Merge tag 'mm-stable-2025-04-02-22-07' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more MM updates from Andrew Morton:

- The series "mm: fixes for fallouts from mem_init() cleanup" from Mike
Rapoport fixes a couple of issues with the just-merged "arch, mm:
reduce code duplication in mem_init()" series

- The series "MAINTAINERS: add my isub-entries to MM part." from Mike
Rapoport does some maintenance on MAINTAINERS

- The series "remove tlb_remove_page_ptdesc()" from Qi Zheng does some
cleanup work to the page mapping code

- The series "mseal system mappings" from Jeff Xu permits sealing of
"system mappings", such as vdso, vvar, vvar_vclock, vectors (arm
compat-mode), sigpage (arm compat-mode)

- Plus the usual shower of singleton patches

* tag 'mm-stable-2025-04-02-22-07' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (31 commits)
mseal sysmap: add arch-support txt
mseal sysmap: enable s390
selftest: test system mappings are sealed
mseal sysmap: update mseal.rst
mseal sysmap: uprobe mapping
mseal sysmap: enable arm64
mseal sysmap: enable x86-64
mseal sysmap: generic vdso vvar mapping
selftests: x86: test_mremap_vdso: skip if vdso is msealed
mseal sysmap: kernel config and header change
mm: pgtable: remove tlb_remove_page_ptdesc()
x86: pgtable: convert to use tlb_remove_ptdesc()
riscv: pgtable: unconditionally use tlb_remove_ptdesc()
mm: pgtable: convert some architectures to use tlb_remove_ptdesc()
mm: pgtable: change pt parameter of tlb_remove_ptdesc() to struct ptdesc*
mm: pgtable: make generic tlb_remove_table() use struct ptdesc
microblaze/mm: put mm_cmdline_setup() in .init.text section
mm/memory_hotplug: fix call folio_test_large with tail page in do_migrate_range
MAINTAINERS: mm: add entry for secretmem
MAINTAINERS: mm: add entry for numa memblocks and numa emulation
...

Documentation/features/core/mseal_sys_mappings/arch-support.txt

···
+#
+# Feature name:          mseal-system-mappings
+#         Kconfig:       ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
+#         description:   arch supports mseal system mappings
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  N/A |
+    |         arm: |  N/A |
+    |       arm64: |  ok  |
+    |        csky: |  N/A |
+    |     hexagon: |  N/A |
+    |   loongarch: | TODO |
+    |        m68k: |  N/A |
+    |  microblaze: |  N/A |
+    |        mips: | TODO |
+    |       nios2: |  N/A |
+    |    openrisc: |  N/A |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |       riscv: | TODO |
+    |        s390: |  ok  |
+    |          sh: |  N/A |
+    |       sparc: | TODO |
+    |          um: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: |  N/A |
+    -----------------------

Documentation/userspace-api/mseal.rst

···
 
 - Chrome browser: protect some security sensitive data structures.
 
+- System mappings:
+  The system mappings are created by the kernel and includes vdso, vvar,
+  vvar_vclock, vectors (arm compat-mode), sigpage (arm compat-mode), uprobes.
+
+  Those system mappings are readonly only or execute only, memory sealing can
+  protect them from ever changing to writable or unmmap/remapped as different
+  attributes. This is useful to mitigate memory corruption issues where a
+  corrupted pointer is passed to a memory management system.
+
+  If supported by an architecture (CONFIG_ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS),
+  the CONFIG_MSEAL_SYSTEM_MAPPINGS seals all system mappings of this
+  architecture.
+
+  The following architectures currently support this feature: x86-64, arm64,
+  and s390.
+
+  WARNING: This feature breaks programs which rely on relocating
+  or unmapping system mappings. Known broken software at the time
+  of writing includes CHECKPOINT_RESTORE, UML, gVisor, rr. Therefore
+  this config can't be enabled universally.
+
 When not to use mseal
 =====================
 Applications can apply sealing to any virtual memory region from userspace,

