Merge tag 'mm-hotfixes-stable-2023-10-01-08-34' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "Fourteen hotfixes, eleven of which are cc:stable. The remainder
  pertain to issues which were introduced after 6.5"

* tag 'mm-hotfixes-stable-2023-10-01-08-34' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  Crash: add lock to serialize crash hotplug handling
  selftests/mm: fix awk usage in charge_reserved_hugetlb.sh and hugetlb_reparenting_test.sh that may cause error
  mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified
  mm/damon/vaddr-test: fix memory leak in damon_do_test_apply_three_regions()
  mm, memcg: reconsider kmem.limit_in_bytes deprecation
  mm: zswap: fix potential memory corruption on duplicate store
  arm64: hugetlb: fix set_huge_pte_at() to work with all swap entries
  mm: hugetlb: add huge page size param to set_huge_pte_at()
  maple_tree: add MAS_UNDERFLOW and MAS_OVERFLOW states
  maple_tree: add mas_is_active() to detect in-tree walks
  nilfs2: fix potential use after free in nilfs_gccache_submit_read_data()
  mm: abstract moving to the next PFN
  mm: report success more often from filemap_map_folio_range()
  fs: binfmt_elf_efpic: fix personality for ELF-FDPIC

Documentation/admin-guide/cgroup-v1/memory.rst

@@ -92,6 +92,13 @@ Brief summary of control files.
  memory.oom_control		     set/show oom controls.
  memory.numa_stat		     show the number of memory usage per numa
 				     node
+ memory.kmem.limit_in_bytes          Deprecated knob to set and read the kernel
+                                     memory hard limit. Kernel hard limit is not
+                                     supported since 5.16. Writing any value to
+                                     do file will not have any effect same as if
+                                     nokmem kernel parameter was specified.
+                                     Kernel memory is still charged and reported
+                                     by memory.kmem.usage_in_bytes.
  memory.kmem.usage_in_bytes          show current kernel memory allocation
  memory.kmem.failcnt                 show the number of kernel memory usage
 				     hits limits

arch/arm64/include/asm/hugetlb.h

@@ -28,7 +28,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
 #define arch_make_huge_pte arch_make_huge_pte
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-			    pte_t *ptep, pte_t pte);
+			    pte_t *ptep, pte_t pte, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,

arch/arm64/mm/hugetlbpage.c

@@ -241,29 +241,19 @@ static void clear_flush(struct mm_struct *mm,
 	flush_tlb_range(&vma, saddr, addr);
 }
 
-static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
-{
-	VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));
-
-	return page_folio(pfn_to_page(swp_offset_pfn(entry)));
-}
-
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-			    pte_t *ptep, pte_t pte)
+			    pte_t *ptep, pte_t pte, unsigned long sz)
 {
 	size_t pgsize;
 	int i;
 	int ncontig;
 	unsigned long pfn, dpfn;
 	pgprot_t hugeprot;
 
-	if (!pte_present(pte)) {
-		struct folio *folio;
-
-		folio = hugetlb_swap_entry_to_folio(pte_to_swp_entry(pte));
-		ncontig = num_contig_ptes(folio_size(folio), &pgsize);
+	ncontig = num_contig_ptes(sz, &pgsize);
 
-		for (i = 0; i < ncontig; i++, ptep++)
+	if (!pte_present(pte)) {
+		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
 			set_pte_at(mm, addr, ptep, pte);
 		return;
 	}
@@ -273,7 +263,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		return;
 	}
 
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	pfn = pte_pfn(pte);
 	dpfn = pgsize >> PAGE_SHIFT;
 	hugeprot = pte_pgprot(pte);
@@ -571,5 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
 				  pte_t old_pte, pte_t pte)
 {
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }

arch/parisc/include/asm/hugetlb.h

@@ -6,7 +6,7 @@
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte);
+		     pte_t *ptep, pte_t pte, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,

arch/parisc/mm/hugetlbpage.c

@@ -140,7 +140,7 @@ static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t entry)
+		     pte_t *ptep, pte_t entry, unsigned long sz)
 {
 	__set_huge_pte_at(mm, addr, ptep, entry);
 }

arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h

@@ -46,7 +46,8 @@ static inline int check_and_get_huge_psize(int shift)
 }
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,

arch/powerpc/mm/book3s64/hugetlbpage.c

@@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				  pte_t *ptep, pte_t old_pte, pte_t pte)
 {
+	unsigned long psize;
 
 	if (radix_enabled())
 		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
 							   old_pte, pte);
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+
+	psize = huge_page_size(hstate_vma(vma));
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
 
 void __init hugetlbpage_init_defaultsize(void)

arch/powerpc/mm/book3s64/radix_hugetlbpage.c

@@ -47,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 					 pte_t old_pte, pte_t pte)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	unsigned long psize = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * POWER9 NMMU must flush the TLB after clearing the PTE before
@@ -58,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 	    atomic_read(&mm->context.copros) > 0)
 		radix__flush_hugetlb_page(vma, addr);
 
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }

arch/powerpc/mm/nohash/8xx.c

@@ -91,7 +91,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 	if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
 		return -EINVAL;
 
