Merge tag 'mm-hotfixes-stable-2025-09-10-20-00' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

torvalds · torvalds · commit 4f553c1e2c7b · 2025-09-10T21:19:34.000-07:00
Pull misc fixes from Andrew Morton:
 "20 hotfixes. 15 are cc:stable and the remainder address post-6.16
  issues or aren't considered necessary for -stable kernels. 14 of these
  fixes are for MM.

  This includes

   - kexec fixes from Breno for a recently introduced
     use-uninitialized bug

   - DAMON fixes from Quanmin Yan to avoid div-by-zero crashes
     which can occur if the operator uses poorly-chosen insmod
     parameters

   and misc singleton fixes"

* tag 'mm-hotfixes-stable-2025-09-10-20-00' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  MAINTAINERS: add tree entry to numa memblocks and emulation block
  mm/damon/sysfs: fix use-after-free in state_show()
  proc: fix type confusion in pde_set_flags()
  compiler-clang.h: define __SANITIZE_*__ macros only when undefined
  mm/vmalloc, mm/kasan: respect gfp mask in kasan_populate_vmalloc()
  ocfs2: fix recursive semaphore deadlock in fiemap call
  mm/memory-failure: fix VM_BUG_ON_PAGE(PagePoisoned(page)) when unpoison memory
  mm/mremap: fix regression in vrm-&gt;new_addr check
  percpu: fix race on alloc failed warning limit
  mm/memory-failure: fix redundant updates for already poisoned pages
  s390: kexec: initialize kexec_buf struct
  riscv: kexec: initialize kexec_buf struct
  arm64: kexec: initialize kexec_buf struct in load_other_segments()
  mm/damon/reclaim: avoid divide-by-zero in damon_reclaim_apply_parameters()
  mm/damon/lru_sort: avoid divide-by-zero in damon_lru_sort_apply_parameters()
  mm/damon/core: set quota-&gt;charged_from to jiffies at first charge window
  mm/hugetlb: add missing hugetlb_lock in __unmap_hugepage_range()
  init/main.c: fix boot time tracing crash
  mm/memory_hotplug: fix hwpoisoned large folio handling in do_migrate_range()
  mm/khugepaged: fix the address passed to notifier on testing young
diff --git a/MAINTAINERS b/MAINTAINERS
@@ -16128,6 +16128,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Mike Rapoport <rppt@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git
 F:	include/linux/numa_memblks.h
 F:	mm/numa.c
 F:	mm/numa_emulation.c
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
@@ -94,7 +94,7 @@ int load_other_segments(struct kimage *image,
 			char *initrd, unsigned long initrd_len,
 			char *cmdline)
 {
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	void *dtb = NULL;
 	unsigned long initrd_load_addr = 0, dtb_len,
 		      orig_segments = image->nr_segments;
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
@@ -16,7 +16,7 @@
 static int kexec_file_add_kernel_elf(struct kimage *image,
 				     struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	const Elf_Ehdr *ehdr;
 	const Elf_Phdr *phdr;
 	Elf_Addr entry;
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
@@ -16,7 +16,7 @@
 static int kexec_file_add_kernel_image(struct kimage *image,
 				       struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 
 	buf.image = image;
 
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
@@ -129,7 +129,7 @@ static int kexec_file_update_purgatory(struct kimage *image,
 static int kexec_file_add_purgatory(struct kimage *image,
 				    struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	int ret;
 
 	buf.image = image;
@@ -152,7 +152,7 @@ static int kexec_file_add_purgatory(struct kimage *image,
 static int kexec_file_add_initrd(struct kimage *image,
 				 struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	int ret;
 
 	buf.image = image;
@@ -184,7 +184,7 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 {
 	__u32 *lc_ipl_parmblock_ptr;
 	unsigned int len, ncerts;
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	unsigned long addr;
 	void *ptr, *end;
 	int ret;
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
@@ -706,6 +706,8 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
  * it not only handles the fiemap for inlined files, but also deals
  * with the fast symlink, cause they have no difference for extent
  * mapping per se.
+ *
+ * Must be called with ip_alloc_sem semaphore held.
  */
 static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
 			       struct fiemap_extent_info *fieinfo,
@@ -717,6 +719,7 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
 	u64 phys;
 	u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	lockdep_assert_held_read(&oi->ip_alloc_sem);
 
 	di = (struct ocfs2_dinode *)di_bh->b_data;
 	if (ocfs2_inode_is_fast_symlink(inode))
@@ -732,8 +735,11 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
 			phys += offsetof(struct ocfs2_dinode,
 					 id2.i_data.id_data);
 
