/*
* set a new huge pmd. We should not be called for updating
* an existing pmd entry. That should go via pmd_hugepage_update.
*/
void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
#ifdef CONFIG_DEBUG_VM
WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
assert_spin_locked(&mm->page_table_lock);
WARN_ON(!pmd_trans_huge(pmd));
#endif
trace_hugepage_set_pmd(addr, pmd_val(pmd));
return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
}
/*
* set a new huge pmd. We should not be called for updating
* an existing pmd entry. That should go via pmd_hugepage_update.
*/
void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
#ifdef CONFIG_DEBUG_VM
/*
* Make sure hardware valid bit is not set. We don't do
* tlb flush for this update.
*/
WARN_ON(pte_hw_valid(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
assert_spin_locked(pmd_lockptr(mm, pmdp));
WARN_ON(!(pmd_large(pmd) || pmd_devmap(pmd)));
#endif
trace_hugepage_set_pmd(addr, pmd_val(pmd));
return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
}
/*
* set_pte stores a linux PTE into the linux page table.
*/
void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
pte_t pte)
{
/*
* When handling numa faults, we already have the pte marked
* _PAGE_PRESENT, but we can be sure that it is not in hpte.
* Hence we can use set_pte_at for them.
*/
VM_WARN_ON(pte_present(*ptep) && !pte_protnone(*ptep));
/* Add the pte bit when trying to set a pte */
pte = __pte(pte_val(pte) | _PAGE_PTE);
/* Note: mm->context.id might not yet have been assigned as
* this context might not have been activated yet when this
* is called.
*/
pte = set_pte_filter(pte);
/* Perform the setting of the PTE */
__set_pte_at(mm, addr, ptep, pte, 0);
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
struct mm_struct *mm = vma->vm_mm;
struct dev_pagemap *pgmap = NULL;
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
retry:
if (unlikely(pmd_bad(*pmd)))
return no_page_table(vma, flags);
ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
pte = *ptep;
if (!pte_present(pte)) {
swp_entry_t entry;
/*
* KSM's break_ksm() relies upon recognizing a ksm page
* even while it is being migrated, so for that case we
* need migration_entry_wait().
*/
if (likely(!(flags & FOLL_MIGRATION)))
goto no_page;
if (pte_none(pte))
goto no_page;
entry = pte_to_swp_entry(pte);
if (!is_migration_entry(entry))
goto no_page;
pte_unmap_unlock(ptep, ptl);
migration_entry_wait(mm, pmd, address);
goto retry;
}
if ((flags & FOLL_NUMA) && pte_protnone(pte))
goto no_page;
if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
pte_unmap_unlock(ptep, ptl);
return NULL;
}
page = vm_normal_page(vma, address, pte);
if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
/*
* Only return device mapping pages in the FOLL_GET case since
* they are only valid while holding the pgmap reference.
*/
pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
if (pgmap)
page = pte_page(pte);
else
goto no_page;
} else if (unlikely(!page)) {
if (flags & FOLL_DUMP) {
/* Avoid special (like zero) pages in core dumps */
page = ERR_PTR(-EFAULT);
goto out;
}
if (is_zero_pfn(pte_pfn(pte))) {
page = pte_page(pte);
} else {
int ret;
ret = follow_pfn_pte(vma, address, ptep, flags);
page = ERR_PTR(ret);
goto out;
}
}
if (flags & FOLL_SPLIT && PageTransCompound(page)) {
int ret;
get_page(page);
pte_unmap_unlock(ptep, ptl);
lock_page(page);
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
if (ret)
return ERR_PTR(ret);
goto retry;
}
if (flags & FOLL_GET) {
get_page(page);
/* drop the pgmap reference now that we hold the page */
if (pgmap) {
put_dev_pagemap(pgmap);
pgmap = NULL;
}
}
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
set_page_dirty(page);
/*
* pte_mkyoung() would be more correct here, but atomic care
* is needed to avoid losing the dirty bit: it is easier to use
* mark_page_accessed().
*/
mark_page_accessed(page);
}
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/* Do not mlock pte-mapped THP */
if (PageTransCompound(page))
goto out;
/*
* The preliminary mapping check is mainly to avoid the
* pointless overhead of lock_page on the ZERO_PAGE
* which might bounce very badly if there is contention.
*
* If the page is already locked, we don't need to
* handle it now - vmscan will handle it later if and
* when it attempts to reclaim the page.
*/
if (page->mapping && trylock_page(page)) {
lru_add_drain(); /* push cached pages to LRU */
/*
* Because we lock page here, and migration is
* blocked by the pte's page reference, and we
* know the page is still mapped, we don't even
* need to check for file-cache page truncation.