MAINTAINERS

···
 F:	tools/testing/selftests/mm/
 N:	include/linux/page[-_]*
 
+MEMORY MANAGEMENT - EXECMEM
+M:	Andrew Morton <[e-mail]>
+M:	Mike Rapoport <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+F:	include/linux/execmem.h
+F:	mm/execmem.c
+
+MEMORY MANAGEMENT - NUMA MEMBLOCKS AND NUMA EMULATION
+M:	Andrew Morton <[e-mail]>
+M:	Mike Rapoport <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+F:	include/linux/numa_memblks.h
+F:	mm/numa.c
+F:	mm/numa_emulation.c
+F:	mm/numa_memblks.c
+
+MEMORY MANAGEMENT - SECRETMEM
+M:	Andrew Morton <[e-mail]>
+M:	Mike Rapoport <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+F:	include/linux/secretmem.h
+F:	mm/secretmem.c
+
+MEMORY MANAGEMENT - USERFAULTFD
+M:	Andrew Morton <[e-mail]>
+R:	Peter Xu <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+F:	Documentation/admin-guide/mm/userfaultfd.rst
+F:	fs/userfaultfd.c
+F:	include/asm-generic/pgtable_uffd.h
+F:	include/linux/userfaultfd_k.h
+F:	include/uapi/linux/userfaultfd.h
+F:	mm/userfaultfd.c
+F:	tools/testing/selftests/mm/uffd-*.[ch]
+
 MEMORY MAPPING
 M:	Andrew Morton <[e-mail]>
 M:	Liam R. Howlett <[e-mail]>

arch/arm64/Kconfig

···
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MEM_ENCRYPT
+	select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT

arch/arm64/kernel/vdso.c

···
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
 				       VM_READ|VM_EXEC|gp_flags|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				       VM_SEALED_SYSMAP,
 				       vdso_info[abi].cm);
 	if (IS_ERR(ret))
 		goto up_fail;
···
 	 */
 	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
 				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC,
+				       VM_MAYREAD | VM_MAYEXEC |
+				       VM_SEALED_SYSMAP,
 				       &aarch32_vdso_maps[AA32_MAP_VECTORS]);
 
 	return PTR_ERR_OR_ZERO(ret);
···
 	 */
 	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
 				       VM_READ | VM_EXEC | VM_MAYREAD |
-				       VM_MAYWRITE | VM_MAYEXEC,
+				       VM_MAYWRITE | VM_MAYEXEC |
+				       VM_SEALED_SYSMAP,
 				       &aarch32_vdso_maps[AA32_MAP_SIGPAGE]);
 	if (IS_ERR(ret))
 		goto out;

arch/csky/include/asm/pgalloc.h

···
 	return ret;
 }
 
-#define __pte_free_tlb(tlb, pte, address)		\
-do {							\
-	pagetable_dtor(page_ptdesc(pte));		\
-	tlb_remove_page_ptdesc(tlb, page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 extern void pagetable_init(void);
 extern void mmu_init(unsigned long min_pfn, unsigned long max_pfn);

arch/hexagon/include/asm/pgalloc.h

···
 		max_kernel_seg = pmdindex;
 }
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor((page_ptdesc(pte)));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif

arch/loongarch/include/asm/pgalloc.h

···
 	return pte;
 }
 
-#define __pte_free_tlb(tlb, pte, address)			\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #ifndef __PAGETABLE_PMD_FOLDED
 

arch/m68k/include/asm/sun3_pgalloc.h

···
 
 extern const char bad_pmd_string[];
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 {

arch/microblaze/mm/init.c

···
 /*
  * Check for command-line options that affect what MMU_init will do.
  */
-static void mm_cmdline_setup(void)
+static void __init mm_cmdline_setup(void)
 {
 	unsigned long maxmem = 0;
 	char *p = cmd_line;

