;
}
/* Look up the Linux PTE for the backing page */
pte_size = psize;
pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size);
if (pte_present(pte) && !pte_numa(pte)) {
if (writing && !pte_write(pte))
/* make the actual HPTE be read-only */
ptel = hpte_make_readonly(ptel);
is_io = hpte_cache_bits(pte_val(pte));
pa = pte_pfn(pte) << PAGE_SHIFT;
pa |= hva & (pte_size - 1);
pa |= gpa & ~PAGE_MASK;
}
if (pte_size < psize)
@ -337,8 +313,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
rmap = real_vmalloc_addr(rmap);
lock_rmap(rmap);
/* Check for pending invalidations under the rmap chain lock */
if (kvm->arch.using_mmu_notifiers &&
mmu_notifier_retry(kvm, mmu_seq)) {
if (mmu_notifier_retry(kvm, mmu_seq)) {
/* inval in progress, write a non-present HPTE */
pteh |= HPTE_V_ABSENT;
pteh &= ~HPTE_V_VALID;
@ -395,61 +370,11 @@ static inline int try_lock_tlbie(unsigned int *lock)
return old == 0;
}
/*
* tlbie/tlbiel is a bit different on the PPC970 compared to later
* processors such as POWER7; the large page bit is in the instruction
* not RB, and the top 16 bits and the bottom 12 bits of the VA
* in RB must be 0.
*/
static void do_tlbies_970(struct kvm *kvm, unsigned long *rbvalues,
long npages, int global, bool need_sync)
{
long i;
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) {
unsigned long rb = rbvalues[i];
if (rb & 1) /* large page */
asm volatile("tlbie %0,1" : :
"r" (rb & 0x0000fffffffff000ul));
else
asm volatile("tlbie %0,0" : :
"r" (rb & 0x0000fffffffff000ul));
}
asm volatile("eieio; tlbsync; ptesync" : : : "memory");
kvm->arch.tlbie_lock = 0;
} else {
if (need_sync)
asm volatile("ptesync" : : : "memory");
for (i = 0; i < npages; ++i) {
unsigned long rb = rbvalues[i];
if (rb & 1) /* large page */
asm volatile("tlbiel %0,1" : :
"r" (rb & 0x0000fffffffff000ul));
else
asm volatile("tlbiel %0,0" : :
"r" (rb & 0x0000fffffffff000ul));
}
asm volatile("ptesync" : : : "memory");
}
}
static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
long npages, int global, bool need_sync)
{
long i;
if (cpu_has_feature(CPU_FTR_ARCH_201)) {
/* PPC970 tlbie instruction is a bit different */
do_tlbies_970(kvm, rbvalues, npages, global, need_sync);
return;
}
if (global) {
while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
cpu_relax();
@ -677,8 +602,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
*/
pte = be64_to_cpu(hpte[1]);
r = (pte & ~mask) | bits;
if (hpte_is_writable(r) && kvm->arch.using_mmu_notifiers &&
!hpte_is_writable(pte))
if (hpte_is_writable(r) && !hpte_is_writable(pte))
r = hpte_make_readonly(r);
/* If the PTE is changing, invalidate it first */
if (r != pte) {

245
arch/powerpc/kvm/book3s_hv_rmhandlers.S
View file

@ -94,20 +94,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
lwz r6, HSTATE_PMC + 12(r13)
lwz r8, HSTATE_PMC + 16(r13)
lwz r9, HSTATE_PMC + 20(r13)
BEGIN_FTR_SECTION
lwz r10, HSTATE_PMC + 24(r13)
lwz r11, HSTATE_PMC + 28(r13)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
mtspr SPRN_PMC1, r3
mtspr SPRN_PMC2, r4
mtspr SPRN_PMC3, r5
mtspr SPRN_PMC4, r6
mtspr SPRN_PMC5, r8
mtspr SPRN_PMC6, r9
BEGIN_FTR_SECTION
mtspr SPRN_PMC7, r10
mtspr SPRN_PMC8, r11
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
ld r3, HSTATE_MMCR(r13)
ld r4, HSTATE_MMCR + 8(r13)
ld r5, HSTATE_MMCR + 16(r13)
@ -153,11 +145,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
cmpwi cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
BEGIN_FTR_SECTION
beq 11f
cmpwi cr2, r12, BOOK3S_INTERRUPT_HMI
beq cr2, 14f /* HMI check */
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* RFI into the highmem handler, or branch to interrupt handler */
mfmsr r6
@ -166,7 +156,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
mtmsrd r6, 1 /* Clear RI in MSR */
mtsrr0 r8
mtsrr1 r7
beqa 0x500 /* external interrupt (PPC970) */
beq cr1, 13f /* machine check */
RFI
@ -374,11 +363,8 @@ kvmppc_hv_entry:
slbia
ptesync
BEGIN_FTR_SECTION
b 30f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
/*
* POWER7 host -> guest partition switch code.
