static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
unsigned long long start, u64 size)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long long addr = start, end = start + size;
u64 next;
while (addr < end) {
pgd = pgdp + pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
addr = pud_addr_end(addr, end);
continue;
}
if (pud_huge(*pud)) {
/*
* If we are dealing with a huge pud, just clear it and
* move on.
*/
clear_pud_entry(kvm, pud, addr);
addr = pud_addr_end(addr, end);
continue;
}
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
addr = pmd_addr_end(addr, end);
continue;
}
if (!kvm_pmd_huge(*pmd)) {
pte = pte_offset_kernel(pmd, addr);
clear_pte_entry(kvm, pte, addr);
next = addr + PAGE_SIZE;
}
/*
* If the pmd entry is to be cleared, walk back up the ladder
*/
if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
clear_pmd_entry(kvm, pmd, addr);
next = pmd_addr_end(addr, end);
if (page_empty(pmd) && !page_empty(pud)) {
clear_pud_entry(kvm, pud, addr);
next = pud_addr_end(addr, end);
}
}
addr = next;
}
}
static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
phys_addr -= addr;
pud = pud_alloc(&init_mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (ioremap_pud_enabled() &&
((next - addr) == PUD_SIZE) &&
IS_ALIGNED(phys_addr + addr, PUD_SIZE)) {
if (pud_set_huge(pud, phys_addr + addr, prot))
continue;
}
if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start,
unsigned long end, unsigned long pfn,
pgprot_t prot)
{
pud_t *pud;
pmd_t *pmd;
unsigned long addr, next;
int ret;
addr = start;
do {
pud = pud_offset(pgd, addr);
if (pud_none_or_clear_bad(pud)) {
pmd = pmd_alloc_one(NULL, addr);
if (!pmd) {
kvm_err("Cannot allocate Hyp pmd\n");
return -ENOMEM;
}
pud_populate(NULL, pud, pmd);
get_page(virt_to_page(pud));
kvm_flush_dcache_to_poc(pud, sizeof(*pud));
}
next = pud_addr_end(addr, end);
ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
if (ret)
return ret;
pfn += (next - addr) >> PAGE_SHIFT;
} while (addr = next, addr != end);
return 0;
}
static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pud_t *pud;
unsigned long next;
int err = 0;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud)) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
if (walk->pud_entry)
err = walk->pud_entry(pud, addr, next, walk);
if (!err && (walk->pmd_entry || walk->pte_entry))
err = walk_pmd_range(pud, addr, next, walk);
if (err)
break;
} while (pud++, addr = next, addr != end);
return err;
}
static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
pudp = pud_offset(&pgd, addr);
do {
pud_t pud = READ_ONCE(*pudp);
next = pud_addr_end(addr, end);
if (pud_none(pud))
return 0;
if (pud_huge(pud)) {
if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next,
write, pages, nr))
return 0;
} else if (is_hugepd(pudp)) {
if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT,
addr, next, write, pages, nr))
return 0;
} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
return 1;
}
static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
unsigned long end)
{
pud_t *dst_pudp;
pud_t *src_pudp;
unsigned long next;
unsigned long addr = start;
if (pgd_none(READ_ONCE(*dst_pgdp))) {
dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
if (!dst_pudp)
return -ENOMEM;
pgd_populate(&init_mm, dst_pgdp, dst_pudp);
}
dst_pudp = pud_offset(dst_pgdp, start);
src_pudp = pud_offset(src_pgdp, start);
do {
pud_t pud = READ_ONCE(*src_pudp);
next = pud_addr_end(addr, end);
if (pud_none(pud))
continue;
if (pud_table(pud)) {
if (copy_pmd(dst_pudp, src_pudp, addr, next))
return -ENOMEM;
} else {
set_pud(dst_pudp,
__pud(pud_val(pud) & ~PMD_SECT_RDONLY));
}
} while (dst_pudp++, src_pudp++, addr = next, addr != end);
return 0;
}
static void idmap_del_pud(pgd_t *pgd, unsigned long addr, unsigned long end)
{
pud_t *pud = pud_offset(pgd, addr);
unsigned long next;
do {
next = pud_addr_end(addr, end);
idmap_del_pmd(pud, addr, next);
} while (pud++, addr = next, addr != end);
}
static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr,
unsigned long end, int node, bool early)
{
unsigned long next;
pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early);
do {
next = pud_addr_end(addr, end);
kasan_pmd_populate(pudp, addr, next, node, early);
} while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp)));
}
static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
unsigned long long start, u64 size)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long long addr = start, end = start + size;
u64 next;
while (addr < end) {
pgd = pgdp + pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
addr = pud_addr_end(addr, end);
continue;
}
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
addr = pmd_addr_end(addr, end);
continue;
}
pte = pte_offset_kernel(pmd, addr);
clear_pte_entry(kvm, pte, addr);
next = addr + PAGE_SIZE;
/* If we emptied the pte, walk back up the ladder */
if (page_empty(pte)) {
clear_pmd_entry(kvm, pmd, addr);
next = pmd_addr_end(addr, end);
if (page_empty(pmd) && !page_empty(pud)) {
clear_pud_entry(kvm, pud, addr);
next = pud_addr_end(addr, end);
}
}
addr = next;
}
}
static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
vunmap_pmd_range(pud, addr, next);
} while (pud++, addr = next, addr != end);
}
static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void))
{
pud_t *pud;
unsigned long next;
if (pgd_none(*pgd)) {
phys_addr_t pud_phys;
BUG_ON(!pgtable_alloc);
pud_phys = pgtable_alloc();
__pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE);
}
BUG_ON(pgd_bad(*pgd));
pud = pud_set_fixmap_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
/*
* For 4K granule only, attempt to put down a 1GB block
*/
if (use_1G_block(addr, next, phys) &&
block_mappings_allowed(pgtable_alloc)) {
pud_t old_pud = *pud;
pud_set_huge(pud, phys, prot);
/*
* If we have an old value for a pud, it will
* be pointing to a pmd table that we no longer
* need (from swapper_pg_dir).