arch/mips/include/asm/pgalloc.h

···
 extern void pgd_init(void *addr);
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
-#define __pte_free_tlb(tlb, pte, address)			\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #ifndef __PAGETABLE_PMD_FOLDED
 

arch/nios2/include/asm/pgalloc.h

···
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
-#define __pte_free_tlb(tlb, pte, addr)					\
-	do {								\
-		pagetable_dtor(page_ptdesc(pte));			\
-		tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-	} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif /* _ASM_NIOS2_PGALLOC_H */

arch/openrisc/include/asm/pgalloc.h

···
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif

arch/riscv/include/asm/pgalloc.h

···
 #define __HAVE_ARCH_PUD_FREE
 #include <asm-generic/pgalloc.h>
 
-/*
- * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
- * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
- * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
- * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
- * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
- * for more details.
- */
-static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt)
-{
-	if (riscv_use_sbi_for_rfence()) {
-		tlb_remove_ptdesc(tlb, pt);
-	} else {
-		pagetable_dtor(pt);
-		tlb_remove_page_ptdesc(tlb, pt);
-	}
-}
-
 static inline void pmd_populate_kernel(struct mm_struct *mm,
 	pmd_t *pmd, pte_t *pte)
 {
···
 				  unsigned long addr)
 {
 	if (pgtable_l4_enabled)
-		riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
+		tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
 }
 
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				  unsigned long addr)
 {
 	if (pgtable_l5_enabled)
-		riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
+		tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
···
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 				  unsigned long addr)
 {
-	riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
 }
 
 #endif /* __PAGETABLE_PMD_FOLDED */
···
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
-	riscv_tlb_remove_ptdesc(tlb, page_ptdesc(pte));
+	tlb_remove_ptdesc(tlb, page_ptdesc(pte));
 }
 #endif /* CONFIG_MMU */
 

arch/s390/Kconfig

···
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_HUGETLBFS
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && CC_IS_CLANG
+	select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_BUILTIN_BSWAP

arch/s390/kernel/vdso.c

···
 	vdso_text_start = vvar_start + VDSO_NR_PAGES * PAGE_SIZE;
 	/* VM_MAYWRITE for COW so gdb can set breakpoints */
 	vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len,
-				       VM_READ|VM_EXEC|
+				       VM_READ|VM_EXEC|VM_SEALED_SYSMAP|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
 				       vdso_mapping);
 	if (IS_ERR(vma)) {

arch/sh/include/asm/pgalloc.h

···
 	set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
 }
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif /* __ASM_SH_PGALLOC_H */

arch/um/include/asm/pgalloc.h

···
  */
 extern pgd_t *pgd_alloc(struct mm_struct *);
 
-#define __pte_free_tlb(tlb, pte, address)			\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #if CONFIG_PGTABLE_LEVELS > 2
 
-#define __pmd_free_tlb(tlb, pmd, address)			\
-do {								\
-	pagetable_dtor(virt_to_ptdesc(pmd));			\
-	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd));	\
-} while (0)
+#define __pmd_free_tlb(tlb, pmd, address)	\
+	tlb_remove_ptdesc((tlb), virt_to_ptdesc(pmd))
 
 #if CONFIG_PGTABLE_LEVELS > 3
 
-#define __pud_free_tlb(tlb, pud, address)			\
-do {								\
-	pagetable_dtor(virt_to_ptdesc(pud));		\
-	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud));	\
-} while (0)
+#define __pud_free_tlb(tlb, pud, address)	\
+	tlb_remove_ptdesc((tlb), virt_to_ptdesc(pud))
 
