/*
* We need our own copy of the higher levels of the page tables
* because we want to avoid inserting EFI region mappings (EFI_VA_END
* to EFI_VA_START) into the standard kernel page tables. Everything
* else can be shared, see efi_sync_low_kernel_mappings().
*/
int __init efi_alloc_page_tables(void)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
gfp_t gfp_mask;
if (efi_enabled(EFI_OLD_MEMMAP))
return 0;
gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
if (!efi_pgd)
return -ENOMEM;
pgd = efi_pgd + pgd_index(EFI_VA_END);
p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
if (!p4d) {
free_page((unsigned long)efi_pgd);
return -ENOMEM;
}
pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
if (!pud) {
if (CONFIG_PGTABLE_LEVELS > 4)
free_page((unsigned long) pgd_page_vaddr(*pgd));
free_page((unsigned long)efi_pgd);
return -ENOMEM;
}
return 0;
}
static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
p4d_t *p4d;
unsigned long next;
phys_addr -= addr;
p4d = p4d_alloc(&init_mm, pgd, addr);
if (!p4d)
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
if (ioremap_p4d_enabled() &&
((next - addr) == P4D_SIZE) &&
IS_ALIGNED(phys_addr + addr, P4D_SIZE)) {
if (p4d_set_huge(p4d, phys_addr + addr, prot))
continue;
}
if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot))
return -ENOMEM;
} while (p4d++, addr = next, addr != end);
return 0;
}
static pteval_t *get_pte(pgd_t *pgtable, uintptr_t vaddr)
{
pgd_t *pgd = pgd_offset(pgtable, vaddr);
p4d_t *p4d = p4d_alloc(pgd, vaddr);
pud_t *pud = pud_alloc(p4d, vaddr);
pmd_t *pmd = pmd_alloc(pud, vaddr);
pte_t *pte = pte_alloc(pmd, vaddr);
return &pte_val(*pte);
}
static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pgd = pgd_offset(mm, address);
p4d = p4d_alloc(mm, pgd, address);
if (!p4d)
return NULL;
pud = pud_alloc(mm, p4d, address);
if (!pud)
return NULL;
/*
* Note that we didn't run this because the pmd was
* missing, the *pmd may be already established and in
* turn it may also be a trans_huge_pmd.
*/
return pmd_alloc(mm, pud, address);
}
/*
* We need our own copy of the higher levels of the page tables
* because we want to avoid inserting EFI region mappings (EFI_VA_END
* to EFI_VA_START) into the standard kernel page tables. Everything
* else can be shared, see efi_sync_low_kernel_mappings().
*
* We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the
* allocation.
*/
int __init efi_alloc_page_tables(void)
{
pgd_t *pgd, *efi_pgd;
p4d_t *p4d;
pud_t *pud;
gfp_t gfp_mask;
if (efi_enabled(EFI_OLD_MEMMAP))
return 0;
gfp_mask = GFP_KERNEL | __GFP_ZERO;
efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
if (!efi_pgd)
return -ENOMEM;
pgd = efi_pgd + pgd_index(EFI_VA_END);
p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
if (!p4d) {
free_page((unsigned long)efi_pgd);
return -ENOMEM;
}
pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
if (!pud) {
if (pgtable_l5_enabled)
free_page((unsigned long) pgd_page_vaddr(*pgd));
free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
return -ENOMEM;
}
efi_mm.pgd = efi_pgd;
mm_init_cpumask(&efi_mm);
init_new_context(NULL, &efi_mm);
return 0;
}
pgd_t * __init efi_call_phys_prolog(void)
{
unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
pgd_t *save_pgd, *pgd_k, *pgd_efi;
p4d_t *p4d, *p4d_k, *p4d_efi;
pud_t *pud;
int pgd;
int n_pgds, i, j;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
save_pgd = (pgd_t *)__read_cr3();
write_cr3((unsigned long)efi_scratch.efi_pgt);
goto out;
}
early_code_mapping_set_exec(1);
n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
/*
* Build 1:1 identity mapping for efi=old_map usage. Note that
* PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
* it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
* address X, the pud_index(X) != pud_index(__va(X)), we can only copy
* PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
* This means here we can only reuse the PMD tables of the direct mapping.
*/
for (pgd = 0; pgd < n_pgds; pgd++) {
addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
pgd_efi = pgd_offset_k(addr_pgd);
save_pgd[pgd] = *pgd_efi;
p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
if (!p4d) {
pr_err("Failed to allocate p4d table!\n");
goto out;
}
for (i = 0; i < PTRS_PER_P4D; i++) {
addr_p4d = addr_pgd + i * P4D_SIZE;
p4d_efi = p4d + p4d_index(addr_p4d);
pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
if (!pud) {
pr_err("Failed to allocate pud table!\n");
goto out;
}
for (j = 0; j < PTRS_PER_PUD; j++) {
addr_pud = addr_p4d + j * PUD_SIZE;
if (addr_pud > (max_pfn << PAGE_SHIFT))
break;
vaddr = (unsigned long)__va(addr_pud);
pgd_k = pgd_offset_k(vaddr);
p4d_k = p4d_offset(pgd_k, vaddr);
pud[j] = *pud_offset(p4d_k, vaddr);
}
}
}
out:
__flush_tlb_all();
return save_pgd;
}
