Merge tag 'mm-hotfixes-stable-2023-12-15-07-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
"17 hotfixes. 8 are cc:stable and the other 9 pertain to post-6.6
issues"

* tag 'mm-hotfixes-stable-2023-12-15-07-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
mm/mglru: reclaim offlined memcgs harder
mm/mglru: respect min_ttl_ms with memcgs
mm/mglru: try to stop at high watermarks
mm/mglru: fix underprotected page cache
mm/shmem: fix race in shmem_undo_range w/THP
Revert "selftests: error out if kernel header files are not yet built"
crash_core: fix the check for whether crashkernel is from high memory
x86, kexec: fix the wrong ifdeffery CONFIG_KEXEC
sh, kexec: fix the incorrect ifdeffery and dependency of CONFIG_KEXEC
mips, kexec: fix the incorrect ifdeffery and dependency of CONFIG_KEXEC
m68k, kexec: fix the incorrect ifdeffery and build dependency of CONFIG_KEXEC
loongarch, kexec: change dependency of object files
mm/damon/core: make damon_start() waits until kdamond_fn() starts
selftests/mm: cow: print ksft header before printing anything else
mm: fix VMA heap bounds checking
riscv: fix VMALLOC_START definition
kexec: drop dependency on ARCH_SUPPORTS_KEXEC from CRASH_DUMP

arch/loongarch/kernel/Makefile

···
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o

arch/m68k/include/asm/kexec.h

···
 #ifndef _ASM_M68K_KEXEC_H
 #define _ASM_M68K_KEXEC_H
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /* Maximum physical address we can use pages from */
 #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
···
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* _ASM_M68K_KEXEC_H */

arch/m68k/kernel/Makefile

···
 
 obj-$(CONFIG_M68K_NONCOHERENT_DMA) += dma.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_BOOTINFO_PROC)	+= bootinfo_proc.o
 obj-$(CONFIG_UBOOT)		+= uboot.o
 

arch/mips/cavium-octeon/smp.c

···
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
···
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };

arch/mips/include/asm/kexec.h

···
 		prepare_frametrace(newregs);
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 struct kimage;
 extern unsigned long kexec_args[4];
 extern int (*_machine_kexec_prepare)(struct kimage *);

arch/mips/include/asm/smp-ops.h

···
 	void (*cpu_die)(unsigned int cpu);
 	void (*cleanup_dead_cpu)(unsigned cpu);
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	void (*kexec_nonboot_cpu)(void);
 #endif
 };

arch/mips/include/asm/smp.h

···
 extern void __noreturn play_dead(void);
 #endif
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static inline void kexec_nonboot_cpu(void)
 {
 	extern const struct plat_smp_ops *mp_ops;	/* private */

arch/mips/kernel/Makefile

···
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_EARLY_PRINTK_8250)	+= early_printk_8250.o

arch/mips/kernel/smp-bmips.c

···
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
···
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };

arch/mips/kernel/smp-cps.c

···
 	local_irq_enable();
 }
 
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE)
 
 enum cpu_death {
 	CPU_DEATH_HALT,
···
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 static void cps_kexec_nonboot_cpu(void)
 {
···
 		cps_shutdown_this_cpu(CPU_DEATH_POWER);
 }
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_HOTPLUG_CPU
 
···
 	.cpu_die		= cps_cpu_die,
 	.cleanup_dead_cpu	= cps_cleanup_dead_cpu,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= cps_kexec_nonboot_cpu,
 #endif
 };

arch/mips/loongson64/reset.c

···
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /* 0X80000000~0X80200000 is safe */
 #define MAX_ARGS	64
···
 	_machine_halt = loongson_halt;
 	pm_power_off = loongson_poweroff;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
 	if (WARN_ON(!kexec_argv))
 		return -ENOMEM;

arch/mips/loongson64/smp.c

···
 	.cpu_disable = loongson3_cpu_disable,
 	.cpu_die = loongson3_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
 #endif
 };

arch/riscv/Kconfig

···
 	  If unsure what to do here, say N.
 