 #endif
 #endif

arch/x86/Kconfig

···
 	# Options that are inherently 64-bit kernel only:
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_PTDUMP
+	select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE

arch/x86/entry/vdso/vma.c

···
 				       text_start,
 				       image->size,
 				       VM_READ|VM_EXEC|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				       VM_SEALED_SYSMAP,
 				       &vdso_mapping);
 
 	if (IS_ERR(vma)) {
···
 				       VDSO_VCLOCK_PAGES_START(addr),
 				       VDSO_NR_VCLOCK_PAGES * PAGE_SIZE,
 				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
-				       VM_PFNMAP,
+				       VM_PFNMAP|VM_SEALED_SYSMAP,
 				       &vvar_vclock_mapping);
 
 	if (IS_ERR(vma)) {

arch/x86/mm/pgtable.c

···
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
 	paravirt_release_pte(page_to_pfn(pte));
-	tlb_remove_table(tlb, page_ptdesc(pte));
+	tlb_remove_ptdesc(tlb, page_ptdesc(pte));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 2
···
 #ifdef CONFIG_X86_PAE
 	tlb->need_flush_all = 1;
 #endif
-	tlb_remove_table(tlb, virt_to_ptdesc(pmd));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	tlb_remove_table(tlb, virt_to_ptdesc(pud));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
 {
 	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
-	tlb_remove_table(tlb, virt_to_ptdesc(p4d));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */

include/asm-generic/tlb.h

···
  */
 static inline void tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
-	struct page *page = (struct page *)table;
+	struct ptdesc *ptdesc = (struct ptdesc *)table;
 
-	pagetable_dtor(page_ptdesc(page));
-	tlb_remove_page(tlb, page);
+	pagetable_dtor(ptdesc);
+	tlb_remove_page(tlb, ptdesc_page(ptdesc));
 }
 #endif /* CONFIG_MMU_GATHER_TABLE_FREE */
 
···
 	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
 
-static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt)
+static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt)
 {
 	tlb_remove_table(tlb, pt);
-}
-
-/* Like tlb_remove_ptdesc, but for page-like page directories. */
-static inline void tlb_remove_page_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt)
-{
-	tlb_remove_page(tlb, ptdesc_page(pt));
 }
 
 static inline void tlb_change_page_size(struct mmu_gather *tlb,

include/linux/mm.h

···
 int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
 int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
 
+
+/*
+ * mseal of userspace process's system mappings.
+ */
+#ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS
+#define VM_SEALED_SYSMAP	VM_SEALED
+#else
+#define VM_SEALED_SYSMAP	VM_NONE
+#endif
+
 #endif /* _LINUX_MM_H */

init/Kconfig

···
 config ARCH_HAS_MEMBARRIER_SYNC_CORE
 	bool
 
+config ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
+	bool
+	help
+	  Control MSEAL_SYSTEM_MAPPINGS access based on architecture.
+
+	  A 64-bit kernel is required for the memory sealing feature.
+	  No specific hardware features from the CPU are needed.
+
+	  To enable this feature, the architecture needs to update their
+	  special mappings calls to include the sealing flag and confirm
+	  that it doesn't unmap/remap system mappings during the life
+	  time of the process. The existence of this flag for an architecture
+	  implies that it does not require the remapping of the system
+	  mappings during process lifetime, so sealing these mappings is safe
+	  from a kernel perspective.
+
+	  After the architecture enables this, a distribution can set
+	  CONFIG_MSEAL_SYSTEM_MAPPING to manage access to the feature.
+
+	  For complete descriptions of memory sealing, please see
+	  Documentation/userspace-api/mseal.rst
+
 config HAVE_PERF_EVENTS
 	bool
 	help

kernel/events/uprobes.c

···
 	}
 
 	vma = _install_special_mapping(mm, area->vaddr, PAGE_SIZE,
-				VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO,
+				VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO|
+				VM_SEALED_SYSMAP,
 				&xol_mapping);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);

lib/vdso/datastore.c

···
 struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr)
 {
 	return _install_special_mapping(mm, addr, VDSO_NR_PAGES * PAGE_SIZE,
-					VM_READ | VM_MAYREAD | VM_IO | VM_DONTDUMP | VM_PFNMAP,
+					VM_READ | VM_MAYREAD | VM_IO | VM_DONTDUMP |
+					VM_PFNMAP | VM_SEALED_SYSMAP,
 					&vdso_vvar_mapping);
 }
 

