Merge branch 'mm-hotfixes-stable' into mm-stable

.mailmap

@@ -29,6 +29,7 @@ Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electr
 Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
 Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
 Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alex Hung <alexhung@gmail.com> <alex.hung@canonical.com>
 Alex Shi <alexs@kernel.org> <alex.shi@intel.com>
 Alex Shi <alexs@kernel.org> <alex.shi@linaro.org>
 Alex Shi <alexs@kernel.org> <alex.shi@linux.alibaba.com>
@@ -382,6 +383,7 @@ Santosh Shilimkar <santosh.shilimkar@oracle.org>
 Santosh Shilimkar <ssantosh@kernel.org>
 Sarangdhar Joshi <spjoshi@codeaurora.org>
 Sascha Hauer <s.hauer@pengutronix.de>
+Satya Priya <quic_c_skakit@quicinc.com> <skakit@codeaurora.org>
 S.Çağlar Onur <caglar@pardus.org.tr>
 Sean Christopherson <seanjc@google.com> <sean.j.christopherson@intel.com>
 Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>

Documentation/dev-tools/kmsan.rst

@@ -67,6 +67,7 @@ uninitialized in the local variable, as well as the stack where the value was
 copied to another memory location before use.
 
 A use of uninitialized value ``v`` is reported by KMSAN in the following cases:
+
  - in a condition, e.g. ``if (v) { ... }``;
  - in an indexing or pointer dereferencing, e.g. ``array[v]`` or ``*v``;
  - when it is copied to userspace or hardware, e.g. ``copy_to_user(..., &v, ...)``;

MAINTAINERS

@@ -10288,7 +10288,7 @@ T:	git https://github.com/intel/gvt-linux.git
 F:	drivers/gpu/drm/i915/gvt/
 
 INTEL HID EVENT DRIVER
-M:	Alex Hung <alex.hung@canonical.com>
+M:	Alex Hung <alexhung@gmail.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/intel/hid.c

arch/loongarch/include/asm/pgtable.h

@@ -480,6 +480,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_ACCESSED);

arch/mips/include/asm/pgtable.h

@@ -620,6 +620,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_ACCESSED);

arch/riscv/include/asm/pgtable.h

@@ -600,6 +600,7 @@ static inline int pmd_dirty(pmd_t pmd)
 	return pte_dirty(pmd_pte(pmd));
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return pte_young(pmd_pte(pmd));

arch/s390/include/asm/pgtable.h

@@ -763,6 +763,7 @@ static inline int pmd_dirty(pmd_t pmd)
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;

arch/sparc/include/asm/pgtable_64.h

@@ -693,6 +693,7 @@ static inline unsigned long pmd_dirty(pmd_t pmd)
 	return pte_dirty(pte);
 }
 
+#define pmd_young pmd_young
 static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));

arch/x86/include/asm/pgtable.h

@@ -139,6 +139,7 @@ static inline int pmd_dirty(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_DIRTY;
 }
 
+#define pmd_young pmd_young
 static inline int pmd_young(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_ACCESSED;
@@ -1438,6 +1439,14 @@ static inline bool arch_has_hw_pte_young(void)
 	return true;
 }
 
+#ifdef CONFIG_XEN_PV
+#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young
+static inline bool arch_has_hw_nonleaf_pmd_young(void)
+{
+	return !cpu_feature_enabled(X86_FEATURE_XENPV);
+}
+#endif
+
 #ifdef CONFIG_PAGE_TABLE_CHECK
 static inline bool pte_user_accessible_page(pte_t pte)
 {

arch/x86/kernel/traps.c

@@ -15,6 +15,7 @@
 #include <linux/context_tracking.h>
 #include <linux/interrupt.h>
 #include <linux/kallsyms.h>
+#include <linux/kmsan.h>
 #include <linux/spinlock.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
@@ -301,6 +302,12 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 {
 	bool handled = false;
 
+	/*
+	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
+	 * is a rare case that uses @regs without passing them to
+	 * irqentry_enter().
+	 */
+	kmsan_unpoison_entry_regs(regs);
 	if (!is_valid_bugaddr(regs->ip))
 		return handled;
 

arch/x86/lib/usercopy.c

@@ -6,6 +6,7 @@
 
 #include <linux/uaccess.h>
 #include <linux/export.h>
+#include <linux/instrumented.h>
 
 #include <asm/tlbflush.h>
 
@@ -44,7 +45,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	 * called from other contexts.
 	 */
 	pagefault_disable();
+	instrument_copy_from_user_before(to, from, n);
 	ret = raw_copy_from_user(to, from, n);
+	instrument_copy_from_user_after(to, from, n, ret);
 	pagefault_enable();
 
 	return ret;

arch/x86/mm/hugetlbpage.c

@@ -37,8 +37,12 @@ int pmd_huge(pmd_t pmd)
  */
 int pud_huge(pud_t pud)
 {
+#if CONFIG_PGTABLE_LEVELS > 2
 	return !pud_none(pud) &&
 		(pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
+#else
+	return 0;
+#endif
 }
 
 #ifdef CONFIG_HUGETLB_PAGE

drivers/gpu/drm/amd/display/Kconfig

@@ -5,6 +5,7 @@ menu "Display Engine Configuration"
 config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
+	depends on BROKEN || !CC_IS_CLANG || X86_64 || SPARC64 || ARM64
 	select SND_HDA_COMPONENT if SND_HDA_CORE
 	select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128)
 	help
@@ -12,6 +13,12 @@ config DRM_AMD_DC
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
+	  calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 || ARM64)
+	  architectures built with Clang (all released versions), whereby the stack
+	  frame gets blown up to well over 5k.  This would cause an immediate kernel
+	  panic on most architectures.  We'll revert this when the following bug report
+	  has been resolved: https://github.com/llvm/llvm-project/issues/41896.
+
 config DRM_AMD_DC_DCN
 	def_bool n
 	help

fs/btrfs/compression.c

@@ -512,7 +512,7 @@ static u64 bio_end_offset(struct bio *bio)
 static noinline int add_ra_bio_pages(struct inode *inode,
 				     u64 compressed_end,
 				     struct compressed_bio *cb,
-				     unsigned long *pflags)
+				     int *memstall, unsigned long *pflags)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	unsigned long end_index;
@@ -581,8 +581,10 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			continue;
 		}
 
-		if (PageWorkingset(page))
+		if (!*memstall && PageWorkingset(page)) {
 			psi_memstall_enter(pflags);
+			*memstall = 1;
+		}
 
 		ret = set_page_extent_mapped(page);
 		if (ret < 0) {
@@ -670,8 +672,8 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	u64 em_len;
 	u64 em_start;
 	struct extent_map *em;
-	/* Initialize to 1 to make skip psi_memstall_leave unless needed */
-	unsigned long pflags = 1;
+	unsigned long pflags;
+	int memstall = 0;
 	blk_status_t ret;
 	int ret2;
 	int i;
@@ -727,7 +729,7 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		goto fail;
 	}
 
-	add_ra_bio_pages(inode, em_start + em_len, cb, &pflags);
+	add_ra_bio_pages(inode, em_start + em_len, cb, &memstall, &pflags);
 
 	/* include any pages we added in add_ra-bio_pages */
 	cb->len = bio->bi_iter.bi_size;
@@ -807,7 +809,7 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		}
 	}
 
-	if (!pflags)
+	if (memstall)
 		psi_memstall_leave(&pflags);
 
 	if (refcount_dec_and_test(&cb->pending_ios))

fs/erofs/zdata.c

@@ -1412,8 +1412,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	struct block_device *last_bdev;
 	unsigned int nr_bios = 0;
 	struct bio *bio = NULL;
-	/* initialize to 1 to make skip psi_memstall_leave unless needed */
-	unsigned long pflags = 1;
+	unsigned long pflags;
+	int memstall = 0;
 
 	bi_private = jobqueueset_init(sb, q, fgq, force_fg);
 	qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
@@ -1463,14 +1463,18 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 			if (bio && (cur != last_index + 1 ||
 				    last_bdev != mdev.m_bdev)) {
 submit_bio_retry:
-				if (!pflags)
-					psi_memstall_leave(&pflags);
 				submit_bio(bio);
+				if (memstall) {
+					psi_memstall_leave(&pflags);
+					memstall = 0;
+				}
 				bio = NULL;
 			}
 
-			if (unlikely(PageWorkingset(page)))
+			if (unlikely(PageWorkingset(page)) && !memstall) {
 				psi_memstall_enter(&pflags);
+				memstall = 1;
+			}
 
 			if (!bio) {
 				bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
@@ -1500,9 +1504,9 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);
 
 	if (bio) {
-		if (!pflags)
-			psi_memstall_leave(&pflags);
 		submit_bio(bio);
+		if (memstall)
+			psi_memstall_leave(&pflags);
 	}
 
 	/*

fs/hugetlbfs/inode.c

@@ -328,6 +328,12 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		} else {
 			unlock_page(page);
 
