29 files changed, 326 insertions, 126 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 69af2173555f..6d02168d78be 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1599,6 +1599,15 @@ The following nested keys are defined.
 	  pglazyfreed (npn)
 		Amount of reclaimed lazyfree pages
 
+	  swpin_zero
+		Number of pages swapped into memory and filled with zero, where I/O
+		was optimized out because the page content was detected to be zero
+		during swapout.
+
+	  swpout_zero
+		Number of zero-filled pages swapped out with I/O skipped due to the
+		content being detected as zero.
+
 	  zswpin
 		Number of pages moved in to memory from zswap.
 
diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h
index c6bce5fbff57..7f52bd31b9d4 100644
--- a/arch/loongarch/include/asm/kasan.h
+++ b/arch/loongarch/include/asm/kasan.h
@@ -25,6 +25,7 @@
 /* 64-bit segment value. */
 #define XKPRANGE_UC_SEG		(0x8000)
 #define XKPRANGE_CC_SEG		(0x9000)
+#define XKPRANGE_WC_SEG		(0xa000)
 #define XKVRANGE_VC_SEG		(0xffff)
 
 /* Cached */
@@ -41,20 +42,28 @@
 #define XKPRANGE_UC_SHADOW_SIZE		(XKPRANGE_UC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
 #define XKPRANGE_UC_SHADOW_END		(XKPRANGE_UC_KASAN_OFFSET + XKPRANGE_UC_SHADOW_SIZE)
 
+/* WriteCombine */
+#define XKPRANGE_WC_START		WRITECOMBINE_BASE
+#define XKPRANGE_WC_SIZE		XRANGE_SIZE
+#define XKPRANGE_WC_KASAN_OFFSET	XKPRANGE_UC_SHADOW_END
+#define XKPRANGE_WC_SHADOW_SIZE		(XKPRANGE_WC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
+#define XKPRANGE_WC_SHADOW_END		(XKPRANGE_WC_KASAN_OFFSET + XKPRANGE_WC_SHADOW_SIZE)
+
 /* VMALLOC (Cached or UnCached)  */
 #define XKVRANGE_VC_START		MODULES_VADDR
 #define XKVRANGE_VC_SIZE		round_up(KFENCE_AREA_END - MODULES_VADDR + 1, PGDIR_SIZE)
-#define XKVRANGE_VC_KASAN_OFFSET	XKPRANGE_UC_SHADOW_END
+#define XKVRANGE_VC_KASAN_OFFSET	XKPRANGE_WC_SHADOW_END
 #define XKVRANGE_VC_SHADOW_SIZE		(XKVRANGE_VC_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
 #define XKVRANGE_VC_SHADOW_END		(XKVRANGE_VC_KASAN_OFFSET + XKVRANGE_VC_SHADOW_SIZE)
 
 /* KAsan shadow memory start right after vmalloc. */
 #define KASAN_SHADOW_START		round_up(KFENCE_AREA_END, PGDIR_SIZE)
 #define KASAN_SHADOW_SIZE		(XKVRANGE_VC_SHADOW_END - XKPRANGE_CC_KASAN_OFFSET)
-#define KASAN_SHADOW_END		round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE)
+#define KASAN_SHADOW_END		(round_up(KASAN_SHADOW_START + KASAN_SHADOW_SIZE, PGDIR_SIZE) - 1)
 
 #define XKPRANGE_CC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_CC_KASAN_OFFSET)
 #define XKPRANGE_UC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_UC_KASAN_OFFSET)
+#define XKPRANGE_WC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKPRANGE_WC_KASAN_OFFSET)
 #define XKVRANGE_VC_SHADOW_OFFSET	(KASAN_SHADOW_START + XKVRANGE_VC_KASAN_OFFSET)
 
 extern bool kasan_early_stage;
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index e85df33f11c7..8f21567a3188 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -113,10 +113,7 @@ struct page *tlb_virt_to_page(unsigned long kaddr);
 extern int __virt_addr_valid(volatile void *kaddr);
 #define virt_addr_valid(kaddr)	__virt_addr_valid((volatile void *)(kaddr))
 
-#define VM_DATA_DEFAULT_FLAGS \
-	(VM_READ | VM_WRITE | \
-	 ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
-	 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index f1a74b80f22c..382a09a7152c 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -58,48 +58,48 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 		return ioremap_cache(phys, size);
 }
 