 config ARCH_SUPPORTS_KEXEC
-	def_bool MMU
+	def_bool y
 
 config ARCH_SELECTS_KEXEC
 	def_bool y
···
 	select HOTPLUG_CPU if SMP
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool 64BIT && MMU
+	def_bool 64BIT
 
 config ARCH_SELECTS_KEXEC_FILE
 	def_bool y

arch/riscv/include/asm/pgtable.h

···
 #define PAGE_KERNEL		__pgprot(0)
 #define swapper_pg_dir		NULL
 #define TASK_SIZE		0xffffffffUL
-#define VMALLOC_START		0
+#define VMALLOC_START		_AC(0, UL)
 #define VMALLOC_END		TASK_SIZE
 
 #endif /* !CONFIG_MMU */

arch/riscv/kernel/crash_core.c

···
 
 void arch_crash_save_vmcoreinfo(void)
 {
-	VMCOREINFO_NUMBER(VA_BITS);
 	VMCOREINFO_NUMBER(phys_ram_base);
 
 	vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET);
 	vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START);
 	vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END);
+#ifdef CONFIG_MMU
+	VMCOREINFO_NUMBER(VA_BITS);
 	vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START);
 	vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END);
 #ifdef CONFIG_64BIT
 	vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR);
 	vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END);
+#endif
 #endif
 	vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR);
 	vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n",

arch/sh/include/asm/kexec.h

···
 /* The native architecture */
 #define KEXEC_ARCH KEXEC_ARCH_SH
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 /* arch/sh/kernel/machine_kexec.c */
 void reserve_crashkernel(void);
 
···
 }
 #else
 static inline void reserve_crashkernel(void) { }
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* __ASM_SH_KEXEC_H */

arch/sh/kernel/Makefile

···
 obj-$(CONFIG_SH_STANDARD_BIOS)	+= sh_bios.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_MODULES)		+= sh_ksyms_32.o module.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_IO_TRAPPED)	+= io_trapped.o

arch/sh/kernel/reboot.c

···
 	.shutdown	= native_machine_shutdown,
 	.restart	= native_machine_restart,
 	.halt		= native_machine_halt,
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.crash_shutdown = native_machine_crash_shutdown,
 #endif
 };
···
 	machine_ops.halt();
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	machine_ops.crash_shutdown(regs);

arch/sh/kernel/setup.c

···
 	request_resource(res, &code_resource);
 	request_resource(res, &data_resource);
 	request_resource(res, &bss_resource);
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	request_resource(res, &crashk_res);
 #endif
 

arch/x86/boot/compressed/acpi.c

···
 {
 	unsigned long addr = 0;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	char val[MAX_ADDR_LEN] = { };
 	int ret;
 

include/linux/damon.h

···
 	 * update
 	 */
 	unsigned long next_ops_update_sis;
+	/* for waiting until the execution of the kdamond_fn is started */
+	struct completion kdamond_started;
 
 /* public: */
 	struct task_struct *kdamond;

include/linux/mm.h

···
  */
 static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
 {
-       return vma->vm_start <= vma->vm_mm->brk &&
-		vma->vm_end >= vma->vm_mm->start_brk;
+	return vma->vm_start < vma->vm_mm->brk &&
+		vma->vm_end > vma->vm_mm->start_brk;
 }
 
 /*
···
 	 * its "stack".  It's not even well-defined for programs written
 	 * languages like Go.
 	 */
-       return vma->vm_start <= vma->vm_mm->start_stack &&
-	       vma->vm_end >= vma->vm_mm->start_stack;
+	return vma->vm_start <= vma->vm_mm->start_stack &&
+		vma->vm_end >= vma->vm_mm->start_stack;
 }
 
 static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)