+			if (PageHWPoison(page)) {
+				put_page(page);
+				retval = -EIO;
+				break;
+			}
+
 			/*
 			 * We have the page, copy it to user space buffer.
 			 */
@@ -1111,13 +1117,6 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 static int hugetlbfs_error_remove_page(struct address_space *mapping,
 				struct page *page)
 {
-	struct inode *inode = mapping->host;
-	pgoff_t index = page->index;
-
-	hugetlb_delete_from_page_cache(page);
-	if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
-		hugetlb_fix_reserve_counts(inode);
-
 	return 0;
 }
 

fs/nilfs2/dat.c

@@ -111,6 +111,13 @@ static void nilfs_dat_commit_free(struct inode *dat,
 	kunmap_atomic(kaddr);
 
 	nilfs_dat_commit_entry(dat, req);
+
+	if (unlikely(req->pr_desc_bh == NULL || req->pr_bitmap_bh == NULL)) {
+		nilfs_error(dat->i_sb,
+			    "state inconsistency probably due to duplicate use of vblocknr = %llu",
+			    (unsigned long long)req->pr_entry_nr);
+		return;
+	}
 	nilfs_palloc_commit_free_entry(dat, req);
 }
 

fs/nilfs2/segment.c

@@ -317,7 +317,7 @@ void nilfs_relax_pressure_in_lock(struct super_block *sb)
 	struct the_nilfs *nilfs = sb->s_fs_info;
 	struct nilfs_sc_info *sci = nilfs->ns_writer;
 
-	if (!sci || !sci->sc_flush_request)
+	if (sb_rdonly(sb) || unlikely(!sci) || !sci->sc_flush_request)
 		return;
 
 	set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags);
@@ -2242,7 +2242,7 @@ int nilfs_construct_segment(struct super_block *sb)
 	struct nilfs_sc_info *sci = nilfs->ns_writer;
 	struct nilfs_transaction_info *ti;
 
-	if (!sci)
+	if (sb_rdonly(sb) || unlikely(!sci))
 		return -EROFS;
 
 	/* A call inside transactions causes a deadlock. */
@@ -2280,7 +2280,7 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
 	struct nilfs_transaction_info ti;
 	int err = 0;
 
-	if (!sci)
+	if (sb_rdonly(sb) || unlikely(!sci))
 		return -EROFS;
 
 	nilfs_transaction_lock(sb, &ti, 0);
@@ -2776,11 +2776,12 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
 
 	if (nilfs->ns_writer) {
 		/*
-		 * This happens if the filesystem was remounted
-		 * read/write after nilfs_error degenerated it into a
-		 * read-only mount.
+		 * This happens if the filesystem is made read-only by
+		 * __nilfs_error or nilfs_remount and then remounted
+		 * read/write.  In these cases, reuse the existing
+		 * writer.
 		 */
-		nilfs_detach_log_writer(sb);
+		return 0;
 	}
 
 	nilfs->ns_writer = nilfs_segctor_new(sb, root);

fs/nilfs2/sufile.c

@@ -495,14 +495,22 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
 {
 	struct buffer_head *bh;
+	void *kaddr;
+	struct nilfs_segment_usage *su;
 	int ret;
 
+	down_write(&NILFS_MDT(sufile)->mi_sem);
 	ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
 	if (!ret) {
 		mark_buffer_dirty(bh);
 		nilfs_mdt_mark_dirty(sufile);
+		kaddr = kmap_atomic(bh->b_page);
+		su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
+		nilfs_segment_usage_set_dirty(su);
+		kunmap_atomic(kaddr);
 		brelse(bh);
 	}
+	up_write(&NILFS_MDT(sufile)->mi_sem);
 	return ret;
 }
 

fs/nilfs2/super.c

@@ -1133,8 +1133,6 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 	if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
 		goto out;
 	if (*flags & SB_RDONLY) {
-		/* Shutting down log writer */
-		nilfs_detach_log_writer(sb);
 		sb->s_flags |= SB_RDONLY;
 
 		/*

fs/nilfs2/the_nilfs.c

@@ -690,9 +690,7 @@ int nilfs_count_free_blocks(struct the_nilfs *nilfs, sector_t *nblocks)
 {
 	unsigned long ncleansegs;
 
-	down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
 	ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile);
-	up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
 	*nblocks = (sector_t)ncleansegs * nilfs->ns_blocks_per_segment;
 	return 0;
 }

fs/proc/meminfo.c

@@ -115,7 +115,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #endif
 	show_val_kb(m, "PageTables:     ",
 		    global_node_page_state(NR_PAGETABLE));
-	show_val_kb(m, "SecPageTables:	",
+	show_val_kb(m, "SecPageTables:  ",
 		    global_node_page_state(NR_SECONDARY_PAGETABLE));
 
 	show_val_kb(m, "NFS_Unstable:   ", 0);

include/asm-generic/tlb.h

@@ -222,12 +222,16 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 #define tlb_needs_table_invalidate() (true)
 #endif
 
+void tlb_remove_table_sync_one(void);
+
 #else
 
 #ifdef tlb_needs_table_invalidate
 #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
 #endif
 
+static inline void tlb_remove_table_sync_one(void) { }
+
 #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
 

include/linux/fault-inject.h

@@ -20,7 +20,6 @@ struct fault_attr {
 	atomic_t space;
 	unsigned long verbose;
 	bool task_filter;
-	bool no_warn;
 	unsigned long stacktrace_depth;
 	unsigned long require_start;
 	unsigned long require_end;
@@ -32,6 +31,10 @@ struct fault_attr {
 	struct dentry *dname;
 };
 
+enum fault_flags {
+	FAULT_NOWARN =	1 << 0,
+};
+
 #define FAULT_ATTR_INITIALIZER {					\
 		.interval = 1,						\
 		.times = ATOMIC_INIT(1),				\
@@ -40,11 +43,11 @@ struct fault_attr {
 		.ratelimit_state = RATELIMIT_STATE_INIT_DISABLED,	\
 		.verbose = 2,						\
 		.dname = NULL,						\
-		.no_warn = false,					\
 	}
 
 #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER
 int setup_fault_attr(struct fault_attr *attr, char *str);
+bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags);
 bool should_fail(struct fault_attr *attr, ssize_t size);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

include/linux/gfp.h

@@ -210,6 +210,20 @@ alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct p
 	return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array);
 }
 
+static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
+{
+	gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN);
+
+	if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN))
+		return;
+
+	if (node_online(this_node))
+		return;
+
+	pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node);
+	dump_stack();
+}
+
 /*
  * Allocate pages, preferring the node given as nid. The node must be valid and
  * online. For more general interface, see alloc_pages_node().
@@ -218,7 +232,7 @@ static inline struct page *
 __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid));
+	warn_if_node_offline(nid, gfp_mask);
 
 	return __alloc_pages(gfp_mask, order, nid, NULL);
 }
@@ -227,7 +241,7 @@ static inline
 struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid));
+	warn_if_node_offline(nid, gfp);
 
 	return __folio_alloc(gfp, order, nid, NULL);
 }

include/linux/maple_tree.h

@@ -638,6 +638,12 @@ static inline void mt_set_in_rcu(struct maple_tree *mt)
 	}
 }
 
+static inline unsigned int mt_height(const struct maple_tree *mt)
+
+{
+	return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET;
+}
+
 void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max);
 void *mt_find_after(struct maple_tree *mt, unsigned long *index,
 		    unsigned long max);
@@ -664,6 +670,7 @@ extern atomic_t maple_tree_tests_passed;
 
 void mt_dump(const struct maple_tree *mt);
 void mt_validate(struct maple_tree *mt);
+void mt_cache_shrink(void);
 #define MT_BUG_ON(__tree, __x) do {					\
 	atomic_inc(&maple_tree_tests_run);				\
 	if (__x) {							\

include/linux/mm.h

@@ -1853,6 +1853,25 @@ static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodem
 	__show_free_areas(flags, nodemask, MAX_NR_ZONES - 1);
 }
 
+/*
+ * Parameter block passed down to zap_pte_range in exceptional cases.
+ */
+struct zap_details {
+	struct folio *single_folio;	/* Locked folio to be unmapped */
+	bool even_cows;			/* Zap COWed private pages too? */
+	zap_flags_t zap_flags;		/* Extra flags for zapping */
+};
+
+/*
+ * Whether to drop the pte markers, for example, the uffd-wp information for
+ * file-backed memory.  This should only be specified when we will completely
+ * drop the page in the mm, either by truncation or unmapping of the vma.  By
+ * default, the flag is not set.
+ */
+#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
+/* Set in unmap_vmas() to indicate a final unmap call.  Only used by hugetlb */
+#define  ZAP_FLAG_UNMAP              ((__force zap_flags_t) BIT(1))
+
 #ifdef CONFIG_MMU
 extern bool can_do_mlock(void);
 #else
@@ -1870,6 +1889,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		  unsigned long size);
 void zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		    unsigned long size);
+void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
+			   unsigned long size, struct zap_details *details);
 void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		struct vm_area_struct *start_vma, unsigned long start,
 		unsigned long end);
@@ -3493,12 +3514,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
-/*
- * Whether to drop the pte markers, for example, the uffd-wp information for
- * file-backed memory.  This should only be specified when we will completely
- * drop the page in the mm, either by truncation or unmapping of the vma.  By
- * default, the flag is not set.
- */
-#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
-
 #endif /* _LINUX_MM_H */

include/linux/pgtable.h

@@ -165,6 +165,13 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr)
 	return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
 }
 