* POWER7/POWER8 host -> guest partition switch code.
* We don't have to lock against concurrent tlbies,
* but we do have to coordinate across hardware threads.
*/
@ -486,97 +472,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
cmpwi r3,512 /* 1 microsecond */
li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
blt hdec_soon
b 31f
/*
* PPC970 host -> guest partition switch code.
* We have to lock against concurrent tlbies,
* using native_tlbie_lock to lock against host tlbies
* and kvm->arch.tlbie_lock to lock against guest tlbies.
* We also have to invalidate the TLB since its
* entries aren't tagged with the LPID.
*/
30: ld r5,HSTATE_KVM_VCORE(r13)
ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
/* first take native_tlbie_lock */
.section ".toc","aw"
toc_tlbie_lock:
.tc native_tlbie_lock[TC],native_tlbie_lock
.previous
ld r3,toc_tlbie_lock@toc(r2)
#ifdef __BIG_ENDIAN__
lwz r8,PACA_LOCK_TOKEN(r13)
#else
lwz r8,PACAPACAINDEX(r13)
#endif
24: lwarx r0,0,r3
cmpwi r0,0
bne 24b
stwcx. r8,0,r3
bne 24b
isync
ld r5,HSTATE_KVM_VCORE(r13)
ld r7,VCORE_LPCR(r5) /* use vcore->lpcr to store HID4 */
li r0,0x18f
rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */
or r0,r7,r0
ptesync
sync
mtspr SPRN_HID4,r0 /* switch to reserved LPID */
isync
li r0,0
stw r0,0(r3) /* drop native_tlbie_lock */
/* invalidate the whole TLB */
li r0,256
mtctr r0
li r6,0
25: tlbiel r6
addi r6,r6,0x1000
bdnz 25b
ptesync
/* Take the guest's tlbie_lock */
addi r3,r9,KVM_TLBIE_LOCK
24: lwarx r0,0,r3
cmpwi r0,0
bne 24b
stwcx. r8,0,r3
bne 24b
isync
ld r6,KVM_SDR1(r9)
mtspr SPRN_SDR1,r6 /* switch to partition page table */
/* Set up HID4 with the guest's LPID etc. */
sync
mtspr SPRN_HID4,r7
isync
/* drop the guest's tlbie_lock */
li r0,0
stw r0,0(r3)
/* Check if HDEC expires soon */
mfspr r3,SPRN_HDEC
cmpwi r3,10
li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
blt hdec_soon
/* Enable HDEC interrupts */
mfspr r0,SPRN_HID0
li r3,1
rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1
sync
mtspr SPRN_HID0,r0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
31:
/* Do we have a guest vcpu to run? */
cmpdi r4, 0
beq kvmppc_primary_no_guest
@ -606,7 +502,6 @@ kvmppc_got_guest:
stb r6, VCPU_VPA_DIRTY(r4)
25:
BEGIN_FTR_SECTION
/* Save purr/spurr */
mfspr r5,SPRN_PURR
mfspr r6,SPRN_SPURR
@ -616,7 +511,6 @@ BEGIN_FTR_SECTION
ld r8,VCPU_SPURR(r4)
mtspr SPRN_PURR,r7
mtspr SPRN_SPURR,r8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
BEGIN_FTR_SECTION
/* Set partition DABR */
@ -625,9 +519,7 @@ BEGIN_FTR_SECTION
ld r6,VCPU_DABR(r4)
mtspr SPRN_DABRX,r5
mtspr SPRN_DABR,r6
BEGIN_FTR_SECTION_NESTED(89)
isync
END_FTR_SECTION_NESTED(CPU_FTR_ARCH_206, CPU_FTR_ARCH_206, 89)
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@ -758,20 +650,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
lwz r7, VCPU_PMC + 12(r4)
lwz r8, VCPU_PMC + 16(r4)
lwz r9, VCPU_PMC + 20(r4)
BEGIN_FTR_SECTION
lwz r10, VCPU_PMC + 24(r4)
lwz r11, VCPU_PMC + 28(r4)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
mtspr SPRN_PMC1, r3
mtspr SPRN_PMC2, r5
mtspr SPRN_PMC3, r6
mtspr SPRN_PMC4, r7
mtspr SPRN_PMC5, r8
mtspr SPRN_PMC6, r9
BEGIN_FTR_SECTION
mtspr SPRN_PMC7, r10
mtspr SPRN_PMC8, r11
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
ld r3, VCPU_MMCR(r4)
ld r5, VCPU_MMCR + 8(r4)
ld r6, VCPU_MMCR + 16(r4)
@ -818,14 +702,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
ld r30, VCPU_GPR(R30)(r4)
ld r31, VCPU_GPR(R31)(r4)
BEGIN_FTR_SECTION
/* Switch DSCR to guest value */
ld r5, VCPU_DSCR(r4)
mtspr SPRN_DSCR, r5
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
BEGIN_FTR_SECTION
/* Skip next section on POWER7 or PPC970 */
/* Skip next section on POWER7 */
b 8f
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
@ -901,7 +783,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_DAR, r5
mtspr SPRN_DSISR, r6
BEGIN_FTR_SECTION
/* Restore AMR and UAMOR, set AMOR to all 1s */
ld r5,VCPU_AMR(r4)
ld r6,VCPU_UAMOR(r4)
@ -909,7 +790,6 @@ BEGIN_FTR_SECTION
mtspr SPRN_AMR,r5
mtspr SPRN_UAMOR,r6
mtspr SPRN_AMOR,r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* Restore state of CTRL run bit; assume 1 on entry */
lwz r5,VCPU_CTRL(r4)