-	set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)));
+	set_huge_pte_at(&init_mm, va, ptep,
+			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
 
 	return 0;
 }

arch/powerpc/mm/pgtable.c

@@ -288,7 +288,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 }
 
 #if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz)
 {
 	pmd_t *pmd = pmd_off(mm, addr);
 	pte_basic_t val;

arch/riscv/include/asm/hugetlb.h

@@ -18,7 +18,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm,
-		     unsigned long addr, pte_t *ptep, pte_t pte);
+		     unsigned long addr, pte_t *ptep, pte_t pte,
+		     unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,

arch/riscv/mm/hugetlbpage.c

@@ -180,7 +180,8 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 void set_huge_pte_at(struct mm_struct *mm,
 		     unsigned long addr,
 		     pte_t *ptep,
-		     pte_t pte)
+		     pte_t pte,
+		     unsigned long sz)
 {
 	int i, pte_num;
 

arch/s390/include/asm/hugetlb.h

@@ -16,6 +16,8 @@
 #define hugepages_supported()			(MACHINE_HAS_EDAT1)
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 pte_t huge_ptep_get(pte_t *ptep);
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
@@ -65,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(huge_ptep_get(ptep), pte);
 	if (changed) {
 		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
-		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
 }
@@ -74,7 +76,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
-	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
+	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
 
 static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)

arch/s390/mm/hugetlbpage.c

@@ -142,7 +142,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
 		__storage_key_init_range(paddr, paddr + size - 1);
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte)
 {
 	unsigned long rste;
@@ -163,6 +163,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	set_pte(ptep, __pte(rste));
 }
 
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte, unsigned long sz)
+{
+	__set_huge_pte_at(mm, addr, ptep, pte);
+}
+
 pte_t huge_ptep_get(pte_t *ptep)
 {
 	return __rste_to_pte(pte_val(*ptep));

arch/sparc/include/asm/hugetlb.h

@@ -14,6 +14,8 @@ extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
@@ -32,7 +34,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
 	pte_t old_pte = *ptep;
-	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -42,7 +44,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 {
 	int changed = !pte_same(*ptep, pte);
 	if (changed) {
-		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 		flush_tlb_page(vma, addr);
 	}
 	return changed;

arch/sparc/mm/hugetlbpage.c

@@ -328,7 +328,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return pte_offset_huge(pmd, addr);
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
 	unsigned int nptes, orig_shift, shift;
@@ -364,6 +364,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				    orig_shift);
 }
 
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry, unsigned long sz)
+{
+	__set_huge_pte_at(mm, addr, ptep, entry);
+}
+
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {

arch/x86/include/asm/pgtable.h

@@ -955,6 +955,14 @@ static inline int pte_same(pte_t a, pte_t b)
 	return a.pte == b.pte;
 }
 
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+	if (__pte_needs_invert(pte_val(pte)))
+		return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
+	return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#define pte_next_pfn	pte_next_pfn
+
 static inline int pte_present(pte_t a)
 {
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);

fs/binfmt_elf_fdpic.c

@@ -345,10 +345,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	/* there's now no turning back... the old userspace image is dead,
 	 * defunct, deceased, etc.
 	 */
+	SET_PERSONALITY(exec_params.hdr);
 	if (elf_check_fdpic(&exec_params.hdr))
-		set_personality(PER_LINUX_FDPIC);
-	else
-		set_personality(PER_LINUX);
+		current->personality |= PER_LINUX_FDPIC;
 	if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
 

fs/nilfs2/gcinode.c

@@ -73,10 +73,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
 		struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 
 		err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn);
-		if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */
-			brelse(bh);
+		if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */
 			goto failed;
-		}
 	}
 
 	lock_buffer(bh);
@@ -102,6 +100,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
  failed:
 	unlock_page(bh->b_page);
 	put_page(bh->b_page);
+	if (unlikely(err))
+		brelse(bh);
 	return err;
 }
 

include/asm-generic/hugetlb.h

@@ -76,7 +76,7 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 
 #ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		pte_t *ptep, pte_t pte)
+		pte_t *ptep, pte_t pte, unsigned long sz)
 {
 	set_pte_at(mm, addr, ptep, pte);
 }

include/linux/hugetlb.h

@@ -984,7 +984,9 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 						unsigned long addr, pte_t *ptep,
 						pte_t old_pte, pte_t pte)
 {
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
 #endif
 
@@ -1173,7 +1175,7 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 }
 
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
+				   pte_t *ptep, pte_t pte, unsigned long sz)
 {
 }
 

include/linux/maple_tree.h

@@ -428,6 +428,8 @@ struct ma_wr_state {
 #define MAS_ROOT	((struct maple_enode *)5UL)
 #define MAS_NONE	((struct maple_enode *)9UL)
 #define MAS_PAUSE	((struct maple_enode *)17UL)
+#define MAS_OVERFLOW	((struct maple_enode *)33UL)
+#define MAS_UNDERFLOW	((struct maple_enode *)65UL)
 #define MA_ERROR(err) \
 		((struct maple_enode *)(((unsigned long)err << 2) | 2UL))
 
@@ -511,6 +513,15 @@ static inline bool mas_is_paused(const struct ma_state *mas)
 	return mas->node == MAS_PAUSE;
 }
 
+/* Check if the mas is pointing to a node or not */
+static inline bool mas_is_active(struct ma_state *mas)
+{
+	if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE)
+		return true;
+
+	return false;
+}
+
 /**
  * mas_reset() - Reset a Maple Tree operation state.
  * @mas: Maple Tree operation state.

include/linux/pgtable.h

@@ -206,6 +206,14 @@ static inline int pmd_young(pmd_t pmd)
 #endif
 
 #ifndef set_ptes
+
+#ifndef pte_next_pfn
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+	return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#endif
+
 /**
  * set_ptes - Map consecutive pages to a contiguous range of addresses.
  * @mm: Address space to map the pages into.
@@ -231,7 +239,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
 		if (--nr == 0)
 			break;
 		ptep++;
-		pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+		pte = pte_next_pfn(pte);
 	}
 	arch_leave_lazy_mmu_mode();
 }