+#ifndef pmd_young
+static inline int pmd_young(pmd_t pmd)
+{
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pte_t *ptep,
@@ -260,6 +267,17 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef arch_has_hw_nonleaf_pmd_young
+/*
+ * Return whether the accessed bit in non-leaf PMD entries is supported on the
+ * local CPU.
+ */
+static inline bool arch_has_hw_nonleaf_pmd_young(void)
+{
+	return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG);
+}
+#endif
+
 #ifndef arch_has_hw_pte_young
 /*
  * Return whether the accessed bit is supported on the local CPU.

include/trace/events/huge_memory.h

@@ -171,15 +171,15 @@ TRACE_EVENT(mm_collapse_huge_page_swapin,
 
 TRACE_EVENT(mm_khugepaged_scan_file,
 
-	TP_PROTO(struct mm_struct *mm, struct page *page, const char *filename,
+	TP_PROTO(struct mm_struct *mm, struct page *page, struct file *file,
 		 int present, int swap, int result),
 
-	TP_ARGS(mm, page, filename, present, swap, result),
+	TP_ARGS(mm, page, file, present, swap, result),
 
 	TP_STRUCT__entry(
 		__field(struct mm_struct *, mm)
 		__field(unsigned long, pfn)
-		__string(filename, filename)
+		__string(filename, file->f_path.dentry->d_iname)
 		__field(int, present)
 		__field(int, swap)
 		__field(int, result)
@@ -188,7 +188,7 @@ TRACE_EVENT(mm_khugepaged_scan_file,
 	TP_fast_assign(
 		__entry->mm = mm;
 		__entry->pfn = page ? page_to_pfn(page) : -1;
-		__assign_str(filename, filename);
+		__assign_str(filename, file->f_path.dentry->d_iname);
 		__entry->present = present;
 		__entry->swap = swap;
 		__entry->result = result;

ipc/shm.c

@@ -275,10 +275,8 @@ static inline void shm_rmid(struct shmid_kernel *s)
 }
 
 
-static int __shm_open(struct vm_area_struct *vma)
+static int __shm_open(struct shm_file_data *sfd)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
 	struct shmid_kernel *shp;
 
 	shp = shm_lock(sfd->ns, sfd->id);
@@ -302,7 +300,15 @@ static int __shm_open(struct vm_area_struct *vma)
 /* This is called by fork, once for every shm attach. */
 static void shm_open(struct vm_area_struct *vma)
 {
-	int err = __shm_open(vma);
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+	int err;
+
+	/* Always call underlying open if present */
+	if (sfd->vm_ops->open)
+		sfd->vm_ops->open(vma);
+
+	err = __shm_open(sfd);
 	/*
 	 * We raced in the idr lookup or with shm_destroy().
 	 * Either way, the ID is busted.
@@ -359,10 +365,8 @@ static bool shm_may_destroy(struct shmid_kernel *shp)
  * The descriptor has already been removed from the current->mm->mmap list
  * and will later be kfree()d.
  */
-static void shm_close(struct vm_area_struct *vma)
+static void __shm_close(struct shm_file_data *sfd)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
 	struct shmid_kernel *shp;
 	struct ipc_namespace *ns = sfd->ns;
 
@@ -388,6 +392,18 @@ static void shm_close(struct vm_area_struct *vma)
 	up_write(&shm_ids(ns).rwsem);
 }
 
+static void shm_close(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	/* Always call underlying close if present */
+	if (sfd->vm_ops->close)
+		sfd->vm_ops->close(vma);
+
+	__shm_close(sfd);
+}
+
 /* Called with ns->shm_ids(ns).rwsem locked */
 static int shm_try_destroy_orphaned(int id, void *p, void *data)
 {
@@ -583,13 +599,13 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	 * IPC ID that was removed, and possibly even reused by another shm
 	 * segment already.  Propagate this case as an error to caller.
 	 */
-	ret = __shm_open(vma);
+	ret = __shm_open(sfd);
 	if (ret)
 		return ret;
 
 	ret = call_mmap(sfd->file, vma);
 	if (ret) {
-		shm_close(vma);
+		__shm_close(sfd);
 		return ret;
 	}
 	sfd->vm_ops = vma->vm_ops;

kernel/gcov/clang.c

@@ -280,6 +280,8 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
 
 		for (i = 0; i < sfn_ptr->num_counters; i++)
 			dfn_ptr->counters[i] += sfn_ptr->counters[i];
+
+		sfn_ptr = list_next_entry(sfn_ptr, head);
 	}
 }
 

lib/Kconfig.debug

@@ -395,12 +395,13 @@ endif # DEBUG_INFO
 config FRAME_WARN
 	int "Warn for stack frames larger than"
 	range 0 8192
+	default 0 if KMSAN
 	default 2048 if GCC_PLUGIN_LATENT_ENTROPY
 	default 2048 if PARISC
 	default 1536 if (!64BIT && XTENSA)
+	default 1280 if KASAN && !64BIT
 	default 1024 if !64BIT
 	default 2048 if 64BIT
-	default 0 if KMSAN
 	help
 	  Tell the compiler to warn at build time for stack frames larger than this.
 	  Setting this too low will cause a lot of warnings.
@@ -2107,6 +2108,7 @@ config KPROBES_SANITY_TEST
 	depends on DEBUG_KERNEL
 	depends on KPROBES
 	depends on KUNIT
+	select STACKTRACE if ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	default KUNIT_ALL_TESTS
 	help
 	  This option provides for testing basic kprobes functionality on
@@ -2241,6 +2243,10 @@ config TEST_UUID
 config TEST_XARRAY
 	tristate "Test the XArray code at runtime"
 
+config TEST_MAPLE_TREE
+	select DEBUG_MAPLE_TREE
+	tristate "Test the Maple Tree code at runtime"
+
 config TEST_RHASHTABLE
 	tristate "Perform selftest on resizable hash table"
 	help

lib/Kconfig.kmsan

@@ -12,6 +12,7 @@ config KMSAN
 	bool "KMSAN: detector of uninitialized values use"
 	depends on HAVE_ARCH_KMSAN && HAVE_KMSAN_COMPILER
 	depends on SLUB && DEBUG_KERNEL && !KASAN && !KCSAN
+	depends on !PREEMPT_RT
 	select STACKDEPOT
 	select STACKDEPOT_ALWAYS_INIT
 	help

lib/Makefile

@@ -85,6 +85,7 @@ obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
 obj-$(CONFIG_TEST_STRSCPY) += test_strscpy.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
 obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
+obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o
 obj-$(CONFIG_TEST_PARMAN) += test_parman.o
 obj-$(CONFIG_TEST_KMOD) += test_kmod.o
 obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o

lib/fault-inject.c

@@ -41,9 +41,6 @@ EXPORT_SYMBOL_GPL(setup_fault_attr);
 
 static void fail_dump(struct fault_attr *attr)
 {
-	if (attr->no_warn)
-		return;
-
 	if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) {
 		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n"
 		       "name %pd, interval %lu, probability %lu, "
@@ -103,7 +100,7 @@ static inline bool fail_stacktrace(struct fault_attr *attr)
  * http://www.nongnu.org/failmalloc/
  */
 
-bool should_fail(struct fault_attr *attr, ssize_t size)
+bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags)
 {
 	if (in_task()) {
 		unsigned int fail_nth = READ_ONCE(current->fail_nth);
@@ -146,13 +143,19 @@ bool should_fail(struct fault_attr *attr, ssize_t size)
 		return false;
 
 fail:
-	fail_dump(attr);
+	if (!(flags & FAULT_NOWARN))
+		fail_dump(attr);
 
 	if (atomic_read(&attr->times) != -1)
 		atomic_dec_not_zero(&attr->times);
 
 	return true;
 }
+
+bool should_fail(struct fault_attr *attr, ssize_t size)
+{
+	return should_fail_ex(attr, size, 0);
+}
 EXPORT_SYMBOL_GPL(should_fail);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

lib/maple_tree.c

@@ -183,10 +183,6 @@ static void ma_free_rcu(struct maple_node *node)
 	call_rcu(&node->rcu, mt_free_rcu);
 }
 