include/linux/mm_inline.h

···
 	if (folio_test_unevictable(folio) || !lrugen->enabled)
 		return false;
 	/*
-	 * There are three common cases for this page:
-	 * 1. If it's hot, e.g., freshly faulted in or previously hot and
-	 *    migrated, add it to the youngest generation.
-	 * 2. If it's cold but can't be evicted immediately, i.e., an anon page
-	 *    not in swapcache or a dirty page pending writeback, add it to the
-	 *    second oldest generation.
-	 * 3. Everything else (clean, cold) is added to the oldest generation.
+	 * There are four common cases for this page:
+	 * 1. If it's hot, i.e., freshly faulted in, add it to the youngest
+	 *    generation, and it's protected over the rest below.
+	 * 2. If it can't be evicted immediately, i.e., a dirty page pending
+	 *    writeback, add it to the second youngest generation.
+	 * 3. If it should be evicted first, e.g., cold and clean from
+	 *    folio_rotate_reclaimable(), add it to the oldest generation.
+	 * 4. Everything else falls between 2 & 3 above and is added to the
+	 *    second oldest generation if it's considered inactive, or the
+	 *    oldest generation otherwise. See lru_gen_is_active().
 	 */
 	if (folio_test_active(folio))
 		seq = lrugen->max_seq;
 	else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
 		 (folio_test_reclaim(folio) &&
 		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
-		seq = lrugen->min_seq[type] + 1;
-	else
+		seq = lrugen->max_seq - 1;
+	else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq)
 		seq = lrugen->min_seq[type];
+	else
+		seq = lrugen->min_seq[type] + 1;
 
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;

include/linux/mmzone.h

···
  * the old generation, is incremented when all its bins become empty.
  *
  * There are four operations:
- * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its
+ * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its
  *    current generation (old or young) and updates its "seg" to "head";
- * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its
+ * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its
  *    current generation (old or young) and updates its "seg" to "tail";
- * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old
+ * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old
  *    generation, updates its "gen" to "old" and resets its "seg" to "default";
- * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the
+ * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the
  *    young generation, updates its "gen" to "young" and resets its "seg" to
  *    "default".
  *
  * The events that trigger the above operations are:
  * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
- * 2. The first attempt to reclaim an memcg below low, which triggers
+ * 2. The first attempt to reclaim a memcg below low, which triggers
  *    MEMCG_LRU_TAIL;
- * 3. The first attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_TAIL;
- * 4. The second attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_YOUNG;
- * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG;
+ * 3. The first attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_TAIL;
+ * 4. The second attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_YOUNG;
+ * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
  * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
- * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
+ * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
  *
- * Note that memcg LRU only applies to global reclaim, and the round-robin
- * incrementing of their max_seq counters ensures the eventual fairness to all
- * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * Notes:
+ * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing
+ *    of their max_seq counters ensures the eventual fairness to all eligible
+ *    memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * 2. There are only two valid generations: old (seq) and young (seq+1).
+ *    MEMCG_NR_GENS is set to three so that when reading the generation counter
+ *    locklessly, a stale value (seq-1) does not wraparound to young.
  */
-#define MEMCG_NR_GENS	2
+#define MEMCG_NR_GENS	3
 #define MEMCG_NR_BINS	8
 
 struct lru_gen_memcg {

kernel/Kconfig.kexec

···
 config CRASH_DUMP
 	bool "kernel crash dumps"
 	depends on ARCH_SUPPORTS_CRASH_DUMP
-	depends on ARCH_SUPPORTS_KEXEC
 	select CRASH_CORE
 	select KEXEC_CORE
 	help

kernel/crash_core.c

···
  * It returns 0 on success and -EINVAL on failure.
  */
 static int __init parse_crashkernel_suffix(char *cmdline,
-					   unsigned long long	*crash_size,
+					   unsigned long long *crash_size,
 					   const char *suffix)
 {
 	char *cur = cmdline;
···
 			     unsigned long long *crash_base,
 			     const char *suffix)
 {
-	char	*first_colon, *first_space;
-	char	*ck_cmdline;
-	char	*name = "crashkernel=";
+	char *first_colon, *first_space;
+	char *ck_cmdline;
+	char *name = "crashkernel=";
 