-static int cpu_enumerated = 0;
-
 #ifdef CONFIG_SMP
-static int set_processor_mask(u32 id, u32 flags)
+static int set_processor_mask(u32 id, u32 pass)
 {
-	int nr_cpus;
-	int cpu, cpuid = id;
-
-	if (!cpu_enumerated)
-		nr_cpus = NR_CPUS;
-	else
-		nr_cpus = nr_cpu_ids;
+	int cpu = -1, cpuid = id;
 
-	if (num_processors >= nr_cpus) {
+	if (num_processors >= NR_CPUS) {
 		pr_warn(PREFIX "nr_cpus limit of %i reached."
-			" processor 0x%x ignored.\n", nr_cpus, cpuid);
+			" processor 0x%x ignored.\n", NR_CPUS, cpuid);
 
 		return -ENODEV;
 
 	}
+
 	if (cpuid == loongson_sysconf.boot_cpu_id)
 		cpu = 0;
-	else
-		cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS);
-
-	if (!cpu_enumerated)
-		set_cpu_possible(cpu, true);
 
-	if (flags & ACPI_MADT_ENABLED) {
+	switch (pass) {
+	case 1: /* Pass 1 handle enabled processors */
+		if (cpu < 0)
+			cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS);
 		num_processors++;
 		set_cpu_present(cpu, true);
-		__cpu_number_map[cpuid] = cpu;
-		__cpu_logical_map[cpu] = cpuid;
-	} else
+		break;
+	case 2: /* Pass 2 handle disabled processors */
+		if (cpu < 0)
+			cpu = find_first_zero_bit(cpumask_bits(cpu_possible_mask), NR_CPUS);
 		disabled_cpus++;
+		break;
+	default:
+		return cpu;
+	}
+
+	set_cpu_possible(cpu, true);
+	__cpu_number_map[cpuid] = cpu;
+	__cpu_logical_map[cpu] = cpuid;
 
 	return cpu;
 }
 #endif
 
 static int __init
-acpi_parse_processor(union acpi_subtable_headers *header, const unsigned long end)
+acpi_parse_p1_processor(union acpi_subtable_headers *header, const unsigned long end)
 {
 	struct acpi_madt_core_pic *processor = NULL;
 
@@ -110,13 +110,30 @@ acpi_parse_processor(union acpi_subtable_headers *header, const unsigned long en
 	acpi_table_print_madt_entry(&header->common);
 #ifdef CONFIG_SMP
 	acpi_core_pic[processor->core_id] = *processor;
-	set_processor_mask(processor->core_id, processor->flags);
+	if (processor->flags & ACPI_MADT_ENABLED)
+		set_processor_mask(processor->core_id, 1);
 #endif
 
 	return 0;
 }
 
 static int __init
+acpi_parse_p2_processor(union acpi_subtable_headers *header, const unsigned long end)
+{
+	struct acpi_madt_core_pic *processor = NULL;
+
+	processor = (struct acpi_madt_core_pic *)header;
+	if (BAD_MADT_ENTRY(processor, end))
+		return -EINVAL;
+
+#ifdef CONFIG_SMP
+	if (!(processor->flags & ACPI_MADT_ENABLED))
+		set_processor_mask(processor->core_id, 2);
+#endif
+
+	return 0;
+}
+static int __init
 acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long end)
 {
 	static int core = 0;
@@ -143,12 +160,14 @@ static void __init acpi_process_madt(void)
 	}
 #endif
 	acpi_table_parse_madt(ACPI_MADT_TYPE_CORE_PIC,
-			acpi_parse_processor, MAX_CORE_PIC);
+			acpi_parse_p1_processor, MAX_CORE_PIC);
+
+	acpi_table_parse_madt(ACPI_MADT_TYPE_CORE_PIC,
+			acpi_parse_p2_processor, MAX_CORE_PIC);
 
 	acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC,
 			acpi_parse_eio_master, MAX_IO_PICS);
 
-	cpu_enumerated = 1;
 	loongson_sysconf.nr_cpus = num_processors;
 }
 
@@ -310,6 +329,10 @@ static int __ref acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 	int nid;
 
 	nid = acpi_get_node(handle);
+
+	if (nid != NUMA_NO_NODE)
+		nid = early_cpu_to_node(cpu);
+
 	if (nid != NUMA_NO_NODE) {
 		set_cpuid_to_node(physid, nid);
 		node_set(nid, numa_nodes_parsed);
@@ -324,12 +347,14 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu
 {
 	int cpu;
 