-static unsigned int mt_height(const struct maple_tree *mt)
-{
-	return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET;
-}
 
 static void mas_set_height(struct ma_state *mas)
 {
@@ -1209,7 +1205,6 @@ static inline void mas_push_node(struct ma_state *mas, struct maple_node *used)
 static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp)
 {
 	struct maple_alloc *node;
-	struct maple_alloc **nodep = &mas->alloc;
 	unsigned long allocated = mas_allocated(mas);
 	unsigned long success = allocated;
 	unsigned int requested = mas_alloc_req(mas);
@@ -1263,8 +1258,7 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp)
 			node->node_count--;
 
 		success += count;
-		nodep = &node->slot[0];
-		node = *nodep;
+		node = node->slot[0];
 		requested -= count;
 	}
 	mas->alloc->total = success;
@@ -1357,6 +1351,7 @@ static inline struct maple_enode *mas_start(struct ma_state *mas)
 		root = mas_root(mas);
 		/* Tree with nodes */
 		if (likely(xa_is_node(root))) {
+			mas->depth = 1;
 			mas->node = mte_safe_root(root);
 			return NULL;
 		}
@@ -3608,8 +3603,7 @@ static inline int mas_commit_b_node(struct ma_wr_state *wr_mas,
 	node = mas_pop_node(wr_mas->mas);
 	node->parent = mas_mn(wr_mas->mas)->parent;
 	wr_mas->mas->node = mt_mk_node(node, b_type);
-	mab_mas_cp(b_node, 0, b_end, wr_mas->mas, true);
-
+	mab_mas_cp(b_node, 0, b_end, wr_mas->mas, false);
 	mas_replace(wr_mas->mas, false);
 reuse_node:
 	mas_update_gap(wr_mas->mas);
@@ -3733,7 +3727,6 @@ static bool mas_is_span_wr(struct ma_wr_state *wr_mas)
 
 static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas)
 {
-	wr_mas->mas->depth++;
 	wr_mas->type = mte_node_type(wr_mas->mas->node);
 	mas_wr_node_walk(wr_mas);
 	wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type);
@@ -3745,6 +3738,7 @@ static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas)
 	wr_mas->mas->min = wr_mas->r_min;
 	wr_mas->mas->node = wr_mas->content;
 	wr_mas->mas->offset = 0;
+	wr_mas->mas->depth++;
 }
 /*
  * mas_wr_walk() - Walk the tree for a write.
@@ -4970,8 +4964,9 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size)
 {
 	enum maple_type type = mte_node_type(mas->node);
 	unsigned long pivot, min, gap = 0;
-	unsigned char count, offset;
-	unsigned long *gaps = NULL, *pivots = ma_pivots(mas_mn(mas), type);
+	unsigned char offset;
+	unsigned long *gaps;
+	unsigned long *pivots = ma_pivots(mas_mn(mas), type);
 	void __rcu **slots = ma_slots(mas_mn(mas), type);
 	bool found = false;
 
@@ -4982,9 +4977,8 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size)
 
 	gaps = ma_gaps(mte_to_node(mas->node), type);
 	offset = mas->offset;
-	count = mt_slots[type];
 	min = mas_safe_min(mas, pivots, offset);
-	for (; offset < count; offset++) {
+	for (; offset < mt_slots[type]; offset++) {
 		pivot = mas_safe_pivot(mas, pivots, offset, type);
 		if (offset && !pivot)
 			break;
@@ -5010,8 +5004,6 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size)
 				mas->min = min;
 				mas->max = pivot;
 				offset = 0;
-				type = mte_node_type(mas->node);
-				count = mt_slots[type];
 				break;
 			}
 		}
@@ -5065,6 +5057,7 @@ void *mas_walk(struct ma_state *mas)
 
 	return entry;
 }
+EXPORT_SYMBOL_GPL(mas_walk);
 
 static inline bool mas_rewind_node(struct ma_state *mas)
 {
@@ -5276,6 +5269,7 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 	mas->last = mas->index + size - 1;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mas_empty_area);
 
 /*
  * mas_empty_area_rev() - Get the highest address within the range that is
@@ -5339,6 +5333,7 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
 	mas->index = mas->last - size + 1;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mas_empty_area_rev);
 
 static inline int mas_alloc(struct ma_state *mas, void *entry,
 		unsigned long size, unsigned long *index)
@@ -5660,6 +5655,7 @@ void *mas_store(struct ma_state *mas, void *entry)
 	mas_wr_store_entry(&wr_mas);
 	return wr_mas.content;
 }
+EXPORT_SYMBOL_GPL(mas_store);
 
 /**
  * mas_store_gfp() - Store a value into the tree.
@@ -5686,6 +5682,7 @@ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mas_store_gfp);
 
 /**
  * mas_store_prealloc() - Store a value into the tree using memory
@@ -5703,6 +5700,7 @@ void mas_store_prealloc(struct ma_state *mas, void *entry)
 	BUG_ON(mas_is_err(mas));
 	mas_destroy(mas);
 }
+EXPORT_SYMBOL_GPL(mas_store_prealloc);
 
 /**
  * mas_preallocate() - Preallocate enough nodes for a store operation
@@ -5772,6 +5770,7 @@ void mas_destroy(struct ma_state *mas)
 	}
 	mas->alloc = NULL;
 }
+EXPORT_SYMBOL_GPL(mas_destroy);
 
 /*
  * mas_expected_entries() - Set the expected number of entries that will be inserted.
@@ -5833,6 +5832,7 @@ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries)
 	return ret;
 
 }
+EXPORT_SYMBOL_GPL(mas_expected_entries);
 
 /**
  * mas_next() - Get the next entry.
@@ -6013,6 +6013,7 @@ void *mas_find(struct ma_state *mas, unsigned long max)
 	/* Retries on dead nodes handled by mas_next_entry */
 	return mas_next_entry(mas, max);
 }
+EXPORT_SYMBOL_GPL(mas_find);
 
 /**
  * mas_find_rev: On the first call, find the first non-null entry at or below
@@ -6059,7 +6060,7 @@ void *mas_find_rev(struct ma_state *mas, unsigned long min)
 	/* Retries on dead nodes handled by mas_next_entry */
 	return mas_prev_entry(mas, min);
 }
-EXPORT_SYMBOL_GPL(mas_find);
+EXPORT_SYMBOL_GPL(mas_find_rev);
 
 /**
  * mas_erase() - Find the range in which index resides and erase the entire
@@ -6541,8 +6542,27 @@ static inline int mas_dead_node(struct ma_state *mas, unsigned long index)
 	mas_rewalk(mas, index);
 	return 1;
 }
-#endif /* not defined __KERNEL__ */
 
+void mt_cache_shrink(void)
+{
+}
+#else
+/*
+ * mt_cache_shrink() - For testing, don't use this.
+ *
+ * Certain testcases can trigger an OOM when combined with other memory
+ * debugging configuration options.  This function is used to reduce the
+ * possibility of an out of memory even due to kmem_cache objects remaining
+ * around for longer than usual.
+ */
+void mt_cache_shrink(void)
+{
+	kmem_cache_shrink(maple_node_cache);
+
+}
+EXPORT_SYMBOL_GPL(mt_cache_shrink);
+
+#endif /* not defined __KERNEL__ */
 /*
  * mas_get_slot() - Get the entry in the maple state node stored at @offset.
  * @mas: The maple state
@@ -6816,6 +6836,7 @@ void mt_dump(const struct maple_tree *mt)
 	else if (entry)
 		mt_dump_node(mt, entry, 0, mt_max[mte_node_type(entry)], 0);
 }
+EXPORT_SYMBOL_GPL(mt_dump);
 
 /*
  * Calculate the maximum gap in a node and check if that's what is reported in
@@ -7126,5 +7147,6 @@ void mt_validate(struct maple_tree *mt)
 	rcu_read_unlock();
 
 }
+EXPORT_SYMBOL_GPL(mt_validate);
 
 #endif /* CONFIG_DEBUG_MAPLE_TREE */

mm/compaction.c

@@ -984,29 +984,29 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			goto isolate_fail;
 		}
 
+		/*
+		 * Be careful not to clear PageLRU until after we're
+		 * sure the page is not being freed elsewhere -- the
+		 * page release code relies on it.
+		 */
+		if (unlikely(!get_page_unless_zero(page)))
+			goto isolate_fail;
+
 		/*
 		 * Migration will fail if an anonymous page is pinned in memory,
 		 * so avoid taking lru_lock and isolating it unnecessarily in an
 		 * admittedly racy check.
 		 */
 		mapping = page_mapping(page);
-		if (!mapping && page_count(page) > page_mapcount(page))
-			goto isolate_fail;
+		if (!mapping && (page_count(page) - 1) > total_mapcount(page))
+			goto isolate_fail_put;
 
 		/*
 		 * Only allow to migrate anonymous pages in GFP_NOFS context
 		 * because those do not depend on fs locks.
 		 */
 		if (!(cc->gfp_mask & __GFP_FS) && mapping)
-			goto isolate_fail;
-
-		/*
-		 * Be careful not to clear PageLRU until after we're
-		 * sure the page is not being freed elsewhere -- the
-		 * page release code relies on it.
-		 */
-		if (unlikely(!get_page_unless_zero(page)))
-			goto isolate_fail;
+			goto isolate_fail_put;
 
