/*
* Unmapping vs dcache management:
*
* If a guest maps certain memory pages as uncached, all writes will
* bypass the data cache and go directly to RAM. However, the CPUs
* can still speculate reads (not writes) and fill cache lines with
* data.
*
* Those cache lines will be *clean* cache lines though, so a
* clean+invalidate operation is equivalent to an invalidate
* operation, because no cache lines are marked dirty.
*
* Those clean cache lines could be filled prior to an uncached write
* by the guest, and the cache coherent IO subsystem would therefore
* end up writing old data to disk.
*
* This is why right after unmapping a page/section and invalidating
* the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
* the IO subsystem will never hit in the cache.
*/
static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
phys_addr_t start_addr = addr;
pte_t *pte, *start_pte;
start_pte = pte = pte_offset_kernel(pmd, addr);
do {
if (!pte_none(*pte)) {
pte_t old_pte = *pte;
kvm_set_pte(pte, __pte(0));
kvm_tlb_flush_vmid_ipa(kvm, addr);
/* No need to invalidate the cache for device mappings */
if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
kvm_flush_dcache_pte(old_pte);
put_page(virt_to_page(pte));
}
} while (pte++, addr += PAGE_SIZE, addr != end);
if (kvm_pte_table_empty(kvm, start_pte))
clear_pmd_entry(kvm, pmd, start_addr);
}
static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte, bool iomap)
{
pmd_t *pmd;
pte_t *pte, old_pte;
/* Create stage-2 page table mapping - Levels 0 and 1 */
pmd = stage2_get_pmd(kvm, cache, addr);
if (!pmd) {
/*
* Ignore calls from kvm_set_spte_hva for unallocated
* address ranges.
*/
return 0;
}
/* Create stage-2 page mappings - Level 2 */
if (pmd_none(*pmd)) {
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
pte = mmu_memory_cache_alloc(cache);
kvm_clean_pte(pte);
pmd_populate_kernel(NULL, pmd, pte);
get_page(virt_to_page(pmd));
}
pte = pte_offset_kernel(pmd, addr);
if (iomap && pte_present(*pte))
return -EFAULT;
/* Create 2nd stage page table mapping - Level 3 */
old_pte = *pte;
if (pte_present(old_pte)) {
/* Skip page table update if there is no change */
if (pte_val(old_pte) == pte_val(*new_pte))
return 0;
kvm_set_pte(pte, __pte(0));
kvm_tlb_flush_vmid_ipa(kvm, addr);
} else {
get_page(virt_to_page(pte));
}
kvm_set_pte(pte, *new_pte);
return 0;
}
static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
{
if (pte_present(*pte)) {
kvm_set_pte(pte, __pte(0));
put_page(virt_to_page(pte));
kvm_tlb_flush_vmid_ipa(kvm, addr);
}
}
static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte,
unsigned long flags)
{
pmd_t *pmd;
pte_t *pte, old_pte;
bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP;
bool logging_active = flags & KVM_S2_FLAG_LOGGING_ACTIVE;
VM_BUG_ON(logging_active && !cache);
/* Create stage-2 page table mapping - Levels 0 and 1 */
pmd = stage2_get_pmd(kvm, cache, addr);
if (!pmd) {
/*
* Ignore calls from kvm_set_spte_hva for unallocated
* address ranges.
*/
return 0;
}
/*
* While dirty page logging - dissolve huge PMD, then continue on to
* allocate page.
*/
if (logging_active)
stage2_dissolve_pmd(kvm, addr, pmd);
/* Create stage-2 page mappings - Level 2 */
if (pmd_none(*pmd)) {
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
pte = mmu_memory_cache_alloc(cache);
kvm_clean_pte(pte);
pmd_populate_kernel(NULL, pmd, pte);
get_page(virt_to_page(pmd));
}
pte = pte_offset_kernel(pmd, addr);
if (iomap && pte_present(*pte))
return -EFAULT;
/* Create 2nd stage page table mapping - Level 3 */
old_pte = *pte;
kvm_set_pte(pte, *new_pte);
if (pte_present(old_pte))
kvm_tlb_flush_vmid_ipa(kvm, addr);
else
get_page(virt_to_page(pte));
return 0;
}
static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start,
unsigned long end, unsigned long pfn,
pgprot_t prot)
{
pte_t *pte;
unsigned long addr;
addr = start;
do {
pte = pte_offset_kernel(pmd, addr);
kvm_set_pte(pte, pfn_pte(pfn, prot));
get_page(virt_to_page(pte));
kvm_flush_dcache_to_poc(pte, sizeof(*pte));
pfn++;
} while (addr += PAGE_SIZE, addr != end);
}
static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte, bool iomap)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte, old_pte;
/* Create 2nd stage page table mapping - Level 1 */
pgd = kvm->arch.pgd + pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
pmd = mmu_memory_cache_alloc(cache);
pud_populate(NULL, pud, pmd);
get_page(virt_to_page(pud));
}
pmd = pmd_offset(pud, addr);
/* Create 2nd stage page table mapping - Level 2 */
if (pmd_none(*pmd)) {
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
pte = mmu_memory_cache_alloc(cache);
kvm_clean_pte(pte);
pmd_populate_kernel(NULL, pmd, pte);
get_page(virt_to_page(pmd));
}
pte = pte_offset_kernel(pmd, addr);
if (iomap && pte_present(*pte))
return -EFAULT;
/* Create 2nd stage page table mapping - Level 3 */
old_pte = *pte;
kvm_set_pte(pte, *new_pte);
if (pte_present(old_pte))
kvm_tlb_flush_vmid_ipa(kvm, addr);
else
get_page(virt_to_page(pte));
return 0;
}
static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
phys_addr_t start_addr = addr;
pte_t *pte, *start_pte;
start_pte = pte = pte_offset_kernel(pmd, addr);
do {
if (!pte_none(*pte)) {
kvm_set_pte(pte, __pte(0));
put_page(virt_to_page(pte));
kvm_tlb_flush_vmid_ipa(kvm, addr);
}
} while (pte++, addr += PAGE_SIZE, addr != end);
if (kvm_pte_table_empty(kvm, start_pte))
clear_pmd_entry(kvm, pmd, start_addr);
}