@ -944,13 +824,11 @@ deliver_guest_interrupt:
rldicl r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
cmpdi cr1, r0, 0
andi. r8, r11, MSR_EE
BEGIN_FTR_SECTION
mfspr r8, SPRN_LPCR
/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
mtspr SPRN_LPCR, r8
isync
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
beq 5f
li r0, BOOK3S_INTERRUPT_EXTERNAL
bne cr1, 12f
@ -1108,11 +986,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* Save HEIR (HV emulation assist reg) in last_inst
if this is an HEI (HV emulation interrupt, e40) */
li r3,KVM_INST_FETCH_FAILED
BEGIN_FTR_SECTION
cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
bne 11f
mfspr r3,SPRN_HEIR
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
11: stw r3,VCPU_LAST_INST(r9)
/* these are volatile across C function calls */
@ -1121,13 +997,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
std r3, VCPU_CTR(r9)
stw r4, VCPU_XER(r9)
BEGIN_FTR_SECTION
/* If this is a page table miss then see if it's theirs or ours */
cmpwi r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
beq kvmppc_hdsi
cmpwi r12, BOOK3S_INTERRUPT_H_INST_STORAGE
beq kvmppc_hisi
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* See if this is a leftover HDEC interrupt */
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
@ -1140,11 +1014,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
beq hcall_try_real_mode
/* Only handle external interrupts here on arch 206 and later */
BEGIN_FTR_SECTION
b ext_interrupt_to_host
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
/* External interrupt ? */
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
bne+ ext_interrupt_to_host
@ -1174,11 +1043,9 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
mfdsisr r7
std r6, VCPU_DAR(r9)
stw r7, VCPU_DSISR(r9)
BEGIN_FTR_SECTION
/* don't overwrite fault_dar/fault_dsisr if HDSI */
cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
beq 6f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
std r6, VCPU_FAULT_DAR(r9)
stw r7, VCPU_FAULT_DSISR(r9)
@ -1217,7 +1084,6 @@ mc_cont:
/*
* Save the guest PURR/SPURR
*/
BEGIN_FTR_SECTION
mfspr r5,SPRN_PURR
mfspr r6,SPRN_SPURR
ld r7,VCPU_PURR(r9)
@ -1237,7 +1103,6 @@ BEGIN_FTR_SECTION
add r4,r4,r6
mtspr SPRN_PURR,r3
mtspr SPRN_SPURR,r4
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
/* Save DEC */
mfspr r5,SPRN_DEC
@ -1287,22 +1152,18 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
8:
/* Save and reset AMR and UAMOR before turning on the MMU */
BEGIN_FTR_SECTION
mfspr r5,SPRN_AMR
mfspr r6,SPRN_UAMOR
std r5,VCPU_AMR(r9)
std r6,VCPU_UAMOR(r9)
li r6,0
mtspr SPRN_AMR,r6
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* Switch DSCR back to host value */
BEGIN_FTR_SECTION
mfspr r8, SPRN_DSCR
ld r7, HSTATE_DSCR(r13)
std r8, VCPU_DSCR(r9)
mtspr SPRN_DSCR, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* Save non-volatile GPRs */
std r14, VCPU_GPR(R14)(r9)
@ -1484,11 +1345,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mfspr r4, SPRN_MMCR0 /* save MMCR0 */
mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */
mfspr r6, SPRN_MMCRA
BEGIN_FTR_SECTION
/* On P7, clear MMCRA in order to disable SDAR updates */
/* Clear MMCRA in order to disable SDAR updates */
li r7, 0
mtspr SPRN_MMCRA, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
isync
beq 21f /* if no VPA, save PMU stuff anyway */
lbz r7, LPPACA_PMCINUSE(r8)
@ -1513,20 +1372,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mfspr r6, SPRN_PMC4
mfspr r7, SPRN_PMC5
mfspr r8, SPRN_PMC6
BEGIN_FTR_SECTION
mfspr r10, SPRN_PMC7
mfspr r11, SPRN_PMC8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
stw r3, VCPU_PMC(r9)
stw r4, VCPU_PMC + 4(r9)
stw r5, VCPU_PMC + 8(r9)
stw r6, VCPU_PMC + 12(r9)
stw r7, VCPU_PMC + 16(r9)
stw r8, VCPU_PMC + 20(r9)
BEGIN_FTR_SECTION
stw r10, VCPU_PMC + 24(r9)
stw r11, VCPU_PMC + 28(r9)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
BEGIN_FTR_SECTION
mfspr r5, SPRN_SIER
mfspr r6, SPRN_SPMC1
@ -1547,11 +1398,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
ptesync
hdec_soon: /* r12 = trap, r13 = paca */
BEGIN_FTR_SECTION
b 32f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
/*
* POWER7 guest -> host partition switch code.
