int flags);
#endif
+#define INVALID_PHYS_ADDR (-1ULL)
+
static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm,
enum pgtable_type pgtable_type)
{
struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL & ~__GFP_ZERO, 0);
phys_addr_t pa;
- BUG_ON(!ptdesc);
+ if (!ptdesc)
+ return INVALID_PHYS_ADDR;
+
pa = page_to_phys(ptdesc_page(ptdesc));
switch (pgtable_type) {
return pa;
}
+static phys_addr_t
+try_pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type)
+{
+ return __pgd_pgtable_alloc(&init_mm, pgtable_type);
+}
+
static phys_addr_t __maybe_unused
pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type)
{
- return __pgd_pgtable_alloc(&init_mm, pgtable_type);
+ phys_addr_t pa;
+
+ pa = __pgd_pgtable_alloc(&init_mm, pgtable_type);
+ BUG_ON(pa == INVALID_PHYS_ADDR);
+ return pa;
}
static phys_addr_t
pgd_pgtable_alloc_special_mm(enum pgtable_type pgtable_type)
{
- return __pgd_pgtable_alloc(NULL, pgtable_type);
+ phys_addr_t pa;
+
+ pa = __pgd_pgtable_alloc(NULL, pgtable_type);
+ BUG_ON(pa == INVALID_PHYS_ADDR);
+ return pa;
+}
+
+static void split_contpte(pte_t *ptep)
+{
+ int i;
+
+ ptep = PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES);
+ for (i = 0; i < CONT_PTES; i++, ptep++)
+ __set_pte(ptep, pte_mknoncont(__ptep_get(ptep)));
+}
+
+static int split_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+ pmdval_t tableprot = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF;
+ unsigned long pfn = pmd_pfn(pmd);
+ pgprot_t prot = pmd_pgprot(pmd);
+ phys_addr_t pte_phys;
+ pte_t *ptep;
+ int i;
+
+ pte_phys = try_pgd_pgtable_alloc_init_mm(TABLE_PTE);
+ if (pte_phys == INVALID_PHYS_ADDR)
+ return -ENOMEM;
+ ptep = (pte_t *)phys_to_virt(pte_phys);
+
+ if (pgprot_val(prot) & PMD_SECT_PXN)
+ tableprot |= PMD_TABLE_PXN;
+
+ prot = __pgprot((pgprot_val(prot) & ~PTE_TYPE_MASK) | PTE_TYPE_PAGE);
+ prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ for (i = 0; i < PTRS_PER_PTE; i++, ptep++, pfn++)
+ __set_pte(ptep, pfn_pte(pfn, prot));
+
+ /*
+ * Ensure the pte entries are visible to the table walker by the time
+ * the pmd entry that points to the ptes is visible.
+ */
+ dsb(ishst);
+ __pmd_populate(pmdp, pte_phys, tableprot);
+
+ return 0;
+}
+
+static void split_contpmd(pmd_t *pmdp)
+{
+ int i;
+
+ pmdp = PTR_ALIGN_DOWN(pmdp, sizeof(*pmdp) * CONT_PMDS);
+ for (i = 0; i < CONT_PMDS; i++, pmdp++)
+ set_pmd(pmdp, pmd_mknoncont(pmdp_get(pmdp)));
+}
+
+static int split_pud(pud_t *pudp, pud_t pud)
+{
+ pudval_t tableprot = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF;
+ unsigned int step = PMD_SIZE >> PAGE_SHIFT;
+ unsigned long pfn = pud_pfn(pud);
+ pgprot_t prot = pud_pgprot(pud);
+ phys_addr_t pmd_phys;
+ pmd_t *pmdp;
+ int i;
+
+ pmd_phys = try_pgd_pgtable_alloc_init_mm(TABLE_PMD);
+ if (pmd_phys == INVALID_PHYS_ADDR)
+ return -ENOMEM;
+ pmdp = (pmd_t *)phys_to_virt(pmd_phys);
+
+ if (pgprot_val(prot) & PMD_SECT_PXN)
+ tableprot |= PUD_TABLE_PXN;
+
+ prot = __pgprot((pgprot_val(prot) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT);
+ prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ for (i = 0; i < PTRS_PER_PMD; i++, pmdp++, pfn += step)
+ set_pmd(pmdp, pfn_pmd(pfn, prot));
+
+ /*
+ * Ensure the pmd entries are visible to the table walker by the time
+ * the pud entry that points to the pmds is visible.
+ */
+ dsb(ishst);
+ __pud_populate(pudp, pmd_phys, tableprot);
+
+ return 0;
+}
+
+static int split_kernel_leaf_mapping_locked(unsigned long addr)
+{
+ pgd_t *pgdp, pgd;
+ p4d_t *p4dp, p4d;
+ pud_t *pudp, pud;
+ pmd_t *pmdp, pmd;
+ pte_t *ptep, pte;
+ int ret = 0;
+
+ /*
+ * PGD: If addr is PGD aligned then addr already describes a leaf
+ * boundary. If not present then there is nothing to split.