+		/* Release the ip_alloc_sem to prevent deadlock on page fault */
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
 		ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
 					      flags);
+		down_read(&OCFS2_I(inode)->ip_alloc_sem);
 		if (ret < 0)
 			return ret;
 	}
@@ -802,9 +808,11 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
 		phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
 		virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
-
+		/* Release the ip_alloc_sem to prevent deadlock on page fault */
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
 		ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
 					      len_bytes, fe_flags);
+		down_read(&OCFS2_I(inode)->ip_alloc_sem);
 		if (ret)
 			break;
 
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
@@ -393,7 +393,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
 	if (proc_alloc_inum(&dp->low_ino))
 		goto out_free_entry;
 
-	pde_set_flags(dp);
+	if (!S_ISDIR(dp->mode))
+		pde_set_flags(dp);
 
 	write_lock(&proc_subdir_lock);
 	dp->parent = dir;
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
@@ -18,23 +18,42 @@
 #define KASAN_ABI_VERSION 5
 
 /*
+ * Clang 22 added preprocessor macros to match GCC, in hopes of eventually
+ * dropping __has_feature support for sanitizers:
+ * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c
+ * Create these macros for older versions of clang so that it is easy to clean
+ * up once the minimum supported version of LLVM for building the kernel always
+ * creates these macros.
+ *
  * Note: Checking __has_feature(*_sanitizer) is only true if the feature is
  * enabled. Therefore it is not required to additionally check defined(CONFIG_*)
  * to avoid adding redundant attributes in other configurations.
  */
+#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__)
+#define __SANITIZE_ADDRESS__
+#endif
+#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__)
+#define __SANITIZE_HWADDRESS__
+#endif
+#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__)
+#define __SANITIZE_THREAD__
+#endif
 
-#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer)
-/* Emulate GCC's __SANITIZE_ADDRESS__ flag */
+/*
+ * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel.
+ */
+#ifdef __SANITIZE_HWADDRESS__
 #define __SANITIZE_ADDRESS__
+#endif
+
+#ifdef __SANITIZE_ADDRESS__
 #define __no_sanitize_address \
 		__attribute__((no_sanitize("address", "hwaddress")))
 #else
 #define __no_sanitize_address
 #endif
 
-#if __has_feature(thread_sanitizer)
-/* emulate gcc's __SANITIZE_THREAD__ flag */
-#define __SANITIZE_THREAD__
+#ifdef __SANITIZE_THREAD__
 #define __no_sanitize_thread \
 		__attribute__((no_sanitize("thread")))
 #else
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
@@ -562,7 +562,7 @@ static inline void kasan_init_hw_tags(void) { }
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
 void kasan_populate_early_vm_area_shadow(void *start, unsigned long size);
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask);
 void kasan_release_vmalloc(unsigned long start, unsigned long end,
 			   unsigned long free_region_start,
 			   unsigned long free_region_end,
@@ -574,7 +574,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start,
 						       unsigned long size)
 { }
 static inline int kasan_populate_vmalloc(unsigned long start,
-					unsigned long size)
+					unsigned long size, gfp_t gfp_mask)
 {
 	return 0;
 }
@@ -610,7 +610,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start,
 static inline void kasan_populate_early_vm_area_shadow(void *start,
 						       unsigned long size) { }
 static inline int kasan_populate_vmalloc(unsigned long start,
-					unsigned long size)
+					unsigned long size, gfp_t gfp_mask)
 {
 	return 0;
 }
diff --git a/init/main.c b/init/main.c
@@ -956,6 +956,7 @@ void start_kernel(void)
 	sort_main_extable();
 	trap_init();
 	mm_core_init();
+	maple_tree_init();
 	poking_init();
 	ftrace_init();
 
@@ -973,7 +974,6 @@ void start_kernel(void)
 		 "Interrupts were enabled *very* early, fixing it\n"))
 		local_irq_disable();
 	radix_tree_init();
-	maple_tree_init();
 
 	/*
 	 * Set up housekeeping before setting up workqueues to allow the unbound
diff --git a/mm/damon/core.c b/mm/damon/core.c
@@ -2111,6 +2111,10 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
 	if (!quota->ms && !quota->sz && list_empty(&quota->goals))
 		return;
 