-	cpu = set_processor_mask(physid, ACPI_MADT_ENABLED);
-	if (cpu < 0) {
+	cpu = cpu_number_map(physid);
+	if (cpu < 0 || cpu >= nr_cpu_ids) {
 		pr_info(PREFIX "Unable to map lapic to logical cpu number\n");
-		return cpu;
+		return -ERANGE;
 	}
 
+	num_processors++;
+	set_cpu_present(cpu, true);
 	acpi_map_cpu2node(handle, cpu, physid);
 
 	*pcpu = cpu;
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index a5fc61f8b348..e5a39bbad078 100644
--- a/arch/loongarch/kernel/paravirt.c
+++ b/arch/loongarch/kernel/paravirt.c
@@ -51,11 +51,18 @@ static u64 paravt_steal_clock(int cpu)
 }
 
 #ifdef CONFIG_SMP
+static struct smp_ops native_ops;
+
 static void pv_send_ipi_single(int cpu, unsigned int action)
 {
 	int min, old;
 	irq_cpustat_t *info = &per_cpu(irq_stat, cpu);
 
+	if (unlikely(action == ACTION_BOOT_CPU)) {
+		native_ops.send_ipi_single(cpu, action);
+		return;
+	}
+
 	old = atomic_fetch_or(BIT(action), &info->message);
 	if (old)
 		return;
@@ -75,6 +82,11 @@ static void pv_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 	if (cpumask_empty(mask))
 		return;
 
+	if (unlikely(action == ACTION_BOOT_CPU)) {
+		native_ops.send_ipi_mask(mask, action);
+		return;
+	}
+
 	action = BIT(action);
 	for_each_cpu(i, mask) {
 		info = &per_cpu(irq_stat, i);
@@ -147,6 +159,8 @@ static void pv_init_ipi(void)
 {
 	int r, swi;
 
+	/* Init native ipi irq for ACTION_BOOT_CPU */
+	native_ops.init_ipi();
 	swi = get_percpu_irq(INT_SWI0);
 	if (swi < 0)
 		panic("SWI0 IRQ mapping failed\n");
@@ -193,6 +207,7 @@ int __init pv_ipi_init(void)
 		return 0;
 
 #ifdef CONFIG_SMP
+	native_ops		= mp_ops;
 	mp_ops.init_ipi		= pv_init_ipi;
 	mp_ops.send_ipi_single	= pv_send_ipi_single;
 	mp_ops.send_ipi_mask	= pv_send_ipi_mask;
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 9afc2d8b3414..5d59e9ce2772 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -302,7 +302,7 @@ static void __init fdt_smp_setup(void)
 		__cpu_number_map[cpuid] = cpu;
 		__cpu_logical_map[cpu] = cpuid;
 
-		early_numa_add_cpu(cpu, 0);
+		early_numa_add_cpu(cpuid, 0);
 		set_cpuid_to_node(cpuid, 0);
 	}
 
@@ -331,11 +331,11 @@ void __init loongson_prepare_cpus(unsigned int max_cpus)
 	int i = 0;
 
 	parse_acpi_topology();
+	cpu_data[0].global_id = cpu_logical_map(0);
 
 	for (i = 0; i < loongson_sysconf.nr_cpus; i++) {
 		set_cpu_present(i, true);
 		csr_mail_send(0, __cpu_logical_map[i], 0);
-		cpu_data[i].global_id = __cpu_logical_map[i];
 	}
 
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
@@ -380,6 +380,7 @@ void loongson_init_secondary(void)
 		     cpu_logical_map(cpu) / loongson_sysconf.cores_per_package;
 	cpu_data[cpu].core = pptt_enabled ? cpu_data[cpu].core :
 		     cpu_logical_map(cpu) % loongson_sysconf.cores_per_package;
+	cpu_data[cpu].global_id = cpu_logical_map(cpu);
 }
 
 void loongson_smp_finish(void)
diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
index 427d6b1aec09..d2681272d8f0 100644
--- a/arch/loongarch/mm/kasan_init.c
+++ b/arch/loongarch/mm/kasan_init.c
@@ -13,6 +13,13 @@
 