+ */
+ if (ALIGN_DOWN(addr, PGDIR_SIZE) == addr)
+ goto out;
+ pgdp = pgd_offset_k(addr);
+ pgd = pgdp_get(pgdp);
+ if (!pgd_present(pgd))
+ goto out;
+
+ /*
+ * P4D: If addr is P4D aligned then addr already describes a leaf
+ * boundary. If not present then there is nothing to split.
+ */
+ if (ALIGN_DOWN(addr, P4D_SIZE) == addr)
+ goto out;
+ p4dp = p4d_offset(pgdp, addr);
+ p4d = p4dp_get(p4dp);
+ if (!p4d_present(p4d))
+ goto out;
+
+ /*
+ * PUD: If addr is PUD aligned then addr already describes a leaf
+ * boundary. If not present then there is nothing to split. Otherwise,
+ * if we have a pud leaf, split to contpmd.
+ */
+ if (ALIGN_DOWN(addr, PUD_SIZE) == addr)
+ goto out;
+ pudp = pud_offset(p4dp, addr);
+ pud = pudp_get(pudp);
+ if (!pud_present(pud))
+ goto out;
+ if (pud_leaf(pud)) {
+ ret = split_pud(pudp, pud);
+ if (ret)
+ goto out;
+ }
+
+ /*
+ * CONTPMD: If addr is CONTPMD aligned then addr already describes a
+ * leaf boundary. If not present then there is nothing to split.
+ * Otherwise, if we have a contpmd leaf, split to pmd.
+ */
+ if (ALIGN_DOWN(addr, CONT_PMD_SIZE) == addr)
+ goto out;
+ pmdp = pmd_offset(pudp, addr);
+ pmd = pmdp_get(pmdp);
+ if (!pmd_present(pmd))
+ goto out;
+ if (pmd_leaf(pmd)) {
+ if (pmd_cont(pmd))
+ split_contpmd(pmdp);
+ /*
+ * PMD: If addr is PMD aligned then addr already describes a
+ * leaf boundary. Otherwise, split to contpte.
+ */
+ if (ALIGN_DOWN(addr, PMD_SIZE) == addr)
+ goto out;
+ ret = split_pmd(pmdp, pmd);
+ if (ret)
+ goto out;
+ }
+
+ /*
+ * CONTPTE: If addr is CONTPTE aligned then addr already describes a
+ * leaf boundary. If not present then there is nothing to split.
+ * Otherwise, if we have a contpte leaf, split to pte.
+ */
+ if (ALIGN_DOWN(addr, CONT_PTE_SIZE) == addr)
+ goto out;
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = __ptep_get(ptep);
+ if (!pte_present(pte))
+ goto out;
+ if (pte_cont(pte))
+ split_contpte(ptep);
+
+out:
+ return ret;
+}
+
+static DEFINE_MUTEX(pgtable_split_lock);
+
+int split_kernel_leaf_mapping(unsigned long start, unsigned long end)
+{
+ int ret;
+
+ /*
+ * !BBML2_NOABORT systems should not be trying to change permissions on
+ * anything that is not pte-mapped in the first place. Just return early
+ * and let the permission change code raise a warning if not already
+ * pte-mapped.
+ */
+ if (!system_supports_bbml2_noabort())
+ return 0;
+
+ /*
+ * Ensure start and end are at least page-aligned since this is the
+ * finest granularity we can split to.
+ */
+ if (start != PAGE_ALIGN(start) || end != PAGE_ALIGN(end))
+ return -EINVAL;
+
+ mutex_lock(&pgtable_split_lock);
+ arch_enter_lazy_mmu_mode();
+
+ /*
+ * The split_kernel_leaf_mapping_locked() may sleep, it is not a
+ * problem for ARM64 since ARM64's lazy MMU implementation allows
+ * sleeping.
+ *
+ * Optimize for the common case of splitting out a single page from a
+ * larger mapping. Here we can just split on the "least aligned" of
+ * start and end and this will guarantee that there must also be a split
+ * on the more aligned address since the both addresses must be in the
+ * same contpte block and it must have been split to ptes.
+ */
+ if (end - start == PAGE_SIZE) {
+ start = __ffs(start) < __ffs(end) ? start : end;
+ ret = split_kernel_leaf_mapping_locked(start);
+ } else {
+ ret = split_kernel_leaf_mapping_locked(start);
+ if (!ret)
+ ret = split_kernel_leaf_mapping_locked(end);
+ }
+
+ arch_leave_lazy_mmu_mode();
+ mutex_unlock(&pgtable_split_lock);
+ return ret;
}
/*
#endif /* CONFIG_KFENCE */
+static inline bool force_pte_mapping(void)
+{
+ bool bbml2 = system_capabilities_finalized() ?
+ system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort();
+
+ return (!bbml2 && (rodata_full || arm64_kfence_can_set_direct_map() ||
+ is_realm_world())) ||
+ debug_pagealloc_enabled();
+}
+
static void __init map_mem(pgd_t *pgdp)
{
static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN);
early_kfence_pool = arm64_kfence_alloc_pool();
- if (can_set_direct_map())
+ if (force_pte_mapping())
flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
VM_BUG_ON(!mhp_range_allowed(start, size, true));
- if (can_set_direct_map())
+ if (force_pte_mapping())
flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),