mm/damon/core.c

···
 
 	if (ops->id >= NR_DAMON_OPS)
 		return -EINVAL;
+
 	mutex_lock(&damon_ops_lock);
 	/* Fail for already registered ops */
-	if (__damon_is_registered_ops(ops->id)) {
+	if (__damon_is_registered_ops(ops->id))
 		err = -EINVAL;
-		goto out;
-	}
-	damon_registered_ops[ops->id] = *ops;
-out:
+	else
+		damon_registered_ops[ops->id] = *ops;
 	mutex_unlock(&damon_ops_lock);
 	return err;
 }

mm/kasan/kasan_test_c.c

···
 	kmem_cache_destroy(cache);
 }
 
-static void empty_cache_ctor(void *object) { }
-
 static void kmem_cache_double_destroy(struct kunit *test)
 {
 	struct kmem_cache *cache;
 
-	/* Provide a constructor to prevent cache merging. */
-	cache = kmem_cache_create("test_cache", 200, 0, 0, empty_cache_ctor);
+	cache = kmem_cache_create("test_cache", 200, 0, SLAB_NO_MERGE, NULL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
 	kmem_cache_destroy(cache);
 	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_destroy(cache));

mm/memblock.c

···
 	unsigned long start_pfn = PFN_UP(start);
 	unsigned long end_pfn = PFN_DOWN(end);
 
+	if (!IS_ENABLED(CONFIG_HIGHMEM) && end_pfn > max_low_pfn)
+		end_pfn = max_low_pfn;
+
 	if (start_pfn >= end_pfn)
 		return 0;
 

mm/memory_hotplug.c

···
 		page = pfn_to_page(pfn);
 		folio = page_folio(page);
 
-		/*
-		 * No reference or lock is held on the folio, so it might
-		 * be modified concurrently (e.g. split).  As such,
-		 * folio_nr_pages() may read garbage.  This is fine as the outer
-		 * loop will revisit the split folio later.
-		 */
-		if (folio_test_large(folio))
-			pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
-
 		if (!folio_try_get(folio))
 			continue;
 
 		if (unlikely(page_folio(page) != folio))
 			goto put_folio;
+
+		if (folio_test_large(folio))
+			pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
 
 		if (folio_contain_hwpoisoned_page(folio)) {
 			if (WARN_ON(folio_test_lru(folio)))

mm/mm_init.c

···
 		}
 	}
 
-#ifdef CONFIG_SPARSEMEM
 	/*
 	 * Initialize the memory map for hole in the range [memory_end,
-	 * section_end].
+	 * section_end] for SPARSEMEM and in the range [memory_end, memmap_end]
+	 * for FLATMEM.
 	 * Append the pages in this hole to the highest zone in the last
 	 * node.
-	 * The call to init_unavailable_range() is outside the ifdef to
-	 * silence the compiler warining about zone_id set but not used;
-	 * for FLATMEM it is a nop anyway
 	 */
+#ifdef CONFIG_SPARSEMEM
 	end_pfn = round_up(end_pfn, PAGES_PER_SECTION);
-	if (hole_pfn < end_pfn)
+#else
+	end_pfn = round_up(end_pfn, MAX_ORDER_NR_PAGES);
 #endif
+	if (hole_pfn < end_pfn)
 		init_unavailable_range(hole_pfn, end_pfn, zone_id, nid);
 }
 

mm/mremap.c

···
 	 * adjacent to the expanded vma and otherwise
 	 * compatible.
 	 */
-	vma = vrm->vma = vma_merge_extend(&vmi, vma, vrm->delta);
+	vma = vma_merge_extend(&vmi, vma, vrm->delta);
 	if (!vma) {
 		vrm_uncharge(vrm);
 		return -ENOMEM;
 	}
+	vrm->vma = vma;
 
 	vrm_stat_account(vrm, vrm->delta);
 

mm/page_alloc.c

···
 
 static void check_new_page_bad(struct page *page)
 {
-	if (unlikely(page->flags & __PG_HWPOISON)) {
+	if (unlikely(PageHWPoison(page))) {
 		/* Don't complain about hwpoisoned pages */
 		if (PageBuddy(page))
 			__ClearPageBuddy(page);
···
 		goto retry;
 