 		/* Only take pages on LRU: a check now makes later tests safe */
 		if (!PageLRU(page))

mm/damon/dbgfs.c

@@ -890,6 +890,7 @@ static ssize_t dbgfs_mk_context_write(struct file *file,
 static int dbgfs_rm_context(char *name)
 {
 	struct dentry *root, *dir, **new_dirs;
+	struct inode *inode;
 	struct damon_ctx **new_ctxs;
 	int i, j;
 	int ret = 0;
@@ -905,6 +906,12 @@ static int dbgfs_rm_context(char *name)
 	if (!dir)
 		return -ENOENT;
 
+	inode = d_inode(dir);
+	if (!S_ISDIR(inode->i_mode)) {
+		ret = -EINVAL;
+		goto out_dput;
+	}
+
 	new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs),
 			GFP_KERNEL);
 	if (!new_dirs) {

mm/damon/sysfs.c

@@ -2283,12 +2283,54 @@ static struct damos *damon_sysfs_mk_scheme(
 			&wmarks);
 }
 
+static void damon_sysfs_update_scheme(struct damos *scheme,
+		struct damon_sysfs_scheme *sysfs_scheme)
+{
+	struct damon_sysfs_access_pattern *access_pattern =
+		sysfs_scheme->access_pattern;
+	struct damon_sysfs_quotas *sysfs_quotas = sysfs_scheme->quotas;
+	struct damon_sysfs_weights *sysfs_weights = sysfs_quotas->weights;
+	struct damon_sysfs_watermarks *sysfs_wmarks = sysfs_scheme->watermarks;
+
+	scheme->pattern.min_sz_region = access_pattern->sz->min;
+	scheme->pattern.max_sz_region = access_pattern->sz->max;
+	scheme->pattern.min_nr_accesses = access_pattern->nr_accesses->min;
+	scheme->pattern.max_nr_accesses = access_pattern->nr_accesses->max;
+	scheme->pattern.min_age_region = access_pattern->age->min;
+	scheme->pattern.max_age_region = access_pattern->age->max;
+
+	scheme->action = sysfs_scheme->action;
+
+	scheme->quota.ms = sysfs_quotas->ms;
+	scheme->quota.sz = sysfs_quotas->sz;
+	scheme->quota.reset_interval = sysfs_quotas->reset_interval_ms;
+	scheme->quota.weight_sz = sysfs_weights->sz;
+	scheme->quota.weight_nr_accesses = sysfs_weights->nr_accesses;
+	scheme->quota.weight_age = sysfs_weights->age;
+
+	scheme->wmarks.metric = sysfs_wmarks->metric;
+	scheme->wmarks.interval = sysfs_wmarks->interval_us;
+	scheme->wmarks.high = sysfs_wmarks->high;
+	scheme->wmarks.mid = sysfs_wmarks->mid;
+	scheme->wmarks.low = sysfs_wmarks->low;
+}
+
 static int damon_sysfs_set_schemes(struct damon_ctx *ctx,
 		struct damon_sysfs_schemes *sysfs_schemes)
 {
-	int i;
+	struct damos *scheme, *next;
+	int i = 0;
 
-	for (i = 0; i < sysfs_schemes->nr; i++) {
+	damon_for_each_scheme_safe(scheme, next, ctx) {
+		if (i < sysfs_schemes->nr)
+			damon_sysfs_update_scheme(scheme,
+					sysfs_schemes->schemes_arr[i]);
+		else
+			damon_destroy_scheme(scheme);
+		i++;
+	}
+
+	for (; i < sysfs_schemes->nr; i++) {
 		struct damos *scheme, *next;
 
 		scheme = damon_sysfs_mk_scheme(sysfs_schemes->schemes_arr[i]);
@@ -2339,6 +2381,10 @@ static int damon_sysfs_upd_schemes_stats(struct damon_sysfs_kdamond *kdamond)
 	damon_for_each_scheme(scheme, ctx) {
 		struct damon_sysfs_stats *sysfs_stats;
 
+		/* user could have removed the scheme sysfs dir */
+		if (schemes_idx >= sysfs_schemes->nr)
+			break;
+
 		sysfs_stats = sysfs_schemes->schemes_arr[schemes_idx++]->stats;
 		sysfs_stats->nr_tried = scheme->stat.nr_tried;
 		sysfs_stats->sz_tried = scheme->stat.sz_tried;

mm/failslab.c

@@ -16,6 +16,8 @@ static struct {
 
 bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
+	int flags = 0;
+
 	/* No fault-injection for bootstrap cache */
 	if (unlikely(s == kmem_cache))
 		return false;
@@ -30,10 +32,16 @@ bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 	if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB))
 		return false;
 
+	/*
+	 * In some cases, it expects to specify __GFP_NOWARN
+	 * to avoid printing any information(not just a warning),
+	 * thus avoiding deadlocks. See commit 6b9dbedbe349 for
+	 * details.
+	 */
 	if (gfpflags & __GFP_NOWARN)
-		failslab.attr.no_warn = true;
+		flags |= FAULT_NOWARN;
 
-	return should_fail(&failslab.attr, s->object_size);
+	return should_fail_ex(&failslab.attr, s->object_size, flags);
 }
 
 static int __init setup_failslab(char *str)

mm/huge_memory.c

@@ -2206,9 +2206,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_wrprotect(entry);
 			if (!young)
 				entry = pte_mkold(entry);
-			/* NOTE: this may set soft-dirty too on some archs */
-			if (dirty)
-				entry = pte_mkdirty(entry);
+			/*
+			 * NOTE: we don't do pte_mkdirty when dirty==true
+			 * because it breaks sparc64 which can sigsegv
+			 * random process.  Need to revisit when we figure
+			 * out what is special with sparc64.
+			 */
 			if (soft_dirty)
 				entry = pte_mksoft_dirty(entry);
 			if (uffd_wp)

mm/hugetlb.c

@@ -1800,6 +1800,7 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order,
 
 	/* we rely on prep_new_huge_page to set the destructor */
 	set_compound_order(page, order);
+	__ClearPageReserved(page);
 	__SetPageHead(page);
 	for (i = 0; i < nr_pages; i++) {
 		p = nth_page(page, i);
@@ -1816,7 +1817,8 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order,
 		 * on the head page when they need know if put_page() is needed
 		 * after get_user_pages().
 		 */
-		__ClearPageReserved(p);
+		if (i != 0)	/* head page cleared above */
+			__ClearPageReserved(p);
 		/*
 		 * Subtle and very unlikely
 		 *
@@ -5199,17 +5201,22 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 
 	__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
 
-	/*
-	 * Unlock and free the vma lock before releasing i_mmap_rwsem.  When
-	 * the vma_lock is freed, this makes the vma ineligible for pmd
-	 * sharing.  And, i_mmap_rwsem is required to set up pmd sharing.
-	 * This is important as page tables for this unmapped range will
-	 * be asynchrously deleted.  If the page tables are shared, there
-	 * will be issues when accessed by someone else.
-	 */
-	__hugetlb_vma_unlock_write_free(vma);
-
-	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
+		/*
+		 * Unlock and free the vma lock before releasing i_mmap_rwsem.
+		 * When the vma_lock is freed, this makes the vma ineligible
+		 * for pmd sharing.  And, i_mmap_rwsem is required to set up
+		 * pmd sharing.  This is important as page tables for this
+		 * unmapped range will be asynchrously deleted.  If the page
+		 * tables are shared, there will be issues when accessed by
+		 * someone else.
+		 */
+		__hugetlb_vma_unlock_write_free(vma);
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+	} else {
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+		hugetlb_vma_unlock_write(vma);
+	}
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
@@ -6103,6 +6110,10 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 	ptl = huge_pte_lock(h, dst_mm, dst_pte);
 
+	ret = -EIO;
+	if (PageHWPoison(page))
+		goto out_release_unlock;
+
 	/*
 	 * We allow to overwrite a pte marker: consider when both MISSING|WP
 	 * registered, we firstly wr-protect a none pte which has no page cache

mm/hugetlb_vmemmap.c

@@ -11,6 +11,7 @@
 #define pr_fmt(fmt)	"HugeTLB: " fmt
 
 #include <linux/pgtable.h>
+#include <linux/moduleparam.h>
 #include <linux/bootmem_info.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>

mm/kfence/report.c

@@ -75,18 +75,23 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 
 		if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfence_") ||
 		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kfence_") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmem_cache_free") ||
 		    !strncmp(buf, ARCH_FUNC_PREFIX "__slab_free", len)) {
 			/*
-			 * In case of tail calls from any of the below
-			 * to any of the above.
+			 * In case of tail calls from any of the below to any of
+			 * the above, optimized by the compiler such that the
+			 * stack trace would omit the initial entry point below.
 			 */
 			fallback = skipnr + 1;
 		}
 