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
* have to coordinate the hardware threads.
*/
@ -1679,87 +1527,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
16: ld r8,KVM_HOST_LPCR(r4)
mtspr SPRN_LPCR,r8
isync
b 33f
/*
* PPC970 guest -> host partition switch code.
* We have to lock against concurrent tlbies, and
* we have to flush the whole TLB.
*/
32: ld r5,HSTATE_KVM_VCORE(r13)
ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
/* Take the guest's tlbie_lock */
#ifdef __BIG_ENDIAN__
lwz r8,PACA_LOCK_TOKEN(r13)
#else
lwz r8,PACAPACAINDEX(r13)
#endif
addi r3,r4,KVM_TLBIE_LOCK
24: lwarx r0,0,r3
cmpwi r0,0
bne 24b
stwcx. r8,0,r3
bne 24b
isync
ld r7,KVM_HOST_LPCR(r4) /* use kvm->arch.host_lpcr for HID4 */
li r0,0x18f
rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */
or r0,r7,r0
ptesync
sync
mtspr SPRN_HID4,r0 /* switch to reserved LPID */
isync
li r0,0
stw r0,0(r3) /* drop guest tlbie_lock */
/* invalidate the whole TLB */
li r0,256
mtctr r0
li r6,0
25: tlbiel r6
addi r6,r6,0x1000
bdnz 25b
ptesync
/* take native_tlbie_lock */
ld r3,toc_tlbie_lock@toc(2)
24: lwarx r0,0,r3
cmpwi r0,0
bne 24b
stwcx. r8,0,r3
bne 24b
isync
ld r6,KVM_HOST_SDR1(r4)
mtspr SPRN_SDR1,r6 /* switch to host page table */
/* Set up host HID4 value */
sync
mtspr SPRN_HID4,r7
isync
li r0,0
stw r0,0(r3) /* drop native_tlbie_lock */
lis r8,0x7fff /* MAX_INT@h */
mtspr SPRN_HDEC,r8
/* Disable HDEC interrupts */
mfspr r0,SPRN_HID0
li r3,0
rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1
sync
mtspr SPRN_HID0,r0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
/* load host SLB entries */
33: ld r8,PACA_SLBSHADOWPTR(r13)
ld r8,PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
li r3, SLBSHADOW_SAVEAREA
@ -2107,9 +1877,6 @@ _GLOBAL(kvmppc_h_cede)
stw r0,VCPU_TRAP(r3)
li r0,H_SUCCESS
std r0,VCPU_GPR(R3)(r3)
BEGIN_FTR_SECTION
b kvm_cede_exit /* just send it up to host on 970 */
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
/*
* Set our bit in the bitmask of napping threads unless all the
@ -2435,7 +2202,6 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
mtmsrd r8
isync
addi r3,r3,VCPU_FPRS
bl store_fp_state
#ifdef CONFIG_ALTIVEC
@ -2471,7 +2237,6 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
mtmsrd r8
isync
addi r3,r4,VCPU_FPRS
bl load_fp_state
#ifdef CONFIG_ALTIVEC

10
arch/powerpc/kvm/powerpc.c
View file

@ -527,18 +527,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = 0;
break;
case KVM_CAP_PPC_RMA:
r = hv_enabled;
/* PPC970 requires an RMA */
if (r && cpu_has_feature(CPU_FTR_ARCH_201))
r = 2;
r = 0;
break;
#endif
case KVM_CAP_SYNC_MMU:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
if (hv_enabled)
r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
else
r = 0;
r = hv_enabled;
#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
r = 1;
#else