void __init page_table_range_init(unsigned long start, unsigned long end,
pgd_t *pgd_base)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
int pgd_idx;
unsigned long vaddr;
vaddr = start & PMD_MASK;
end = (end + PMD_SIZE - 1) & PMD_MASK;
pgd_idx = pgd_index(vaddr);
pgd = pgd_base + pgd_idx;
for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) {
BUG_ON(pgd_none(*pgd));
pud = pud_offset(pgd, 0);
BUG_ON(pud_none(*pud));
pmd = pmd_offset(pud, 0);
if (!pmd_present(*pmd)) {
pte_t *pte_table;
pte_table = (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
memset(pte_table, 0, PAGE_SIZE);
pmd_populate_kernel(&init_mm, pmd, pte_table);
}
vaddr += PMD_SIZE;
}
}
/**
* kvm_mips_walk_pgd() - Walk page table with optional allocation.
* @pgd: Page directory pointer.
* @addr: Address to index page table using.
* @cache: MMU page cache to allocate new page tables from, or NULL.
*
* Walk the page tables pointed to by @pgd to find the PTE corresponding to the
* address @addr. If page tables don't exist for @addr, they will be created
* from the MMU cache if @cache is not NULL.
*
* Returns: Pointer to pte_t corresponding to @addr.
* NULL if a page table doesn't exist for @addr and !@cache.
* NULL if a page table allocation failed.
*/
static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache,
unsigned long addr)
{
pud_t *pud;
pmd_t *pmd;
pgd += pgd_index(addr);
if (pgd_none(*pgd)) {
/* Not used on MIPS yet */
BUG();
return NULL;
}
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
pmd_t *new_pmd;
if (!cache)
return NULL;
new_pmd = mmu_memory_cache_alloc(cache);
pmd_init((unsigned long)new_pmd,
(unsigned long)invalid_pte_table);
pud_populate(NULL, pud, new_pmd);
}
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
pte_t *new_pte;
if (!cache)
return NULL;
new_pte = mmu_memory_cache_alloc(cache);
clear_page(new_pte);
pmd_populate_kernel(NULL, pmd, new_pte);
}
return pte_offset(pmd, addr);
}
static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start,
unsigned long end, unsigned long pfn,
pgprot_t prot)
{
pmd_t *pmd;
pte_t *pte;
unsigned long addr, next;
addr = start;
do {
pmd = pmd_offset(pud, addr);
BUG_ON(pmd_sect(*pmd));
if (pmd_none(*pmd)) {
pte = pte_alloc_one_kernel(NULL, addr);
if (!pte) {
kvm_err("Cannot allocate Hyp pte\n");
return -ENOMEM;
}
pmd_populate_kernel(NULL, pmd, pte);
get_page(virt_to_page(pmd));
kvm_flush_dcache_to_poc(pmd, sizeof(*pmd));
}
next = pmd_addr_end(addr, end);
create_hyp_pte_mappings(pmd, addr, next, pfn, prot);
pfn += (next - addr) >> PAGE_SHIFT;
} while (addr = next, addr != end);
return 0;
}
static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
unsigned long end, int nid)
{
pte_t *pte;
if (pmd_none(*pmd)) {
void *p;
if (boot_cpu_has(X86_FEATURE_PSE) &&
((end - addr) == PMD_SIZE) &&
IS_ALIGNED(addr, PMD_SIZE)) {
p = early_alloc(PMD_SIZE, nid, false);
if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
return;
else if (p)
memblock_free(__pa(p), PMD_SIZE);
}
p = early_alloc(PAGE_SIZE, nid, true);
pmd_populate_kernel(&init_mm, pmd, p);
}
pte = pte_offset_kernel(pmd, addr);
do {
pte_t entry;
void *p;
if (!pte_none(*pte))
continue;
p = early_alloc(PAGE_SIZE, nid, true);
entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
set_pte_at(&init_mm, addr, pte, entry);
} while (pte++, addr += PAGE_SIZE, addr != end);
}
static pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va)
{
if (pmd_none(*pmdp)) {
pte_t *ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
pmd_populate_kernel(&init_mm, pmdp, ptep);
}
return pte_offset_kernel(pmdp, va);
}
static void __init zero_pmd_populate(pud_t *pud, unsigned long addr,
unsigned long end)
{
pmd_t *pmd = pmd_offset(pud, addr);
unsigned long next;
do {
next = pmd_addr_end(addr, end);
if (IS_ALIGNED(addr, PMD_SIZE) && end - addr >= PMD_SIZE) {
pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
continue;
}
if (pmd_none(*pmd)) {
pmd_populate_kernel(&init_mm, pmd,
early_alloc(PAGE_SIZE, NUMA_NO_NODE));
}
zero_pte_populate(pmd, addr, next);
} while (pmd++, addr = next, 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,
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 pte_t * __init one_page_table_init(pmd_t *pmd)
{
if (pmd_none(*pmd)) {
pte_t *pte;
pte = alloc_bootmem_pages(PAGE_SIZE);
pmd_populate_kernel(&init_mm, pmd, pte);
