bool can_set_direct_map(void)
{ /* * rodata_full, DEBUG_PAGEALLOC and a Realm guest all require linear * map to be mapped at page granularity, so that it is possible to * protect/unprotect single pages. * * KFENCE pool requires page-granular mapping if initialized late. * * Realms need to make pages shared/protected at page granularity.
*/ return rodata_full || debug_pagealloc_enabled() ||
arm64_kfence_can_set_direct_map() || is_realm_world();
}
/* * This function assumes that the range is mapped with PAGE_SIZE pages.
*/ staticint __change_memory_common(unsignedlong start, unsignedlong size,
pgprot_t set_mask, pgprot_t clear_mask)
{ struct page_change_data data; int ret;
ret = apply_to_page_range(&init_mm, start, size, change_page_range,
&data);
/* * If the memory is being made valid without changing any other bits * then a TLBI isn't required as a non-valid entry cannot be cached in * the TLB.
*/ if (pgprot_val(set_mask) != PTE_VALID || pgprot_val(clear_mask))
flush_tlb_kernel_range(start, start + size); return ret;
}
if (!PAGE_ALIGNED(addr)) {
start &= PAGE_MASK;
end = start + size;
WARN_ON_ONCE(1);
}
/* * Kernel VA mappings are always live, and splitting live section * mappings into page mappings may cause TLB conflicts. This means * we have to ensure that changing the permission bits of the range * we are operating on does not result in such splitting. * * Let's restrict ourselves to mappings created by vmalloc (or vmap). * Disallow VM_ALLOW_HUGE_VMAP mappings to guarantee that only page * mappings are updated and splitting is never needed. * * So check whether the [addr, addr + size) interval is entirely * covered by precisely one VM area that has the VM_ALLOC flag set.
*/
area = find_vm_area((void *)addr); if (!area ||
end > (unsignedlong)kasan_reset_tag(area->addr) + area->size ||
((area->flags & (VM_ALLOC | VM_ALLOW_HUGE_VMAP)) != VM_ALLOC)) return -EINVAL;
if (!numpages) return 0;
/* * If we are manipulating read-only permissions, apply the same * change to the linear mapping of the pages that back this VM area.
*/ if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
pgprot_val(clear_mask) == PTE_RDONLY)) { for (i = 0; i < area->nr_pages; i++) {
__change_memory_common((u64)page_address(area->pages[i]),
PAGE_SIZE, set_mask, clear_mask);
}
}
/* * Get rid of potentially aliasing lazily unmapped vm areas that may * have permissions set that deviate from the ones we are setting here.
*/
vm_unmap_aliases();
staticint __set_memory_enc_dec(unsignedlong addr, int numpages, bool encrypt)
{ unsignedlong set_prot = 0, clear_prot = 0;
phys_addr_t start, end; int ret;
if (!is_realm_world()) return 0;
if (!__is_lm_address(addr)) return -EINVAL;
start = __virt_to_phys(addr);
end = start + numpages * PAGE_SIZE;
if (encrypt)
clear_prot = PROT_NS_SHARED; else
set_prot = PROT_NS_SHARED;
/* * Break the mapping before we make any changes to avoid stale TLB * entries or Synchronous External Aborts caused by RIPAS_EMPTY
*/
ret = __change_memory_common(addr, PAGE_SIZE * numpages,
__pgprot(set_prot),
__pgprot(clear_prot | PTE_VALID));
if (ret) return ret;
if (encrypt)
ret = rsi_set_memory_range_protected(start, end); else
ret = rsi_set_memory_range_shared(start, end);
staticint realm_set_memory_encrypted(unsignedlong addr, int numpages)
{ int ret = __set_memory_enc_dec(addr, numpages, true);
/* * If the request to change state fails, then the only sensible cause * of action for the caller is to leak the memory
*/
WARN(ret, "Failed to encrypt memory, %d pages will be leaked",
numpages);
return ret;
}
staticint realm_set_memory_decrypted(unsignedlong addr, int numpages)
{ int ret = __set_memory_enc_dec(addr, numpages, false);
WARN(ret, "Failed to decrypt memory, %d pages will be leaked",
numpages);
#ifdef CONFIG_DEBUG_PAGEALLOC /* * This is - apart from the return value - doing the same * thing as the new set_direct_map_valid_noflush() function. * * Unify? Explain the conceptual differences?
*/ void __kernel_map_pages(struct page *page, int numpages, int enable)
{ if (!can_set_direct_map()) return;
/* * This function is used to determine if a linear map page has been marked as * not-valid. Walk the page table and check the PTE_VALID bit. * * Because this is only called on the kernel linear map, p?d_sect() implies * p?d_present(). When debug_pagealloc is enabled, sections mappings are * disabled.
*/ bool kernel_page_present(struct page *page)
{
pgd_t *pgdp;
p4d_t *p4dp;
pud_t *pudp, pud;
pmd_t *pmdp, pmd;
pte_t *ptep; unsignedlong addr = (unsignedlong)page_address(page);
pgdp = pgd_offset_k(addr); if (pgd_none(READ_ONCE(*pgdp))) returnfalse;
p4dp = p4d_offset(pgdp, addr); if (p4d_none(READ_ONCE(*p4dp))) returnfalse;
pudp = pud_offset(p4dp, addr);
pud = READ_ONCE(*pudp); if (pud_none(pud)) returnfalse; if (pud_sect(pud)) returntrue;
pmdp = pmd_offset(pudp, addr);
pmd = READ_ONCE(*pmdp); if (pmd_none(pmd)) returnfalse; if (pmd_sect(pmd)) returntrue;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.