 static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
 
+#ifdef __PAGETABLE_P4D_FOLDED
+#define __pgd_none(early, pgd) (0)
+#else
+#define __pgd_none(early, pgd) (early ? (pgd_val(pgd) == 0) : \
+(__pa(pgd_val(pgd)) == (unsigned long)__pa(kasan_early_shadow_p4d)))
+#endif
+
 #ifdef __PAGETABLE_PUD_FOLDED
 #define __p4d_none(early, p4d) (0)
 #else
@@ -55,6 +62,9 @@ void *kasan_mem_to_shadow(const void *addr)
 		case XKPRANGE_UC_SEG:
 			offset = XKPRANGE_UC_SHADOW_OFFSET;
 			break;
+		case XKPRANGE_WC_SEG:
+			offset = XKPRANGE_WC_SHADOW_OFFSET;
+			break;
 		case XKVRANGE_VC_SEG:
 			offset = XKVRANGE_VC_SHADOW_OFFSET;
 			break;
@@ -79,6 +89,8 @@ const void *kasan_shadow_to_mem(const void *shadow_addr)
 
 	if (addr >= XKVRANGE_VC_SHADOW_OFFSET)
 		return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START);
+	else if (addr >= XKPRANGE_WC_SHADOW_OFFSET)
+		return (void *)(((addr - XKPRANGE_WC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_WC_START);
 	else if (addr >= XKPRANGE_UC_SHADOW_OFFSET)
 		return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START);
 	else if (addr >= XKPRANGE_CC_SHADOW_OFFSET)
@@ -142,6 +154,19 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node,
 	return pud_offset(p4dp, addr);
 }
 
+static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node, bool early)
+{
+	if (__pgd_none(early, pgdp_get(pgdp))) {
+		phys_addr_t p4d_phys = early ?
+			__pa_symbol(kasan_early_shadow_p4d) : kasan_alloc_zeroed_page(node);
+		if (!early)
+			memcpy(__va(p4d_phys), kasan_early_shadow_p4d, sizeof(kasan_early_shadow_p4d));
+		pgd_populate(&init_mm, pgdp, (p4d_t *)__va(p4d_phys));
+	}
+
+	return p4d_offset(pgdp, addr);
+}
+
 static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
@@ -178,19 +203,19 @@ static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,
 	do {
 		next = pud_addr_end(addr, end);
 		kasan_pmd_populate(pudp, addr, next, node, early);
-	} while (pudp++, addr = next, addr != end);
+	} while (pudp++, addr = next, addr != end && __pud_none(early, READ_ONCE(*pudp)));
 }
 
 static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr,
 					    unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	p4d_t *p4dp = p4d_offset(pgdp, addr);
+	p4d_t *p4dp = kasan_p4d_offset(pgdp, addr, node, early);
 
 	do {
 		next = p4d_addr_end(addr, end);
 		kasan_pud_populate(p4dp, addr, next, node, early);
-	} while (p4dp++, addr = next, addr != end);
+	} while (p4dp++, addr = next, addr != end && __p4d_none(early, READ_ONCE(*p4dp)));
 }
 
 static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
@@ -218,7 +243,7 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end,
 asmlinkage void __init kasan_early_init(void)
 {
 	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE));
-	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END + 1, PGDIR_SIZE));
 }
 
 static inline void kasan_set_pgd(pgd_t *pgdp, pgd_t pgdval)
@@ -233,7 +258,7 @@ static void __init clear_pgds(unsigned long start, unsigned long end)
 	 * swapper_pg_dir. pgd_clear() can't be used
 	 * here because it's nop on 2,3-level pagetable setups
 	 */
-	for (; start < end; start += PGDIR_SIZE)
+	for (; start < end; start = pgd_addr_end(start, end))
 		kasan_set_pgd((pgd_t *)pgd_offset_k(start), __pgd(0));
 }
 
@@ -243,6 +268,17 @@ void __init kasan_init(void)
 	phys_addr_t pa_start, pa_end;
 