BUG_ON(pte != pte_offset_kernel(pmd, 0));
}
return pte_offset_kernel(pmd, 0);
}
static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
{
pgd_t *pgd_k;
pud_t *pud_k;
pmd_t *pmd_k;
pte_t *pte_k;
pgd_k = pgd_offset_k(kvaddr);
pud_k = pud_offset(pgd_k, kvaddr);
pmd_k = pmd_offset(pud_k, kvaddr);
pte_k = (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
pmd_populate_kernel(&init_mm, pmd_k, pte_k);
return pte_k;
}
static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr,
unsigned long end)
{
pte_t *pte;
unsigned long next;
if (pmd_none(*pmd))
pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
pte = pte_offset_kimg(pmd, addr);
do {
next = addr + PAGE_SIZE;
set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page),
PAGE_KERNEL));
} while (pte++, addr = next, addr != end && pte_none(*pte));
}
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 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 int early_map_kernel_page(unsigned long ea, unsigned long pa,
pgprot_t flags,
unsigned int map_page_size,
int nid,
unsigned long region_start, unsigned long region_end)
{
unsigned long pfn = pa >> PAGE_SHIFT;
pgd_t *pgdp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
pgdp = pgd_offset_k(ea);
if (pgd_none(*pgdp)) {
pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid,
region_start, region_end);
pgd_populate(&init_mm, pgdp, pudp);
}
pudp = pud_offset(pgdp, ea);
if (map_page_size == PUD_SIZE) {
ptep = (pte_t *)pudp;
goto set_the_pte;
}
if (pud_none(*pudp)) {
pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid,
region_start, region_end);
pud_populate(&init_mm, pudp, pmdp);
}
pmdp = pmd_offset(pudp, ea);
if (map_page_size == PMD_SIZE) {
ptep = pmdp_ptep(pmdp);
goto set_the_pte;
}
if (!pmd_present(*pmdp)) {
ptep = early_alloc_pgtable(PAGE_SIZE, nid,
region_start, region_end);
pmd_populate_kernel(&init_mm, pmdp, ptep);
}
ptep = pte_offset_kernel(pmdp, ea);
set_the_pte:
set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
smp_wmb();
return 0;
}
/*
* map_kernel_page currently only called by __ioremap
* map_kernel_page adds an entry to the ioremap page table
* and adds an entry to the HPT, possibly bolting it
*/
int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
{
pgd_t *pgdp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
BUILD_BUG_ON(TASK_SIZE_USER64 > PGTABLE_RANGE);
if (slab_is_available()) {
pgdp = pgd_offset_k(ea);
pudp = pud_alloc(&init_mm, pgdp, ea);
if (!pudp)
return -ENOMEM;
pmdp = pmd_alloc(&init_mm, pudp, ea);
if (!pmdp)
return -ENOMEM;
ptep = pte_alloc_kernel(pmdp, ea);
if (!ptep)
return -ENOMEM;
} else {
pgdp = pgd_offset_k(ea);
#ifndef __PAGETABLE_PUD_FOLDED
if (pgd_none(*pgdp)) {
pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
pgd_populate(&init_mm, pgdp, pudp);
}
#endif /* !__PAGETABLE_PUD_FOLDED */
pudp = pud_offset(pgdp, ea);
if (pud_none(*pudp)) {
pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
pud_populate(&init_mm, pudp, pmdp);
}
pmdp = pmd_offset(pudp, ea);
if (!pmd_present(*pmdp)) {
ptep = early_alloc_pgtable(PAGE_SIZE);
pmd_populate_kernel(&init_mm, pmdp, ptep);
}
ptep = pte_offset_kernel(pmdp, ea);
}
set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, prot));
smp_wmb();
return 0;
}
static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
unsigned long end)
{
pte_t *src_ptep;
pte_t *dst_ptep;
unsigned long addr = start;
dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
if (!dst_ptep)
return -ENOMEM;
pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
dst_ptep = pte_offset_kernel(dst_pmdp, start);
src_ptep = pte_offset_kernel(src_pmdp, start);
do {
_copy_pte(dst_ptep, src_ptep, addr);
} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
return 0;
}
/**
* kasan_populate_zero_shadow - populate shadow memory region with
* kasan_zero_page
* @shadow_start - start of the memory range to populate
* @shadow_end - end of the memory range to populate
*/
void __init kasan_populate_zero_shadow(const void *shadow_start,
const void *shadow_end)
{
unsigned long addr = (unsigned long)shadow_start;
unsigned long end = (unsigned long)shadow_end;
pgd_t *pgd = pgd_offset_k(addr);
unsigned long next;
do {
next = pgd_addr_end(addr, end);
if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) {
pud_t *pud;
pmd_t *pmd;
/*
* kasan_zero_pud should be populated with pmds
* at this moment.