*
* Look up the old pmd table and free it.
*/
if (!pud_none(old_pud)) {
flush_tlb_all();
if (pud_table(old_pud)) {
phys_addr_t table = pud_page_paddr(old_pud);
if (!WARN_ON_ONCE(slab_is_available()))
memblock_free(table, PAGE_SIZE);
}
}
} else {
alloc_init_pmd(pud, addr, next, phys, prot,
pgtable_alloc);
}
phys += next - addr;
} while (pud++, addr = next, addr != end);
pud_clear_fixmap();
}
static inline unsigned long msync_pud_range(struct vm_area_struct *vma,
pgd_t *pgd, unsigned long addr, unsigned long end)
{
pud_t *pud;
unsigned long next;
unsigned long ret = 0;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
ret += msync_pmd_range(vma, pud, addr, next);
} while (pud++, addr = next, addr != end);
return ret;
}
static unsigned long clear_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none(*pud))
continue;
next = clear_pmd_range(vma, pud, addr, next);
} while (pud++, addr = next, addr != end);
return addr;
}
static void __init kasan_early_pud_populate(pgd_t *pgd,
unsigned long addr,
unsigned long end)
{
pud_t *pud;
unsigned long next;
if (pgd_none(*pgd))
pgd_populate(&init_mm, pgd, kasan_zero_pud);
pud = pud_offset_kimg(pgd, addr);
do {
next = pud_addr_end(addr, end);
kasan_early_pmd_populate(pud, addr, next);
} while (pud++, addr = next, addr != end && pud_none(*pud));
}
static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pud_t *pud;
unsigned long next;
pud = pud_alloc(&init_mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (vmap_pmd_range(pud, addr, next, prot, pages, nr))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
static void __init kasan_early_pud_populate(pgd_t *pgd,
unsigned long addr,
unsigned long end)
{
pud_t *pud;
unsigned long next;
if (pgd_none(*pgd))
__pgd_populate(pgd, __pa_symbol(kasan_zero_pud), PUD_TYPE_TABLE);
pud = pud_offset_kimg(pgd, addr);
do {
next = pud_addr_end(addr, end);
kasan_early_pmd_populate(pud, addr, next);
} while (pud++, addr = next, addr != end && pud_none(*pud));
}
static inline int check_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end, unsigned long *nodes)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
if (check_pmd_range(mm, pud, addr, next, nodes))
return -EIO;
} while (pud++, addr = next, addr != end);
return 0;
}
static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
void *(*alloc)(unsigned long size))
{
pud_t *pud;
unsigned long next;
if (pgd_none(*pgd)) {
pud = alloc(PTRS_PER_PUD * sizeof(pud_t));
pgd_populate(mm, pgd, pud);
}
BUG_ON(pgd_bad(*pgd));
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
/*
* For 4K granule only, attempt to put down a 1GB block
*/
if (use_1G_block(addr, next, phys)) {
pud_t old_pud = *pud;
set_pud(pud, __pud(phys |
pgprot_val(mk_sect_prot(prot))));
/*
* If we have an old value for a pud, it will
* be pointing to a pmd table that we no longer
* need (from swapper_pg_dir).
*
* Look up the old pmd table and free it.