+	/* First charge window */
+	if (!quota->total_charged_sz && !quota->charged_from)
+		quota->charged_from = jiffies;
+
 	/* New charge window starts */
 	if (time_after_eq(jiffies, quota->charged_from +
 				msecs_to_jiffies(quota->reset_interval))) {
diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
@@ -198,6 +198,11 @@ static int damon_lru_sort_apply_parameters(void)
 	if (err)
 		return err;
 
+	if (!damon_lru_sort_mon_attrs.sample_interval) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = damon_set_attrs(ctx, &damon_lru_sort_mon_attrs);
 	if (err)
 		goto out;
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
@@ -194,6 +194,11 @@ static int damon_reclaim_apply_parameters(void)
 	if (err)
 		return err;
 
+	if (!damon_reclaim_mon_attrs.aggr_interval) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = damon_set_attrs(param_ctx, &damon_reclaim_mon_attrs);
 	if (err)
 		goto out;
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
@@ -1260,14 +1260,18 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 {
 	struct damon_sysfs_kdamond *kdamond = container_of(kobj,
 			struct damon_sysfs_kdamond, kobj);
-	struct damon_ctx *ctx = kdamond->damon_ctx;
-	bool running;
+	struct damon_ctx *ctx;
+	bool running = false;
 
-	if (!ctx)
-		running = false;
-	else
+	if (!mutex_trylock(&damon_sysfs_lock))
+		return -EBUSY;
+
+	ctx = kdamond->damon_ctx;
+	if (ctx)
 		running = damon_is_running(ctx);
 
+	mutex_unlock(&damon_sysfs_lock);
+
 	return sysfs_emit(buf, "%s\n", running ?
 			damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] :
 			damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
@@ -5851,7 +5851,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
-	bool adjust_reservation = false;
+	bool adjust_reservation;
 	unsigned long last_addr_mask;
 	bool force_flush = false;
 
@@ -5944,21 +5944,24 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 					sz);
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		hugetlb_remove_rmap(folio);
+		spin_unlock(ptl);
 
 		/*
 		 * Restore the reservation for anonymous page, otherwise the
 		 * backing page could be stolen by someone.
 		 * If there we are freeing a surplus, do not set the restore
 		 * reservation bit.
 		 */
+		adjust_reservation = false;
+
+		spin_lock_irq(&hugetlb_lock);
 		if (!h->surplus_huge_pages && __vma_private_lock(vma) &&
 		    folio_test_anon(folio)) {
 			folio_set_hugetlb_restore_reserve(folio);
 			/* Reservation to be adjusted after the spin lock */
 			adjust_reservation = true;
 		}
-
-		spin_unlock(ptl);
+		spin_unlock_irq(&hugetlb_lock);
 
 		/*
 		 * Adjust the reservation for the region that will have the
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
@@ -336,13 +336,13 @@ static void ___free_pages_bulk(struct page **pages, int nr_pages)
 	}
 }
 
-static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
+static int ___alloc_pages_bulk(struct page **pages, int nr_pages, gfp_t gfp_mask)
 {
 	unsigned long nr_populated, nr_total = nr_pages;
 	struct page **page_array = pages;
 
 	while (nr_pages) {
-		nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages);
+		nr_populated = alloc_pages_bulk(gfp_mask, nr_pages, pages);
 		if (!nr_populated) {
 			___free_pages_bulk(page_array, nr_total - nr_pages);
 			return -ENOMEM;
@@ -354,25 +354,42 @@ static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
 	return 0;
 }
 
-static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
+static int __kasan_populate_vmalloc(unsigned long start, unsigned long end, gfp_t gfp_mask)
 {
 	unsigned long nr_pages, nr_total = PFN_UP(end - start);
 	struct vmalloc_populate_data data;
+	unsigned int flags;
 	int ret = 0;
 