* [pud,pmd]_populate*() below needed only for
* 3,2 - level page tables where we don't have
* puds,pmds, so pgd_populate(), pud_populate()
* is noops.
*/
pgd_populate(&init_mm, pgd, kasan_zero_pud);
pud = pud_offset(pgd, addr);
pud_populate(&init_mm, pud, kasan_zero_pmd);
pmd = pmd_offset(pud, addr);
pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
continue;
}
if (pgd_none(*pgd)) {
pgd_populate(&init_mm, pgd,
early_alloc(PAGE_SIZE, NUMA_NO_NODE));
}
zero_pud_populate(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
/*
* Copies length bytes, starting at src_start into an new page,
* perform cache maintentance, then maps it at the specified address low
* address as executable.
*
* This is used by hibernate to copy the code it needs to execute when
* overwriting the kernel text. This function generates a new set of page
* tables, which it loads into ttbr0.
*
* Length is provided as we probably only want 4K of data, even on a 64K
* page system.
*/
static int create_safe_exec_page(void *src_start, size_t length,
unsigned long dst_addr,
phys_addr_t *phys_dst_addr,
void *(*allocator)(gfp_t mask),
gfp_t mask)
{
int rc = 0;
pgd_t *pgdp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
unsigned long dst = (unsigned long)allocator(mask);
if (!dst) {
rc = -ENOMEM;
goto out;
}
memcpy((void *)dst, src_start, length);
flush_icache_range(dst, dst + length);
pgdp = pgd_offset_raw(allocator(mask), dst_addr);
if (pgd_none(READ_ONCE(*pgdp))) {
pudp = allocator(mask);
if (!pudp) {
rc = -ENOMEM;
goto out;
}
pgd_populate(&init_mm, pgdp, pudp);
}
pudp = pud_offset(pgdp, dst_addr);
if (pud_none(READ_ONCE(*pudp))) {
pmdp = allocator(mask);
if (!pmdp) {
rc = -ENOMEM;
goto out;
}
pud_populate(&init_mm, pudp, pmdp);
}
pmdp = pmd_offset(pudp, dst_addr);
if (pmd_none(READ_ONCE(*pmdp))) {
ptep = allocator(mask);
if (!ptep) {
rc = -ENOMEM;
goto out;
}
pmd_populate_kernel(&init_mm, pmdp, ptep);
}
ptep = pte_offset_kernel(pmdp, dst_addr);
set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
/*
* Load our new page tables. A strict BBM approach requires that we
* ensure that TLBs are free of any entries that may overlap with the
* global mappings we are about to install.
*
* For a real hibernate/resume cycle TTBR0 currently points to a zero
* page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI
* runtime services), while for a userspace-driven test_resume cycle it
* points to userspace page tables (and we must point it at a zero page
* ourselves). Elsewhere we only (un)install the idmap with preemption
* disabled, so T0SZ should be as required regardless.
*/
cpu_set_reserved_ttbr0();
local_flush_tlb_all();
write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1);
isb();
*phys_dst_addr = virt_to_phys((void *)dst);
out:
return rc;
}