 	BUG_ON(!crash_size || !crash_base);
 	*crash_size = 0;
···
 		return;
 	}
 
-	if ((crash_base > CRASH_ADDR_LOW_MAX) &&
+	if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
 	     crash_low_size && reserve_crashkernel_low(crash_low_size)) {
 		memblock_phys_free(crash_base, crash_size);
 		return;

mm/damon/core.c

···
 	if (!ctx)
 		return NULL;
 
+	init_completion(&ctx->kdamond_started);
+
 	ctx->attrs.sample_interval = 5 * 1000;
 	ctx->attrs.aggr_interval = 100 * 1000;
 	ctx->attrs.ops_update_interval = 60 * 1000 * 1000;
···
 	mutex_lock(&ctx->kdamond_lock);
 	if (!ctx->kdamond) {
 		err = 0;
+		reinit_completion(&ctx->kdamond_started);
 		ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
 				nr_running_ctxs);
 		if (IS_ERR(ctx->kdamond)) {
 			err = PTR_ERR(ctx->kdamond);
 			ctx->kdamond = NULL;
+		} else {
+			wait_for_completion(&ctx->kdamond_started);
 		}
 	}
 	mutex_unlock(&ctx->kdamond_lock);
···
 
 	pr_debug("kdamond (%d) starts\n", current->pid);
 
+	complete(&ctx->kdamond_started);
 	kdamond_init_intervals_sis(ctx);
 
 	if (ctx->ops.init)

mm/shmem.c

···
 				}
 				VM_BUG_ON_FOLIO(folio_test_writeback(folio),
 						folio);
-				truncate_inode_folio(mapping, folio);
+
+				if (!folio_test_large(folio)) {
+					truncate_inode_folio(mapping, folio);
+				} else if (truncate_inode_partial_folio(folio, lstart, lend)) {
+					/*
+					 * If we split a page, reset the loop so
+					 * that we pick up the new sub pages.
+					 * Otherwise the THP was entirely
+					 * dropped or the target range was
+					 * zeroed, so just continue the loop as
+					 * is.
+					 */
+					if (!folio_test_large(folio)) {
+						folio_unlock(folio);
+						index = start;
+						break;
+					}
+				}
 			}
 			folio_unlock(folio);
 		}

mm/vmscan.c

···
 	else
 		VM_WARN_ON_ONCE(true);
 
+	WRITE_ONCE(lruvec->lrugen.seg, seg);
+	WRITE_ONCE(lruvec->lrugen.gen, new);
+
 	hlist_nulls_del_rcu(&lruvec->lrugen.list);
 
 	if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
···
 
 	pgdat->memcg_lru.nr_memcgs[old]--;
 	pgdat->memcg_lru.nr_memcgs[new]++;
-
-	lruvec->lrugen.gen = new;
-	WRITE_ONCE(lruvec->lrugen.seg, seg);
 
 	if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
 		WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
···
 
 		gen = get_memcg_gen(pgdat->memcg_lru.seq);
 
+		lruvec->lrugen.gen = gen;
+
 		hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
 		pgdat->memcg_lru.nr_memcgs[gen]++;
-
-		lruvec->lrugen.gen = gen;
 
 		spin_unlock_irq(&pgdat->memcg_lru.lock);
 	}
···
 	}
 
 	/* protected */
-	if (tier > tier_idx) {
+	if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
 		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
 		gen = folio_inc_gen(lruvec, folio, false);
···
 	}
 
 	/* try to scrape all its memory if this memcg was deleted */
-	*nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+	if (!mem_cgroup_online(memcg)) {
+		*nr_to_scan = total;
+		return false;
+	}
+
+	*nr_to_scan = total >> sc->priority;
 
 	/*
 	 * The aging tries to be lazy to reduce the overhead, while the eviction
···
 	DEFINE_MAX_SEQ(lruvec);
 
 	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
-		return 0;
+		return -1;
 
 	if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
 		return nr_to_scan;
···
 	return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0;
 }
 
-static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
 {
+	int i;
+	enum zone_watermarks mark;
+
 	/* don't abort memcg reclaim to ensure fairness */
 	if (!root_reclaim(sc))
-		return -1;
+		return false;
 