 	/*
+	 * If PGDIR_SIZE is too large for cpu_vabits, KASAN_SHADOW_END will
+	 * overflow UINTPTR_MAX and then looks like a user space address.
+	 * For example, PGDIR_SIZE of CONFIG_4KB_4LEVEL is 2^39, which is too
+	 * large for Loongson-2K series whose cpu_vabits = 39.
+	 */
+	if (KASAN_SHADOW_END < vm_map_base) {
+		pr_warn("PGDIR_SIZE too large for cpu_vabits, KernelAddressSanitizer disabled.\n");
+		return;
+	}
+
+	/*
 	 * PGD was populated as invalid_pmd_table or invalid_pud_table
 	 * in pagetable_init() which depends on how many levels of page
 	 * table you are using, but we had to clean the gpd of kasan
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 2dd21e0b399e..7d0c83b5b071 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -373,7 +373,7 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr
 	struct page *pg;
 	unsigned int nsg;
 	int sglen;
-	u64 pa;
+	u64 pa, offset;
 	u64 paend;
 	struct scatterlist *sg;
 	struct device *dma = mvdev->vdev.dma_dev;
@@ -396,8 +396,10 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr
 	sg = mr->sg_head.sgl;
 	for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
 	     map; map = vhost_iotlb_itree_next(map, mr->start, mr->end - 1)) {
-		paend = map->addr + maplen(map, mr);
-		for (pa = map->addr; pa < paend; pa += sglen) {
+		offset = mr->start > map->start ? mr->start - map->start : 0;
+		pa = map->addr + offset;
+		paend = map->addr + offset + maplen(map, mr);
+		for (; pa < paend; pa += sglen) {
 			pg = pfn_to_page(__phys_to_pfn(pa));
 			if (!sg) {
 				mlx5_vdpa_warn(mvdev, "sg null. start 0x%llx, end 0x%llx\n",
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 57b4af5ad646..501ad7be5174 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -68,7 +68,6 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 		goto failed;
 	}
 	memset(bh->b_data, 0, i_blocksize(inode));
-	bh->b_bdev = inode->i_sb->s_bdev;
 	bh->b_blocknr = blocknr;
 	set_buffer_mapped(bh);
 	set_buffer_uptodate(bh);
@@ -133,7 +132,6 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
 		goto found;
 	}
 	set_buffer_mapped(bh);
-	bh->b_bdev = inode->i_sb->s_bdev;
 	bh->b_blocknr = pblocknr; /* set block address for read */
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 1c9ae36a03ab..ace22253fed0 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -83,10 +83,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
 		goto out;
 	}
 
-	if (!buffer_mapped(bh)) {
-		bh->b_bdev = inode->i_sb->s_bdev;
+	if (!buffer_mapped(bh))
 		set_buffer_mapped(bh);
-	}
 	bh->b_blocknr = pbn;
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index ceb7dc0b5bad..2db6350b5ac2 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -89,7 +89,6 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
 	if (buffer_uptodate(bh))
 		goto failed_bh;
 
-	bh->b_bdev = sb->s_bdev;
 	err = nilfs_mdt_insert_new_block(inode, block, bh, init_block);
 	if (likely(!err)) {
 		get_bh(bh);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 10def4b55995..6dd8b854cd1f 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -39,7 +39,6 @@ static struct buffer_head *__nilfs_get_folio_block(struct folio *folio,
 	first_block = (unsigned long)index << (PAGE_SHIFT - blkbits);
 	bh = get_nth_bh(bh, block - first_block);
 
-	touch_buffer(bh);
 	wait_on_buffer(bh);
 	return bh;
 }
@@ -64,6 +63,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode,
 		folio_put(folio);
 		return NULL;
 	}
+	bh->b_bdev = inode->i_sb->s_bdev;
 	return bh;
 }
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 3d404624bb96..c79b4291777f 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2319,6 +2319,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
 			       struct ocfs2_blockcheck_stats *stats)
 {
 	int status = -EAGAIN;
+	u32 blksz_bits;
 
 	if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE,
 		   strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) {
@@ -2333,11 +2334,15 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
 				goto out;
 		}
 		status = -EINVAL;
-		if ((1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits)) != blksz) {
+		/* Acceptable block sizes are 512 bytes, 1K, 2K and 4K. */
+		blksz_bits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
+		if (blksz_bits < 9 || blksz_bits > 12) {
 			mlog(ML_ERROR, "found superblock with incorrect block "
-			     "size: found %u, should be %u\n",
-			     1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits),
-			       blksz);
+			     "size bits: found %u, should be 9, 10, 11, or 12\n",
+			     blksz_bits);
+		} else if ((1 << le32_to_cpu(blksz_bits)) != blksz) {
+			mlog(ML_ERROR, "found superblock with incorrect block "
+			     "size: found %u, should be %u\n", 1 << blksz_bits, blksz);
 		} else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) !=
 			   OCFS2_MAJOR_REV_LEVEL ||
 			   le16_to_cpu(di->id2.i_super.s_minor_rev_level) !=
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 34d2da05f2f1..e1b41554a5fb 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1760,8 +1760,9 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 
 struct mem_cgroup *mem_cgroup_from_slab_obj(void *p);
 