-		/* Also the *_bulk() variants by only checking prefixes. */
+		/*
+		 * The below list should only include the initial entry points
+		 * into the slab allocators. Includes the *_bulk() variants by
+		 * checking prefixes.
+		 */
 		if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfree") ||
 		    str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_free") ||
-		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmem_cache_free") ||
 		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmalloc") ||
 		    str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_alloc"))
 			goto found;

mm/khugepaged.c

@@ -97,8 +97,8 @@ struct collapse_control {
 	/* Num pages scanned per node */
 	u32 node_load[MAX_NUMNODES];
 
-	/* Last target selected in hpage_collapse_find_target_node() */
-	int last_target_node;
+	/* nodemask for allocation fallback */
+	nodemask_t alloc_nmask;
 };
 
 /**
@@ -734,7 +734,6 @@ static void khugepaged_alloc_sleep(void)
 
 struct collapse_control khugepaged_collapse_control = {
 	.is_khugepaged = true,
-	.last_target_node = NUMA_NO_NODE,
 };
 
 static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc)
@@ -783,16 +782,11 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc)
 			target_node = nid;
 		}
 
-	/* do some balance if several nodes have the same hit record */
-	if (target_node <= cc->last_target_node)
-		for (nid = cc->last_target_node + 1; nid < MAX_NUMNODES;
-		     nid++)
-			if (max_value == cc->node_load[nid]) {
-				target_node = nid;
-				break;
-			}
+	for_each_online_node(nid) {
+		if (max_value == cc->node_load[nid])
+			node_set(nid, cc->alloc_nmask);
+	}
 
-	cc->last_target_node = target_node;
 	return target_node;
 }
 #else
@@ -802,9 +796,10 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc)
 }
 #endif
 
-static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node)
+static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node,
+				      nodemask_t *nmask)
 {
-	*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
+	*hpage = __alloc_pages(gfp, HPAGE_PMD_ORDER, node, nmask);
 	if (unlikely(!*hpage)) {
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 		return false;
@@ -955,12 +950,11 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
 static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm,
 			      struct collapse_control *cc)
 {
-	/* Only allocate from the target node */
 	gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() :
-		     GFP_TRANSHUGE) | __GFP_THISNODE;
+		     GFP_TRANSHUGE);
 	int node = hpage_collapse_find_target_node(cc);
 
-	if (!hpage_collapse_alloc_page(hpage, gfp, node))
+	if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask))
 		return SCAN_ALLOC_HUGE_PAGE_FAIL;
 	if (unlikely(mem_cgroup_charge(page_folio(*hpage), mm, gfp)))
 		return SCAN_CGROUP_CHARGE_FAIL;
@@ -1057,6 +1051,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	_pmd = pmdp_collapse_flush(vma, address, pmd);
 	spin_unlock(pmd_ptl);
 	mmu_notifier_invalidate_range_end(&range);
+	tlb_remove_table_sync_one();
 
 	spin_lock(pte_ptl);
 	result =  __collapse_huge_page_isolate(vma, address, pte, cc,
@@ -1144,6 +1139,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 		goto out;
 
 	memset(cc->node_load, 0, sizeof(cc->node_load));
+	nodes_clear(cc->alloc_nmask);
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
@@ -1384,16 +1380,43 @@ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr,
 	return SCAN_SUCCEED;
 }
 
+/*
+ * A note about locking:
+ * Trying to take the page table spinlocks would be useless here because those
+ * are only used to synchronize:
+ *
+ *  - modifying terminal entries (ones that point to a data page, not to another
+ *    page table)
+ *  - installing *new* non-terminal entries
+ *
+ * Instead, we need roughly the same kind of protection as free_pgtables() or
+ * mm_take_all_locks() (but only for a single VMA):
+ * The mmap lock together with this VMA's rmap locks covers all paths towards
+ * the page table entries we're messing with here, except for hardware page
+ * table walks and lockless_pages_from_mm().
+ */
 static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 				  unsigned long addr, pmd_t *pmdp)
 {
-	spinlock_t *ptl;
 	pmd_t pmd;
+	struct mmu_notifier_range range;
 
 	mmap_assert_write_locked(mm);
-	ptl = pmd_lock(vma->vm_mm, pmdp);
+	if (vma->vm_file)
+		lockdep_assert_held_write(&vma->vm_file->f_mapping->i_mmap_rwsem);
+	/*
+	 * All anon_vmas attached to the VMA have the same root and are
+	 * therefore locked by the same lock.
+	 */
+	if (vma->anon_vma)
+		lockdep_assert_held_write(&vma->anon_vma->root->rwsem);
+
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, addr,
+				addr + HPAGE_PMD_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
 	pmd = pmdp_collapse_flush(vma, addr, pmdp);
-	spin_unlock(ptl);
+	tlb_remove_table_sync_one();
+	mmu_notifier_invalidate_range_end(&range);
 	mm_dec_nr_ptes(mm);
 	page_table_check_pte_clear_range(mm, addr, pmd);
 	pte_free(mm, pmd_pgtable(pmd));
@@ -1444,6 +1467,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
 		return SCAN_VMA_CHECK;
 
+	/*
+	 * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings
+	 * that got written to. Without this, we'd have to also lock the
+	 * anon_vma if one exists.
+	 */
+	if (vma->anon_vma)
+		return SCAN_VMA_CHECK;
+
 	/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
 	if (userfaultfd_wp(vma))
 		return SCAN_PTE_UFFD_WP;
@@ -1477,6 +1508,20 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		goto drop_hpage;
 	}
 
+	/*
+	 * We need to lock the mapping so that from here on, only GUP-fast and
+	 * hardware page walks can access the parts of the page tables that
+	 * we're operating on.
+	 * See collapse_and_free_pmd().
+	 */
+	i_mmap_lock_write(vma->vm_file->f_mapping);
+
+	/*
+	 * This spinlock should be unnecessary: Nobody else should be accessing
+	 * the page tables under spinlock protection here, only
+	 * lockless_pages_from_mm() and the hardware page walker can access page
+	 * tables while all the high-level locks are held in write mode.
+	 */
 	start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
 	result = SCAN_FAIL;
 
@@ -1531,6 +1576,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	/* step 4: remove pte entries */
 	collapse_and_free_pmd(mm, vma, haddr, pmd);
 
+	i_mmap_unlock_write(vma->vm_file->f_mapping);
+
 maybe_install_pmd:
 	/* step 5: install pmd entry */
 	result = install_pmd
@@ -1544,6 +1591,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 
 abort:
 	pte_unmap_unlock(start_pte, ptl);
+	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	goto drop_hpage;
 }
 
@@ -1600,7 +1648,8 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff,
 		 * An alternative would be drop the check, but check that page
 		 * table is clear before calling pmdp_collapse_flush() under
 		 * ptl. It has higher chance to recover THP for the VMA, but
-		 * has higher cost too.
+		 * has higher cost too. It would also probably require locking
+		 * the anon_vma.
 		 */
 		if (vma->anon_vma) {
 			result = SCAN_PAGE_ANON;
@@ -2077,6 +2126,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 	present = 0;
 	swap = 0;
 	memset(cc->node_load, 0, sizeof(cc->node_load));
+	nodes_clear(cc->alloc_nmask);
 	rcu_read_lock();
 	xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) {
 		if (xas_retry(&xas, page))
@@ -2157,8 +2207,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 		}
 	}
 
-	trace_mm_khugepaged_scan_file(mm, page, file->f_path.dentry->d_iname,
-				      present, swap, result);
+	trace_mm_khugepaged_scan_file(mm, page, file, present, swap, result);
 	return result;
 }
 #else
@@ -2576,7 +2625,6 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	if (!cc)
 		return -ENOMEM;
 	cc->is_khugepaged = false;
-	cc->last_target_node = NUMA_NO_NODE;
 
 	mmgrab(mm);
 	lru_add_drain_all();
@@ -2602,6 +2650,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		}
 		mmap_assert_locked(mm);
 		memset(cc->node_load, 0, sizeof(cc->node_load));
+		nodes_clear(cc->alloc_nmask);
 		if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) {
 			struct file *file = get_file(vma->vm_file);
 			pgoff_t pgoff = linear_page_index(vma, addr);

mm/kmsan/kmsan.h

@@ -124,6 +124,8 @@ static __always_inline bool kmsan_in_runtime(void)
 {
 	if ((hardirq_count() >> HARDIRQ_SHIFT) > 1)
 		return true;
+	if (in_nmi())
+		return true;
 	return kmsan_get_context()->kmsan_in_runtime;
 }
 

mm/madvise.c

@@ -772,8 +772,8 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
  * Application no longer needs these pages.  If the pages are dirty,
  * it's OK to just throw them away.  The app will be more careful about
  * data it wants to keep.  Be sure to free swap resources too.  The
- * zap_page_range call sets things up for shrink_active_list to actually free
- * these pages later if no one else has touched them in the meantime,
+ * zap_page_range_single call sets things up for shrink_active_list to actually
+ * free these pages later if no one else has touched them in the meantime,
  * although we could add these pages to a global reuse list for
  * shrink_active_list to pick up before reclaiming other pages.
  *
@@ -790,7 +790,7 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
 					unsigned long start, unsigned long end)
 {
-	zap_page_range(vma, start, end - start);
+	zap_page_range_single(vma, start, end - start, NULL);
 	return 0;
 }
 

mm/memcontrol.c

@@ -3026,7 +3026,7 @@ struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
 {
 	struct obj_cgroup *objcg;
 