 	/* Reclaim/compaction failed to prevent the fallback */
-	if (defrag_mode) {
-		alloc_flags &= ALLOC_NOFRAGMENT;
+	if (defrag_mode && (alloc_flags & ALLOC_NOFRAGMENT)) {
+		alloc_flags &= ~ALLOC_NOFRAGMENT;
 		goto retry;
 	}
 

security/Kconfig

···
 
 endchoice
 
+config MSEAL_SYSTEM_MAPPINGS
+	bool "mseal system mappings"
+	depends on 64BIT
+	depends on ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
+	depends on !CHECKPOINT_RESTORE
+	help
+	  Apply mseal on system mappings.
+	  The system mappings includes vdso, vvar, vvar_vclock,
+	  vectors (arm compat-mode), sigpage (arm compat-mode), uprobes.
+
+	  A 64-bit kernel is required for the memory sealing feature.
+	  No specific hardware features from the CPU are needed.
+
+	  WARNING: This feature breaks programs which rely on relocating
+	  or unmapping system mappings. Known broken software at the time
+	  of writing includes CHECKPOINT_RESTORE, UML, gVisor, rr. Therefore
+	  this config can't be enabled universally.
+
+	  For complete descriptions of memory sealing, please see
+	  Documentation/userspace-api/mseal.rst
+
 config SECURITY
 	bool "Enable different security models"
 	depends on SYSFS

tools/testing/selftests/Makefile

···
 TARGETS += mount_setattr
 TARGETS += move_mount_set_group
 TARGETS += mqueue
+TARGETS += mseal_system_mappings
 TARGETS += nci
 TARGETS += net
 TARGETS += net/af_unix

tools/testing/selftests/mm/va_high_addr_switch.sh

···
 	fi
 }
 
+check_supported_ppc64()
+{
+	local config="/proc/config.gz"
+	[[ -f "${config}" ]] || config="/boot/config-$(uname -r)"
+	[[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot"
+
+	local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2)
+	if [[ "${pg_table_levels}" -lt 5 ]]; then
+		echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
+		exit $ksft_skip
+	fi
+
+	local mmu_support=$(grep -m1 "mmu" /proc/cpuinfo | awk '{print $3}')
+	if [[ "$mmu_support" != "radix" ]]; then
+		echo "$0: System does not use Radix MMU, required for 5-level paging"
+		exit $ksft_skip
+	fi
+
+	local hugepages_total=$(awk '/HugePages_Total/ {print $2}' /proc/meminfo)
+	if [[ "${hugepages_total}" -eq 0 ]]; then
+		echo "$0: HugePages are not enabled, required for some tests"
+		exit $ksft_skip
+	fi
+}
+
 check_test_requirements()
 {
 	# The test supports x86_64 and powerpc64. We currently have no useful
···
 	case `uname -m` in
 		"x86_64")
 			check_supported_x86_64
+		;;
+		"ppc64le"|"ppc64")
+			check_supported_ppc64
 		;;
 		*)
 			return 0

tools/testing/selftests/mseal_system_mappings/.gitignore

···
+# SPDX-License-Identifier: GPL-2.0-only
+sysmap_is_sealed

tools/testing/selftests/mseal_system_mappings/Makefile

···
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -std=c99 -pthread -Wall $(KHDR_INCLUDES)
+
+TEST_GEN_PROGS := sysmap_is_sealed
+
+include ../lib.mk