*/
mlock_vma_page(page);
unlock_page(page);
}
}
out:
pte_unmap_unlock(ptep, ptl);
return page;
no_page:
pte_unmap_unlock(ptep, ptl);
if (!pte_none(pte))
return NULL;
return no_page_table(vma, flags);
}
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 *pte_idx_ret)
{
unsigned long i, pa, gpa, gfn, psize;
unsigned long slot_fn, hva;
__be64 *hpte;
struct revmap_entry *rev;
unsigned long g_ptel;
struct kvm_memory_slot *memslot;
unsigned hpage_shift;
bool is_ci;
unsigned long *rmap;
pte_t *ptep;
unsigned int writing;
unsigned long mmu_seq;
unsigned long rcbits, irq_flags = 0;
if (kvm_is_radix(kvm))
return H_FUNCTION;
psize = kvmppc_actual_pgsz(pteh, ptel);
if (!psize)
return H_PARAMETER;
writing = hpte_is_writable(ptel);
pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
ptel &= ~HPTE_GR_RESERVED;
g_ptel = ptel;
/* used later to detect if we might have been invalidated */
mmu_seq = kvm->mmu_notifier_seq;
smp_rmb();
/* Find the memslot (if any) for this address */
gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
gfn = gpa >> PAGE_SHIFT;
memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
pa = 0;
is_ci = false;
rmap = NULL;
if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID))) {
/* Emulated MMIO - mark this with key=31 */
pteh |= HPTE_V_ABSENT;
ptel |= HPTE_R_KEY_HI | HPTE_R_KEY_LO;
goto do_insert;
}
/* Check if the requested page fits entirely in the memslot. */
if (!slot_is_aligned(memslot, psize))
return H_PARAMETER;
slot_fn = gfn - memslot->base_gfn;
rmap = &memslot->arch.rmap[slot_fn];
/* Translate to host virtual address */
hva = __gfn_to_hva_memslot(memslot, gfn);
/*
* If we had a page table table change after lookup, we would
* retry via mmu_notifier_retry.
*/
if (!realmode)
local_irq_save(irq_flags);
/*
* 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;
if (hpage_shift)
host_pte_size = 1ul << hpage_shift;
else
host_pte_size = PAGE_SIZE;
/*
* We should always find the guest page size
* to <= host page size, if host is using hugepage
*/
if (host_pte_size < psize) {
if (!realmode)
local_irq_restore(flags);
return H_PARAMETER;
}
pte = kvmppc_read_update_linux_pte(ptep, writing);
if (pte_present(pte) && !pte_protnone(pte)) {
if (writing && !__pte_write(pte))
/* make the actual HPTE be read-only */
ptel = hpte_make_readonly(ptel);
is_ci = pte_ci(pte);
pa = pte_pfn(pte) << PAGE_SHIFT;
pa |= hva & (host_pte_size - 1);
pa |= gpa & ~PAGE_MASK;
}
}
if (!realmode)
local_irq_restore(irq_flags);
ptel &= HPTE_R_KEY | HPTE_R_PP0 | (psize-1);
ptel |= pa;
if (pa)
pteh |= HPTE_V_VALID;
else {
pteh |= HPTE_V_ABSENT;
ptel &= ~(HPTE_R_KEY_HI | HPTE_R_KEY_LO);
}
/*If we had host pte mapping then Check WIMG */
if (ptep && !hpte_cache_flags_ok(ptel, is_ci)) {
if (is_ci)
return H_PARAMETER;
/*
* Allow guest to map emulated device memory as
* uncacheable, but actually make it cacheable.
*/
ptel &= ~(HPTE_R_W|HPTE_R_I|HPTE_R_G);
ptel |= HPTE_R_M;
}
/* Find and lock the HPTEG slot to use */
do_insert:
if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt))
return H_PARAMETER;
if (likely((flags & H_EXACT) == 0)) {
pte_index &= ~7UL;
hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
for (i = 0; i < 8; ++i) {
if ((be64_to_cpu(*hpte) & HPTE_V_VALID) == 0 &&
try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
HPTE_V_ABSENT))
break;
hpte += 2;
}
if (i == 8) {
/*
* Since try_lock_hpte doesn't retry (not even stdcx.
* failures), it could be that there is a free slot
* but we transiently failed to lock it. Try again,
* actually locking each slot and checking it.
*/
hpte -= 16;
for (i = 0; i < 8; ++i) {
u64 pte;
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
pte = be64_to_cpu(hpte[0]);
if (!(pte & (HPTE_V_VALID | HPTE_V_ABSENT)))
break;
__unlock_hpte(hpte, pte);
hpte += 2;
}
if (i == 8)
return H_PTEG_FULL;
}
pte_index += i;
} else {
hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4));
if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
HPTE_V_ABSENT)) {
/* Lock the slot and check again */
u64 pte;
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
pte = be64_to_cpu(hpte[0]);
if (pte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
__unlock_hpte(hpte, pte);
return H_PTEG_FULL;
}
}
}
/* Save away the guest's idea of the second HPTE dword */
rev = &kvm->arch.hpt.rev[pte_index];
if (realmode)
rev = real_vmalloc_addr(rev);
if (rev) {
rev->guest_rpte = g_ptel;
note_hpte_modification(kvm, rev);
}
/* Link HPTE into reverse-map chain */
if (pteh & HPTE_V_VALID) {
if (realmode)
rmap = real_vmalloc_addr(rmap);
lock_rmap(rmap);
/* Check for pending invalidations under the rmap chain lock */
if (mmu_notifier_retry(kvm, mmu_seq)) {
/* inval in progress, write a non-present HPTE */
pteh |= HPTE_V_ABSENT;
pteh &= ~HPTE_V_VALID;
ptel &= ~(HPTE_R_KEY_HI | HPTE_R_KEY_LO);
unlock_rmap(rmap);
} else {
kvmppc_add_revmap_chain(kvm, rev, rmap, pte_index,
realmode);
/* Only set R/C in real HPTE if already set in *rmap */
rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
ptel &= rcbits | ~(HPTE_R_R | HPTE_R_C);
}
}
/* 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 */
eieio();
__unlock_hpte(hpte, pteh);
asm volatile("ptesync" : : : "memory");
*pte_idx_ret = pte_index;
return H_SUCCESS;
}