-	if (!memcg_kmem_enabled() || memcg_kmem_bypass())
+	if (!memcg_kmem_enabled())
 		return NULL;
 
 	if (PageMemcgKmem(page)) {

mm/memory-failure.c

@@ -1093,6 +1093,7 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 	int res;
 	struct page *hpage = compound_head(p);
 	struct address_space *mapping;
+	bool extra_pins = false;
 
 	if (!PageHuge(hpage))
 		return MF_DELAYED;
@@ -1100,6 +1101,8 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 	mapping = page_mapping(hpage);
 	if (mapping) {
 		res = truncate_error_page(hpage, page_to_pfn(p), mapping);
+		/* The page is kept in page cache. */
+		extra_pins = true;
 		unlock_page(hpage);
 	} else {
 		unlock_page(hpage);
@@ -1117,7 +1120,7 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 		}
 	}
 
-	if (has_extra_refcount(ps, p, false))
+	if (has_extra_refcount(ps, p, extra_pins))
 		res = MF_FAILED;
 
 	return res;

mm/memory.c

@@ -1341,15 +1341,6 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 	return ret;
 }
 
-/*
- * Parameter block passed down to zap_pte_range in exceptional cases.
- */
-struct zap_details {
-	struct folio *single_folio;	/* Locked folio to be unmapped */
-	bool even_cows;			/* Zap COWed private pages too? */
-	zap_flags_t zap_flags;		/* Extra flags for zapping */
-};
-
 /* Whether we should zap all COWed (private) pages too */
 static inline bool should_zap_cows(struct zap_details *details)
 {
@@ -1718,7 +1709,7 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 {
 	struct mmu_notifier_range range;
 	struct zap_details details = {
-		.zap_flags = ZAP_FLAG_DROP_MARKER,
+		.zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP,
 		/* Careful - we need to zap private pages too! */
 		.even_cows = true,
 	};
@@ -1772,19 +1763,27 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
  *
  * The range must fit into one VMA.
  */
-static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
+void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *details)
 {
+	const unsigned long end = address + size;
 	struct mmu_notifier_range range;
 	struct mmu_gather tlb;
 
 	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
-				address, address + size);
+				address, end);
+	if (is_vm_hugetlb_page(vma))
+		adjust_range_if_pmd_sharing_possible(vma, &range.start,
+						     &range.end);
 	tlb_gather_mmu(&tlb, vma->vm_mm);
 	update_hiwater_rss(vma->vm_mm);
 	mmu_notifier_invalidate_range_start(&range);
-	unmap_single_vma(&tlb, vma, address, range.end, details);
+	/*
+	 * unmap 'address-end' not 'range.start-range.end' as range
+	 * could have been expanded for hugetlb pmd sharing.
+	 */
+	unmap_single_vma(&tlb, vma, address, end, details);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
 }
@@ -3761,7 +3760,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			 */
 			get_page(vmf->page);
 			pte_unmap_unlock(vmf->pte, vmf->ptl);
-			vmf->page->pgmap->ops->migrate_to_ram(vmf);
+			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
 			put_page(vmf->page);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;

mm/memremap.c

@@ -335,6 +335,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			WARN(1, "File system DAX not supported\n");
 			return ERR_PTR(-EINVAL);
 		}
+		params.pgprot = pgprot_decrypted(params.pgprot);
 		break;
 	case MEMORY_DEVICE_GENERIC:
 		break;

mm/migrate_device.c

@@ -357,7 +357,8 @@ static bool migrate_vma_check_page(struct page *page, struct page *fault_page)
 }
 
 /*
- * Unmaps pages for migration. Returns number of unmapped pages.
+ * Unmaps pages for migration. Returns number of source pfns marked as
+ * migrating.
  */
 static unsigned long migrate_device_unmap(unsigned long *src_pfns,
 					  unsigned long npages,
@@ -373,8 +374,11 @@ static unsigned long migrate_device_unmap(unsigned long *src_pfns,
 		struct page *page = migrate_pfn_to_page(src_pfns[i]);
 		struct folio *folio;
 
-		if (!page)
+		if (!page) {
+			if (src_pfns[i] & MIGRATE_PFN_MIGRATE)
+				unmapped++;
 			continue;
+		}
 
 		/* ZONE_DEVICE pages are not on LRU */
 		if (!is_zone_device_page(page)) {

mm/mmap.c

@@ -456,7 +456,7 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas)
  * vma_mas_szero() - Set a given range to zero.  Used when modifying a
  * vm_area_struct start or end.
  *
- * @mm: The struct_mm
+ * @mas: The maple tree ma_state
  * @start: The start address to zero
  * @end: The end address to zero.
  */
@@ -2674,6 +2674,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		error = -EINVAL;
 		if (file)
 			goto close_and_free_vma;
+		else if (vma->vm_file)
+			goto unmap_and_free_vma;
 		else
 			goto free_vma;
 	}
@@ -2682,6 +2684,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		error = -ENOMEM;
 		if (file)
 			goto close_and_free_vma;
+		else if (vma->vm_file)
+			goto unmap_and_free_vma;
 		else
 			goto free_vma;
 	}
@@ -2751,7 +2755,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 
 	/* Undo any partial mapping done by a device driver. */
 	unmap_region(mm, mas.tree, vma, prev, next, vma->vm_start, vma->vm_end);
-	if (vm_flags & VM_SHARED)
+	if (file && (vm_flags & VM_SHARED))
 		mapping_unmap_writable(file->f_mapping);
 free_vma:
 	vm_area_free(vma);

mm/mmu_gather.c

@@ -153,7 +153,7 @@ static void tlb_remove_table_smp_sync(void *arg)
 	/* Simply deliver the interrupt */
 }
 
-static void tlb_remove_table_sync_one(void)
+void tlb_remove_table_sync_one(void)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
@@ -177,8 +177,6 @@ static void tlb_remove_table_free(struct mmu_table_batch *batch)
 
 #else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
-static void tlb_remove_table_sync_one(void) { }
-
 static void tlb_remove_table_free(struct mmu_table_batch *batch)
 {
 	__tlb_remove_table_free(batch);

mm/page_alloc.c

@@ -3887,6 +3887,8 @@ __setup("fail_page_alloc=", setup_fail_page_alloc);
 
 static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
+	int flags = 0;
+
 	if (order < fail_page_alloc.min_order)
 		return false;
 	if (gfp_mask & __GFP_NOFAIL)
@@ -3897,10 +3899,11 @@ static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 			(gfp_mask & __GFP_DIRECT_RECLAIM))
 		return false;
 
+	/* See comment in __should_failslab() */
 	if (gfp_mask & __GFP_NOWARN)
-		fail_page_alloc.attr.no_warn = true;
+		flags |= FAULT_NOWARN;
 
-	return should_fail(&fail_page_alloc.attr, 1 << order);
+	return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags);
 }
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

mm/page_ext.c

@@ -166,7 +166,7 @@ struct page_ext *page_ext_get(struct page *page)
 
 /**
  * page_ext_put() - Working with page extended information is done.
- * @page_ext - Page extended information received from page_ext_get().
+ * @page_ext: Page extended information received from page_ext_get().
  *
  * The page extended information of the page may not be valid after this
  * function is called.