tools/testing/selftests/mseal_system_mappings/config

···
+CONFIG_MSEAL_SYSTEM_MAPPINGS=y

tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * test system mappings are sealed when
+ * KCONFIG_MSEAL_SYSTEM_MAPPINGS=y
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+#define VMFLAGS "VmFlags:"
+#define MSEAL_FLAGS "sl"
+#define MAX_LINE_LEN 512
+
+bool has_mapping(char *name, FILE *maps)
+{
+	char line[MAX_LINE_LEN];
+
+	while (fgets(line, sizeof(line), maps)) {
+		if (strstr(line, name))
+			return true;
+	}
+
+	return false;
+}
+
+bool mapping_is_sealed(char *name, FILE *maps)
+{
+	char line[MAX_LINE_LEN];
+
+	while (fgets(line, sizeof(line), maps)) {
+		if (!strncmp(line, VMFLAGS, strlen(VMFLAGS))) {
+			if (strstr(line, MSEAL_FLAGS))
+				return true;
+
+			return false;
+		}
+	}
+
+	return false;
+}
+
+FIXTURE(basic) {
+	FILE *maps;
+};
+
+FIXTURE_SETUP(basic)
+{
+	self->maps = fopen("/proc/self/smaps", "r");
+	if (!self->maps)
+		SKIP(return, "Could not open /proc/self/smap, errno=%d",
+			errno);
+};
+
+FIXTURE_TEARDOWN(basic)
+{
+	if (self->maps)
+		fclose(self->maps);
+};
+
+FIXTURE_VARIANT(basic)
+{
+	char *name;
+	bool sealed;
+};
+
+FIXTURE_VARIANT_ADD(basic, vdso) {
+	.name = "[vdso]",
+	.sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, vvar) {
+	.name = "[vvar]",
+	.sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, vvar_vclock) {
+	.name = "[vvar_vclock]",
+	.sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, sigpage) {
+	.name = "[sigpage]",
+	.sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, vectors) {
+	.name = "[vectors]",
+	.sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, uprobes) {
+	.name = "[uprobes]",
+	.sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, stack) {
+	.name = "[stack]",
+	.sealed = false,
+};
+
+TEST_F(basic, check_sealed)
+{
+	if (!has_mapping(variant->name, self->maps)) {
+		SKIP(return, "could not find the mapping, %s",
+			variant->name);
+	}
+
+	EXPECT_EQ(variant->sealed,
+		mapping_is_sealed(variant->name, self->maps));
+};
+
+TEST_HARNESS_MAIN

tools/testing/selftests/x86/test_mremap_vdso.c

···
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
+#include <stdbool.h>
 
 #include <sys/mman.h>
 #include <sys/auxv.h>
···
 
 }
 
+#define VDSO_NAME "[vdso]"
+#define VMFLAGS "VmFlags:"
+#define MSEAL_FLAGS "sl"
+#define MAX_LINE_LEN 512
+
+bool vdso_sealed(FILE *maps)
+{
+	char line[MAX_LINE_LEN];
+	bool has_vdso = false;
+
+	while (fgets(line, sizeof(line), maps)) {
+		if (strstr(line, VDSO_NAME))
+			has_vdso = true;
+
+		if (has_vdso && !strncmp(line, VMFLAGS, strlen(VMFLAGS))) {
+			if (strstr(line, MSEAL_FLAGS))
+				return true;
+
+			return false;
+		}
+	}
+
+	return false;
+}
+
 int main(int argc, char **argv, char **envp)
 {
 	pid_t child;
+	FILE *maps;
 
 	ksft_print_header();
 	ksft_set_plan(1);
+
+	maps = fopen("/proc/self/smaps", "r");
+	if (!maps) {
+		ksft_test_result_skip(
+			"Could not open /proc/self/smaps, errno=%d\n",
+			 errno);
+
+		return 0;
+	}
+
+	if (vdso_sealed(maps)) {
+		ksft_test_result_skip("vdso is sealed\n");
+		return 0;
+	}
+
+	fclose(maps);
 
 	child = fork();
 	if (child == -1)