-	data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	data.pages = (struct page **)__get_free_page(gfp_mask | __GFP_ZERO);
 	if (!data.pages)
 		return -ENOMEM;
 
 	while (nr_total) {
 		nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0]));
-		ret = ___alloc_pages_bulk(data.pages, nr_pages);
+		ret = ___alloc_pages_bulk(data.pages, nr_pages, gfp_mask);
 		if (ret)
 			break;
 
 		data.start = start;
+
+		/*
+		 * page tables allocations ignore external gfp mask, enforce it
+		 * by the scope API
+		 */
+		if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+			flags = memalloc_nofs_save();
+		else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+			flags = memalloc_noio_save();
+
 		ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE,
 					  kasan_populate_vmalloc_pte, &data);
+
+		if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+			memalloc_nofs_restore(flags);
+		else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+			memalloc_noio_restore(flags);
+
 		___free_pages_bulk(data.pages, nr_pages);
 		if (ret)
 			break;
@@ -386,7 +403,7 @@ static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
 	return ret;
 }
 
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask)
 {
 	unsigned long shadow_start, shadow_end;
 	int ret;
@@ -415,7 +432,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 	shadow_start = PAGE_ALIGN_DOWN(shadow_start);
 	shadow_end = PAGE_ALIGN(shadow_end);
 
-	ret = __kasan_populate_vmalloc(shadow_start, shadow_end);
+	ret = __kasan_populate_vmalloc(shadow_start, shadow_end, gfp_mask);
 	if (ret)
 		return ret;
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
@@ -1417,8 +1417,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 		 */
 		if (cc->is_khugepaged &&
 		    (pte_young(pteval) || folio_test_young(folio) ||
-		     folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
-								     address)))
+		     folio_test_referenced(folio) ||
+		     mmu_notifier_test_young(vma->vm_mm, _address)))
 			referenced++;
 	}
 	if (!writable) {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
diff --git a/mm/mremap.c b/mm/mremap.c
diff --git a/mm/percpu.c b/mm/percpu.c
diff --git a/mm/vmalloc.c b/mm/vmalloc.c

Original file line number	Diff line number	Diff line change
`@@ -94,7 +94,7 @@ int load_other_segments(struct kimage *image,`
`94`	`94`	`char *initrd, unsigned long initrd_len,`
`95`	`95`	`char *cmdline)`
`96`	`96`	`{`
`97`		`- struct kexec_buf kbuf;`
	`97`	`+ struct kexec_buf kbuf = {};`
`98`	`98`	`void *dtb = NULL;`
`99`	`99`	`unsigned long initrd_load_addr = 0, dtb_len,`
`100`	`100`	`orig_segments = image->nr_segments;`
Original file line number	Diff line number	Diff line change
`@@ -16,7 +16,7 @@`
`16`	`16`	`static int kexec_file_add_kernel_elf(struct kimage *image,`
`17`	`17`	`struct s390_load_data *data)`
`18`	`18`	`{`
`19`		`- struct kexec_buf buf;`
	`19`	`+ struct kexec_buf buf = {};`
`20`	`20`	`const Elf_Ehdr *ehdr;`
`21`	`21`	`const Elf_Phdr *phdr;`
`22`	`22`	`Elf_Addr entry;`
Original file line number	Diff line number	Diff line change
`@@ -562,7 +562,7 @@ static inline void kasan_init_hw_tags(void) { }`
`562`	`562`	`#if defined(CONFIG_KASAN_GENERIC) \|\| defined(CONFIG_KASAN_SW_TAGS)`
`563`	`563`
`564`	`564`	`void kasan_populate_early_vm_area_shadow(void *start, unsigned long size);`
`565`		`-int kasan_populate_vmalloc(unsigned long addr, unsigned long size);`
	`565`	`+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask);`
`566`	`566`	`void kasan_release_vmalloc(unsigned long start, unsigned long end,`
`567`	`567`	`unsigned long free_region_start,`
`568`	`568`	`unsigned long free_region_end,`
`@@ -574,7 +574,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start,`
`574`	`574`	`unsigned long size)`
`575`	`575`	`{ }`
`576`	`576`	`static inline int kasan_populate_vmalloc(unsigned long start,`
`577`		`- unsigned long size)`
	`577`	`+ unsigned long size, gfp_t gfp_mask)`
`578`	`578`	`{`
`579`	`579`	`return 0;`
`580`	`580`	`}`
`@@ -610,7 +610,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start,`
`610`	`610`	`static inline void kasan_populate_early_vm_area_shadow(void *start,`
`611`	`611`	`unsigned long size) { }`
`612`	`612`	`static inline int kasan_populate_vmalloc(unsigned long start,`
`613`		`- unsigned long size)`
	`613`	`+ unsigned long size, gfp_t gfp_mask)`
`614`	`614`	`{`
`615`	`615`	`return 0;`
`616`	`616`	`}`