*/
if (!pud_none(old_pud)) {
flush_tlb_all();
if (pud_table(old_pud)) {
phys_addr_t table = __pa(pmd_offset(&old_pud, 0));
if (!WARN_ON_ONCE(slab_is_available()))
memblock_free(table, PAGE_SIZE);
}
}
} else {
alloc_init_pmd(mm, pud, addr, next, phys, prot, alloc);
}
phys += next - addr;
} while (pud++, addr = next, addr != end);
}
static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
unsigned long end, unsigned long phys_addr, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
phys_addr -= addr;
pud = pud_alloc(&init_mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
if (unuse_pmd_range(vma, pud, addr, next, entry, page))
return 1;
} while (pud++, addr = next, addr != end);
return 0;
}
static void mincore_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned char *vec)
{
unsigned long next;
pud_t *pud;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
mincore_unmapped_range(vma, addr, next, vec);
else
mincore_pmd_range(vma, pud, addr, next, vec);
vec += (next - addr) >> PAGE_SHIFT;
} while (pud++, addr = next, addr != end);
}
static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
pudp = pud_offset(&pgd, addr);
do {
pud_t pud = *pudp;
next = pud_addr_end(addr, end);
if (pud_none(pud))
return 0;
if (!gup_pmd_range(pud, addr, next, write, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
return 1;
}
static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
unsigned long end, int nid)
{
pud_t *pud;
unsigned long next;
if (p4d_none(*p4d)) {
void *p = early_alloc(PAGE_SIZE, nid, true);
p4d_populate(&init_mm, p4d, p);
}
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (!pud_large(*pud))
kasan_populate_pud(pud, addr, next, nid);
} while (pud++, addr = next, addr != end);
}
static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pud_t *pud;
unsigned long next;
int err = 0;
pud = pud_offset(p4d, addr);
do {
again:
next = pud_addr_end(addr, end);
if (pud_none(*pud) || !walk->vma) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
if (walk->pud_entry) {
spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
if (ptl) {
err = walk->pud_entry(pud, addr, next, walk);
spin_unlock(ptl);
if (err)
break;
continue;
}
}
split_huge_pud(walk->vma, pud, addr);
if (pud_none(*pud))
goto again;
if (walk->pmd_entry || walk->pte_entry)
err = walk_pmd_range(pud, addr, next, walk);
if (err)
break;
} while (pud++, addr = next, addr != end);
return err;
}
static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
unsigned long end)
{
pud_t *pud = pud_offset(pgd, addr);
unsigned long next;
do {
next = pud_addr_end(addr, end);
if (IS_ALIGNED(addr, PUD_SIZE) && end - addr >= PUD_SIZE) {
pmd_t *pmd;
pud_populate(&init_mm, pud, kasan_zero_pmd);
pmd = pmd_offset(pud, addr);
pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
continue;
}
if (pud_none(*pud)) {
pud_populate(&init_mm, pud,
early_alloc(PAGE_SIZE, NUMA_NO_NODE));
}
zero_pmd_populate(pud, addr, next);
} while (pud++, addr = next, addr != end);
}
/*
(Yet another) pagetable walker. This one is intended for pinning a
pagetable. This means that it walks a pagetable and calls the
callback function on each page it finds making up the page table,
at every level. It walks the entire pagetable, but it only bothers
pinning pte pages which are below pte_limit. In the normal case
this will be TASK_SIZE, but at boot we need to pin up to
FIXADDR_TOP. But the important bit is that we don't pin beyond
there, because then we start getting into Xen's ptes.
*/
static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, unsigned),
unsigned long limit)
{
pgd_t *pgd = pgd_base;
int flush = 0;
unsigned long addr = 0;
unsigned long pgd_next;
BUG_ON(limit > FIXADDR_TOP);
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
for (; addr != FIXADDR_TOP; pgd++, addr = pgd_next) {
pud_t *pud;
unsigned long pud_limit, pud_next;
pgd_next = pud_limit = pgd_addr_end(addr, FIXADDR_TOP);
if (!pgd_val(*pgd))
continue;
pud = pud_offset(pgd, 0);
if (PTRS_PER_PUD > 1) /* not folded */
flush |= (*func)(virt_to_page(pud), 0);
for (; addr != pud_limit; pud++, addr = pud_next) {
pmd_t *pmd;
unsigned long pmd_limit;
pud_next = pud_addr_end(addr, pud_limit);
if (pud_next < limit)
pmd_limit = pud_next;
else
pmd_limit = limit;
if (pud_none(*pud))
continue;
pmd = pmd_offset(pud, 0);
if (PTRS_PER_PMD > 1) /* not folded */
flush |= (*func)(virt_to_page(pmd), 0);
for (; addr != pmd_limit; pmd++) {
addr += (PAGE_SIZE * PTRS_PER_PTE);
if ((pmd_limit-1) < (addr-1)) {
addr = pmd_limit;
break;
}
if (pmd_none(*pmd))
continue;
flush |= (*func)(pmd_page(*pmd), 0);
}
}
}
flush |= (*func)(virt_to_page(pgd_base), UVMF_TLB_FLUSH);
return flush;
}