-static inline void count_objcg_event(struct obj_cgroup *objcg,
-				     enum vm_event_item idx)
+static inline void count_objcg_events(struct obj_cgroup *objcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
 {
 	struct mem_cgroup *memcg;
 
@@ -1770,7 +1771,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 
 	rcu_read_lock();
 	memcg = obj_cgroup_memcg(objcg);
-	count_memcg_events(memcg, idx, 1);
+	count_memcg_events(memcg, idx, count);
 	rcu_read_unlock();
 }
 
@@ -1825,8 +1826,9 @@ static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
 	return NULL;
 }
 
-static inline void count_objcg_event(struct obj_cgroup *objcg,
-				     enum vm_event_item idx)
+static inline void count_objcg_events(struct obj_cgroup *objcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
 {
 }
 
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index aed952d04132..f70d0958095c 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -134,6 +134,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_SWAP
 		SWAP_RA,
 		SWAP_RA_HIT,
+		SWPIN_ZERO,
+		SWPOUT_ZERO,
 #ifdef CONFIG_KSM
 		KSM_SWPIN_COPY,
 #endif
diff --git a/include/net/tls.h b/include/net/tls.h
index 3a33924db2bc..61fef2880114 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -390,8 +390,12 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx)
 
 static inline bool tls_sw_has_ctx_tx(const struct sock *sk)
 {
-	struct tls_context *ctx = tls_get_ctx(sk);
+	struct tls_context *ctx;
+
+	if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk))
+		return false;
 
+	ctx = tls_get_ctx(sk);
 	if (!ctx)
 		return false;
 	return !!tls_sw_ctx_tx(ctx);
@@ -399,8 +403,12 @@ static inline bool tls_sw_has_ctx_tx(const struct sock *sk)
 
 static inline bool tls_sw_has_ctx_rx(const struct sock *sk)
 {
-	struct tls_context *ctx = tls_get_ctx(sk);
+	struct tls_context *ctx;
+
+	if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk))
+		return false;
 
+	ctx = tls_get_ctx(sk);
 	if (!ctx)
 		return false;
 	return !!tls_sw_ctx_rx(ctx);
diff --git a/mm/gup.c b/mm/gup.c
index 4637dab7b54f..ad0c8922dac3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2273,20 +2273,57 @@ struct page *get_dump_page(unsigned long addr)
 #endif /* CONFIG_ELF_CORE */
 
 #ifdef CONFIG_MIGRATION
+
+/*
+ * An array of either pages or folios ("pofs"). Although it may seem tempting to
+ * avoid this complication, by simply interpreting a list of folios as a list of
+ * pages, that approach won't work in the longer term, because eventually the
+ * layouts of struct page and struct folio will become completely different.
+ * Furthermore, this pof approach avoids excessive page_folio() calls.
+ */
+struct pages_or_folios {
+	union {
+		struct page **pages;
+		struct folio **folios;
+		void **entries;
+	};
+	bool has_folios;
+	long nr_entries;
+};
+
+static struct folio *pofs_get_folio(struct pages_or_folios *pofs, long i)
+{
+	if (pofs->has_folios)
+		return pofs->folios[i];
+	return page_folio(pofs->pages[i]);
+}
+
+static void pofs_clear_entry(struct pages_or_folios *pofs, long i)
+{
+	pofs->entries[i] = NULL;
+}
+
+static void pofs_unpin(struct pages_or_folios *pofs)
+{
+	if (pofs->has_folios)
+		unpin_folios(pofs->folios, pofs->nr_entries);
+	else
+		unpin_user_pages(pofs->pages, pofs->nr_entries);
+}
+
 /*
  * Returns the number of collected folios. Return value is always >= 0.
  */
 static unsigned long collect_longterm_unpinnable_folios(
-					struct list_head *movable_folio_list,
-					unsigned long nr_folios,
-					struct folio **folios)
+		struct list_head *movable_folio_list,
+		struct pages_or_folios *pofs)
 {
 	unsigned long i, collected = 0;
 	struct folio *prev_folio = NULL;
 	bool drain_allow = true;
 