-	return max(sc->nr_to_reclaim, compact_gap(sc->order));
+	if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order)))
+		return true;
+
+	/* check the order to exclude compaction-induced reclaim */
+	if (!current_is_kswapd() || sc->order)
+		return false;
+
+	mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ?
+	       WMARK_PROMO : WMARK_HIGH;
+
+	for (i = 0; i <= sc->reclaim_idx; i++) {
+		struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
+		unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH;
+
+		if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0))
+			return false;
+	}
+
+	/* kswapd should abort if all eligible zones are safe */
+	return true;
 }
 
 static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	long nr_to_scan;
 	unsigned long scanned = 0;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
 	int swappiness = get_swappiness(lruvec, sc);
 
 	/* clean file folios are more likely to exist */
···
 		if (scanned >= nr_to_scan)
 			break;
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 
 		cond_resched();
 	}
 
-	/* whether try_to_inc_max_seq() was successful */
+	/* whether this lruvec should be rotated */
 	return nr_to_scan < 0;
 }
 
···
 	bool success;
 	unsigned long scanned = sc->nr_scanned;
 	unsigned long reclaimed = sc->nr_reclaimed;
-	int seg = lru_gen_memcg_seg(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-
-	/* see the comment on MEMCG_NR_GENS */
-	if (!lruvec_is_sizable(lruvec, sc))
-		return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
 
 	mem_cgroup_calculate_protection(NULL, memcg);
 
···
 
 	if (mem_cgroup_below_low(NULL, memcg)) {
 		/* see the comment on MEMCG_NR_GENS */
-		if (seg != MEMCG_LRU_TAIL)
+		if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL)
 			return MEMCG_LRU_TAIL;
 
 		memcg_memory_event(memcg, MEMCG_LOW);
···
 
 	flush_reclaim_state(sc);
 
-	return success ? MEMCG_LRU_YOUNG : 0;
+	if (success && mem_cgroup_online(memcg))
+		return MEMCG_LRU_YOUNG;
+
+	if (!success && lruvec_is_sizable(lruvec, sc))
+		return 0;
+
+	/* one retry if offlined or too small */
+	return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ?
+	       MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
 }
 
 #ifdef CONFIG_MEMCG
···
 	struct lruvec *lruvec;
 	struct lru_gen_folio *lrugen;
 	struct mem_cgroup *memcg;
-	const struct hlist_nulls_node *pos;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+	struct hlist_nulls_node *pos;
 
+	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 	bin = first_bin = get_random_u32_below(MEMCG_NR_BINS);
 restart:
 	op = 0;
 	memcg = NULL;
-	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 
 	rcu_read_lock();
 
···
 		}
 
 		mem_cgroup_put(memcg);
+		memcg = NULL;
+
+		if (gen != READ_ONCE(lrugen->gen))
+			continue;
 
 		lruvec = container_of(lrugen, struct lruvec, lrugen);
 		memcg = lruvec_memcg(lruvec);
···
 
 		rcu_read_lock();
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 	}
 
···
 
 	mem_cgroup_put(memcg);
 
-	if (sc->nr_reclaimed >= nr_to_reclaim)
+	if (!is_a_nulls(pos))
 		return;
 
 	/* restart if raced with lru_gen_rotate_memcg() */
···
 	if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
 		return;
 	/*
-	 * Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
-	 * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
-	 * estimated reclaimed_to_scanned_ratio = inactive / total.
+	 * Determine the initial priority based on
+	 * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
+	 * where reclaimed_to_scanned_ratio = inactive / total.
 	 */
 	reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
 	if (get_swappiness(lruvec, sc))
 		reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
-
-	reclaimable /= MEMCG_NR_GENS;
 