mm/swapfile.c

@@ -973,23 +973,23 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 scan:
 	spin_unlock(&si->lock);
 	while (++offset <= READ_ONCE(si->highest_bit)) {
-		if (swap_offset_available_and_locked(si, offset))
-			goto checks;
 		if (unlikely(--latency_ration < 0)) {
 			cond_resched();
 			latency_ration = LATENCY_LIMIT;
 			scanned_many = true;
 		}
+		if (swap_offset_available_and_locked(si, offset))
+			goto checks;
 	}
 	offset = si->lowest_bit;
 	while (offset < scan_base) {
-		if (swap_offset_available_and_locked(si, offset))
-			goto checks;
 		if (unlikely(--latency_ration < 0)) {
 			cond_resched();
 			latency_ration = LATENCY_LIMIT;
 			scanned_many = true;
 		}
+		if (swap_offset_available_and_locked(si, offset))
+			goto checks;
 		offset++;
 	}
 	spin_lock(&si->lock);

mm/userfaultfd.c

@@ -64,7 +64,7 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 	pte_t _dst_pte, *dst_pte;
 	bool writable = dst_vma->vm_flags & VM_WRITE;
 	bool vm_shared = dst_vma->vm_flags & VM_SHARED;
-	bool page_in_cache = page->mapping;
+	bool page_in_cache = page_mapping(page);
 	spinlock_t *ptl;
 	struct inode *inode;
 	pgoff_t offset, max_off;

mm/vmscan.c

@@ -2514,8 +2514,20 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 	 * the flushers simply cannot keep up with the allocation
 	 * rate. Nudge the flusher threads in case they are asleep.
 	 */
-	if (stat.nr_unqueued_dirty == nr_taken)
+	if (stat.nr_unqueued_dirty == nr_taken) {
 		wakeup_flusher_threads(WB_REASON_VMSCAN);
+		/*
+		 * For cgroupv1 dirty throttling is achieved by waking up
+		 * the kernel flusher here and later waiting on folios
+		 * which are in writeback to finish (see shrink_folio_list()).
+		 *
+		 * Flusher may not be able to issue writeback quickly
+		 * enough for cgroupv1 writeback throttling to work
+		 * on a large system.
+		 */
+		if (!writeback_throttling_sane(sc))
+			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
+	}
 
 	sc->nr.dirty += stat.nr_dirty;
 	sc->nr.congested += stat.nr_congested;
@@ -3977,7 +3989,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area
 			goto next;
 
 		if (!pmd_trans_huge(pmd[i])) {
-			if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) &&
+			if (arch_has_hw_nonleaf_pmd_young() &&
 			    get_cap(LRU_GEN_NONLEAF_YOUNG))
 				pmdp_test_and_clear_young(vma, addr, pmd + i);
 			goto next;
@@ -4075,14 +4087,14 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
 #endif
 		walk->mm_stats[MM_NONLEAF_TOTAL]++;
 
-#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
-		if (get_cap(LRU_GEN_NONLEAF_YOUNG)) {
+		if (arch_has_hw_nonleaf_pmd_young() &&
+		    get_cap(LRU_GEN_NONLEAF_YOUNG)) {
 			if (!pmd_young(val))
 				continue;
 
 			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
 		}
-#endif
+
 		if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
 			continue;
 
@@ -4973,10 +4985,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	int scanned;
 	int reclaimed;
 	LIST_HEAD(list);
+	LIST_HEAD(clean);
 	struct folio *folio;
+	struct folio *next;
 	enum vm_event_item item;
 	struct reclaim_stat stat;
 	struct lru_gen_mm_walk *walk;
+	bool skip_retry = false;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
@@ -4993,20 +5008,37 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 
 	if (list_empty(&list))
 		return scanned;
-
+retry:
 	reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false);
+	sc->nr_reclaimed += reclaimed;
 
-	list_for_each_entry(folio, &list, lru) {
-		/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
-		if (folio_test_workingset(folio))
-			folio_set_referenced(folio);
+	list_for_each_entry_safe_reverse(folio, next, &list, lru) {
+		if (!folio_evictable(folio)) {
+			list_del(&folio->lru);
+			folio_putback_lru(folio);
+			continue;
+		}
 
-		/* don't add rejected pages to the oldest generation */
 		if (folio_test_reclaim(folio) &&
-		    (folio_test_dirty(folio) || folio_test_writeback(folio)))
-			folio_clear_active(folio);
-		else
-			folio_set_active(folio);
+		    (folio_test_dirty(folio) || folio_test_writeback(folio))) {
+			/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
+			if (folio_test_workingset(folio))
+				folio_set_referenced(folio);
+			continue;
+		}
+
+		if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) ||
+		    folio_mapped(folio) || folio_test_locked(folio) ||
+		    folio_test_dirty(folio) || folio_test_writeback(folio)) {
+			/* don't add rejected folios to the oldest generation */
+			set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS,
+				      BIT(PG_active));
+			continue;
+		}
+
+		/* retry folios that may have missed folio_rotate_reclaimable() */
+		list_move(&folio->lru, &clean);
+		sc->nr_scanned -= folio_nr_pages(folio);
 	}
 
 	spin_lock_irq(&lruvec->lru_lock);
@@ -5028,7 +5060,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	mem_cgroup_uncharge_list(&list);
 	free_unref_page_list(&list);
 
-	sc->nr_reclaimed += reclaimed;
+	INIT_LIST_HEAD(&list);
+	list_splice_init(&clean, &list);
+
+	if (!list_empty(&list)) {
+		skip_retry = true;
+		goto retry;
+	}
 
 	if (need_swapping && type == LRU_GEN_ANON)
 		*need_swapping = true;
@@ -5356,7 +5394,7 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c
 	if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))
 		caps |= BIT(LRU_GEN_MM_WALK);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG))
+	if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG))
 		caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
 
 	return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps);
@@ -5846,8 +5884,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	enum lru_list lru;
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
+	bool proportional_reclaim;
 	struct blk_plug plug;
-	bool scan_adjusted;
 
 	if (lru_gen_enabled()) {
 		lru_gen_shrink_lruvec(lruvec, sc);
@@ -5870,8 +5908,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	 * abort proportional reclaim if either the file or anon lru has already
 	 * dropped to zero at the first pass.
 	 */
-	scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
-			 sc->priority == DEF_PRIORITY);
+	proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
+				sc->priority == DEF_PRIORITY);
 
 	blk_start_plug(&plug);
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
@@ -5891,7 +5929,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 
 		cond_resched();
 
-		if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
+		if (nr_reclaimed < nr_to_reclaim || proportional_reclaim)
 			continue;
 
 		/*
@@ -5942,8 +5980,6 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		nr_scanned = targets[lru] - nr[lru];
 		nr[lru] = targets[lru] * (100 - percentage) / 100;
 		nr[lru] -= min(nr[lru], nr_scanned);
-
-		scan_adjusted = true;
 	}
 	blk_finish_plug(&plug);
 	sc->nr_reclaimed += nr_reclaimed;

tools/testing/radix-tree/.gitignore

 # SPDX-License-Identifier: GPL-2.0-only
+generated/bit-length.h
 generated/map-shift.h
 idr.c
 idr-test

tools/testing/radix-tree/Makefile

@@ -18,9 +18,14 @@ endif
 ifeq ($(BUILD), 32)
 	CFLAGS += -m32
 	LDFLAGS += -m32
+LONG_BIT := 32
 endif
 
-targets: generated/map-shift.h $(TARGETS)
+ifndef LONG_BIT
+LONG_BIT := $(shell getconf LONG_BIT)
+endif
+
+targets: generated/map-shift.h generated/bit-length.h $(TARGETS)
 
 main:	$(OFILES)
 
@@ -34,11 +39,11 @@ maple: $(CORE_OFILES)
 multiorder: multiorder.o $(CORE_OFILES)
 
 clean:
-	$(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h
+	$(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h generated/bit-length.h
 
 vpath %.c ../../lib
 
-$(OFILES): Makefile *.h */*.h generated/map-shift.h \
+$(OFILES): Makefile *.h */*.h generated/map-shift.h generated/bit-length.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
 	../../../include/linux/xarray.h \
@@ -61,3 +66,11 @@ generated/map-shift.h:
 		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
 	fi
+
+generated/bit-length.h: FORCE
+	@if ! grep -qws CONFIG_$(LONG_BIT)BIT generated/bit-length.h; then   \
+		echo "Generating $@";                                        \
+		echo "#define CONFIG_$(LONG_BIT)BIT 1" > $@;                 \
+	fi
+
+FORCE: ;

tools/testing/radix-tree/generated/autoconf.h

+#include "bit-length.h"
 #define CONFIG_XARRAY_MULTI 1
-#define CONFIG_64BIT 1

tools/testing/radix-tree/linux.c

@@ -129,6 +129,10 @@ void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
 	pthread_mutex_unlock(&cachep->lock);
 }
 
+void kmem_cache_shrink(struct kmem_cache *cachep)
+{
+}
+
 int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
 			  void **p)
 {

tools/vm/slabinfo-gnuplot.sh

@@ -150,7 +150,7 @@ do_preprocess()
 	let lines=3
 	out=`basename "$in"`"-slabs-by-loss"
 	`cat "$in" | grep -A "$lines" 'Slabs sorted by loss' |\
-		egrep -iv '\-\-|Name|Slabs'\
+		grep -E -iv '\-\-|Name|Slabs'\
 		| awk '{print $1" "$4+$2*$3" "$4}' > "$out"`
 	if [ $? -eq 0 ]; then
 		do_slabs_plotting "$out"
@@ -159,7 +159,7 @@ do_preprocess()
 	let lines=3
 	out=`basename "$in"`"-slabs-by-size"
 	`cat "$in" | grep -A "$lines" 'Slabs sorted by size' |\
-		egrep -iv '\-\-|Name|Slabs'\
+		grep -E -iv '\-\-|Name|Slabs'\
 		| awk '{print $1" "$4" "$4-$2*$3}' > "$out"`
 	if [ $? -eq 0 ]; then
 		do_slabs_plotting "$out"