-	for (i = 0; i < nr_folios; i++) {
-		struct folio *folio = folios[i];
+	for (i = 0; i < pofs->nr_entries; i++) {
+		struct folio *folio = pofs_get_folio(pofs, i);
 
 		if (folio == prev_folio)
 			continue;
@@ -2327,16 +2364,15 @@ static unsigned long collect_longterm_unpinnable_folios(
  * Returns -EAGAIN if all folios were successfully migrated or -errno for
  * failure (or partial success).
  */
-static int migrate_longterm_unpinnable_folios(
-					struct list_head *movable_folio_list,
-					unsigned long nr_folios,
-					struct folio **folios)
+static int
+migrate_longterm_unpinnable_folios(struct list_head *movable_folio_list,
+				   struct pages_or_folios *pofs)
 {
 	int ret;
 	unsigned long i;
 
-	for (i = 0; i < nr_folios; i++) {
-		struct folio *folio = folios[i];
+	for (i = 0; i < pofs->nr_entries; i++) {
+		struct folio *folio = pofs_get_folio(pofs, i);
 
 		if (folio_is_device_coherent(folio)) {
 			/*
@@ -2344,7 +2380,7 @@ static int migrate_longterm_unpinnable_folios(
 			 * convert the pin on the source folio to a normal
 			 * reference.
 			 */
-			folios[i] = NULL;
+			pofs_clear_entry(pofs, i);
 			folio_get(folio);
 			gup_put_folio(folio, 1, FOLL_PIN);
 
@@ -2363,8 +2399,8 @@ static int migrate_longterm_unpinnable_folios(
 		 * calling folio_isolate_lru() which takes a reference so the
 		 * folio won't be freed if it's migrating.
 		 */
-		unpin_folio(folios[i]);
-		folios[i] = NULL;
+		unpin_folio(folio);
+		pofs_clear_entry(pofs, i);
 	}
 
 	if (!list_empty(movable_folio_list)) {
@@ -2387,12 +2423,26 @@ static int migrate_longterm_unpinnable_folios(
 	return -EAGAIN;
 
 err:
-	unpin_folios(folios, nr_folios);
+	pofs_unpin(pofs);
 	putback_movable_pages(movable_folio_list);
 
 	return ret;
 }
 
+static long
+check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
+{
+	LIST_HEAD(movable_folio_list);
+	unsigned long collected;
+
+	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
+						       pofs);
+	if (!collected)
+		return 0;
+
+	return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);
+}
+
 /*
  * Check whether all folios are *allowed* to be pinned indefinitely (long term).
  * Rather confusingly, all folios in the range are required to be pinned via
@@ -2417,16 +2467,13 @@ err:
 static long check_and_migrate_movable_folios(unsigned long nr_folios,
 					     struct folio **folios)
 {
-	unsigned long collected;
-	LIST_HEAD(movable_folio_list);
+	struct pages_or_folios pofs = {
+		.folios = folios,
+		.has_folios = true,
+		.nr_entries = nr_folios,
+	};
 
-	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
-						       nr_folios, folios);
-	if (!collected)
-		return 0;
-
-	return migrate_longterm_unpinnable_folios(&movable_folio_list,
-						  nr_folios, folios);
+	return check_and_migrate_movable_pages_or_folios(&pofs);
 }
 
 /*
@@ -2436,22 +2483,13 @@ static long check_and_migrate_movable_folios(unsigned long nr_folios,
 static long check_and_migrate_movable_pages(unsigned long nr_pages,
 					    struct page **pages)
 {
-	struct folio **folios;
-	long i, ret;
+	struct pages_or_folios pofs = {
+		.pages = pages,
+		.has_folios = false,
+		.nr_entries = nr_pages,
+	};
 
-	folios = kmalloc_array(nr_pages, sizeof(*folios), GFP_KERNEL);
-	if (!folios) {
-		unpin_user_pages(pages, nr_pages);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nr_pages; i++)
-		folios[i] = page_folio(pages[i]);
-
-	ret = check_and_migrate_movable_folios(nr_pages, folios);
-
-	kfree(folios);
-	return ret;
+	return check_and_migrate_movable_pages_or_folios(&pofs);
 }
 #else
 static long check_and_migrate_movable_pages(unsigned long nr_pages,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 03fd4bc39ea1..5734d5d5060f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3790,7 +3790,9 @@ next:
 		 * in the case it was underused, then consider it used and
 		 * don't add it back to split_queue.
 		 */
-		if (!did_split && !folio_test_partially_mapped(folio)) {
+		if (did_split) {
+			; /* folio already removed from list */
+		} else if (!folio_test_partially_mapped(folio)) {
 			list_del_init(&folio->_deferred_list);
 			removed++;
 		} else {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 06df2af97415..53db98d2c4a1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -431,6 +431,10 @@ static const unsigned int memcg_vm_event_stat[] = {
 	PGDEACTIVATE,
 	PGLAZYFREE,
 	PGLAZYFREED,
+#ifdef CONFIG_SWAP
+	SWPIN_ZERO,
+	SWPOUT_ZERO,
+#endif
 #ifdef CONFIG_ZSWAP
 	ZSWPIN,
 	ZSWPOUT,
diff --git a/mm/nommu.c b/mm/nommu.c
index e9b5f527ab5b..9cb6e99215e2 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -573,7 +573,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma)
 	VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_start);
 