 	/* round down reclaimable and round up sc->nr_to_reclaim */
 	priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);

mm/workingset.c

···
 	 * 1. For pages accessed through page tables, hotter pages pushed out
 	 *    hot pages which refaulted immediately.
 	 * 2. For pages accessed multiple times through file descriptors,
-	 *    numbers of accesses might have been out of the range.
+	 *    they would have been protected by sort_folio().
 	 */
-	if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
-		folio_set_workingset(folio);
+	if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) {
+		set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset));
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
 	}
 unlock:

tools/testing/selftests/Makefile

···
   abs_objtree := $(realpath $(abs_objtree))
   BUILD := $(abs_objtree)/kselftest
   KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include
-  KHDR_DIR := ${abs_objtree}/usr/include
 else
   BUILD := $(CURDIR)
   abs_srctree := $(shell cd $(top_srcdir) && pwd)
   KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include
-  KHDR_DIR := ${abs_srctree}/usr/include
   DEFAULT_INSTALL_HDR_PATH := 1
 endif
 
···
 # all isn't the first target in the file.
 .DEFAULT_GOAL := all
 
-all: kernel_header_files
+all:
 	@ret=1;							\
 	for TARGET in $(TARGETS); do				\
 		BUILD_TARGET=$$BUILD/$$TARGET;			\
···
 				$(if $(FORCE_TARGETS),|| exit);	\
 		ret=$$((ret * $$?));				\
 	done; exit $$ret;
-
-kernel_header_files:
-	@ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null;                          \
-	if [ $$? -ne 0 ]; then                                                     \
-            RED='\033[1;31m';                                                  \
-            NOCOLOR='\033[0m';                                                 \
-            echo;                                                              \
-            echo -e "$${RED}error$${NOCOLOR}: missing kernel header files.";   \
-            echo "Please run this and try again:";                             \
-            echo;                                                              \
-            echo "    cd $(top_srcdir)";                                       \
-            echo "    make headers";                                           \
-            echo;                                                              \
-	    exit 1;                                                                \
-	fi
-
-.PHONY: kernel_header_files
 
 run_tests: all
 	@for TARGET in $(TARGETS); do \

tools/testing/selftests/lib.mk

···
 selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST))))
 top_srcdir = $(selfdir)/../../..
 
-ifeq ("$(origin O)", "command line")
-  KBUILD_OUTPUT := $(O)
+ifeq ($(KHDR_INCLUDES),)
+KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include
 endif
-
-ifneq ($(KBUILD_OUTPUT),)
-  # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot
-  # expand a shell special character '~'. We use a somewhat tedious way here.
-  abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd)
-  $(if $(abs_objtree),, \
-    $(error failed to create output directory "$(KBUILD_OUTPUT)"))
-  # $(realpath ...) resolves symlinks
-  abs_objtree := $(realpath $(abs_objtree))
-  KHDR_DIR := ${abs_objtree}/usr/include
-else
-  abs_srctree := $(shell cd $(top_srcdir) && pwd)
-  KHDR_DIR := ${abs_srctree}/usr/include
-endif
-
-KHDR_INCLUDES := -isystem $(KHDR_DIR)
 
 # The following are built by lib.mk common compile rules.
 # TEST_CUSTOM_PROGS should be used by tests that require
···
 TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
-all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \
-     $(TEST_GEN_FILES)
-
-kernel_header_files:
-	@ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null;                      \
-	if [ $$? -ne 0 ]; then                                                 \
-            RED='\033[1;31m';                                                  \
-            NOCOLOR='\033[0m';                                                 \
-            echo;                                                              \
-            echo -e "$${RED}error$${NOCOLOR}: missing kernel header files.";   \
-            echo "Please run this and try again:";                             \
-            echo;                                                              \
-            echo "    cd $(top_srcdir)";                                       \
-            echo "    make headers";                                           \
-            echo;                                                              \
-	    exit 1; \
-	fi
-
-.PHONY: kernel_header_files
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 
 define RUN_TESTS
 	BASE_DIR="$(selfdir)";			\

tools/testing/selftests/mm/cow.c

···
 {
 	int err;
 
+	ksft_print_header();
+
 	pagesize = getpagesize();
 	thpsize = read_pmd_pagesize();
 	if (thpsize)
···
 						    ARRAY_SIZE(hugetlbsizes));
 	detect_huge_zeropage();
 
-	ksft_print_header();
 	ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() +
 		      ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() +
 		      ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case());