 	vma_iter_config(&vmi, vma->vm_start, vma->vm_end);
-	if (vma_iter_prealloc(&vmi, vma)) {
+	if (vma_iter_prealloc(&vmi, NULL)) {
 		pr_warn("Allocation of vma tree for process %d failed\n",
 		       current->pid);
 		return -ENOMEM;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c6c7bb3ea71b..216fbbfbedcf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1048,6 +1048,7 @@ __always_inline bool free_pages_prepare(struct page *page,
 	bool skip_kasan_poison = should_skip_kasan_poison(page);
 	bool init = want_init_on_free();
 	bool compound = PageCompound(page);
+	struct folio *folio = page_folio(page);
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
@@ -1057,6 +1058,20 @@ __always_inline bool free_pages_prepare(struct page *page,
 	if (memcg_kmem_online() && PageMemcgKmem(page))
 		__memcg_kmem_uncharge_page(page, order);
 
+	/*
+	 * In rare cases, when truncation or holepunching raced with
+	 * munlock after VM_LOCKED was cleared, Mlocked may still be
+	 * found set here.  This does not indicate a problem, unless
+	 * "unevictable_pgs_cleared" appears worryingly large.
+	 */
+	if (unlikely(folio_test_mlocked(folio))) {
+		long nr_pages = folio_nr_pages(folio);
+
+		__folio_clear_mlocked(folio);
+		zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages);
+		count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
+	}
+
 	if (unlikely(PageHWPoison(page)) && !order) {
 		/* Do not let hwpoison pages hit pcplists/buddy */
 		reset_page_owner(page, order);
diff --git a/mm/page_io.c b/mm/page_io.c
index 69536a2b3c13..01749b99fb54 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -204,7 +204,9 @@ static bool is_folio_zero_filled(struct folio *folio)
 
 static void swap_zeromap_folio_set(struct folio *folio)
 {
+	struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio);
 	struct swap_info_struct *sis = swp_swap_info(folio->swap);
+	int nr_pages = folio_nr_pages(folio);
 	swp_entry_t entry;
 	unsigned int i;
 
@@ -212,6 +214,12 @@ static void swap_zeromap_folio_set(struct folio *folio)
 		entry = page_swap_entry(folio_page(folio, i));
 		set_bit(swp_offset(entry), sis->zeromap);
 	}
+
+	count_vm_events(SWPOUT_ZERO, nr_pages);
+	if (objcg) {
+		count_objcg_events(objcg, SWPOUT_ZERO, nr_pages);
+		obj_cgroup_put(objcg);
+	}
 }
 
 static void swap_zeromap_folio_clear(struct folio *folio)
@@ -503,6 +511,7 @@ static void sio_read_complete(struct kiocb *iocb, long ret)
 static bool swap_read_folio_zeromap(struct folio *folio)
 {
 	int nr_pages = folio_nr_pages(folio);
+	struct obj_cgroup *objcg;
 	bool is_zeromap;
 
 	/*
@@ -517,6 +526,13 @@ static bool swap_read_folio_zeromap(struct folio *folio)
 	if (!is_zeromap)
 		return false;
 
+	objcg = get_obj_cgroup_from_folio(folio);
+	count_vm_events(SWPIN_ZERO, nr_pages);
+	if (objcg) {
+		count_objcg_events(objcg, SWPIN_ZERO, nr_pages);
+		obj_cgroup_put(objcg);
+	}
+
 	folio_zero_range(folio, 0, folio_size(folio));
 	folio_mark_uptodate(folio);
 	return true;
diff --git a/mm/swap.c b/mm/swap.c
index b8e3259ea2c4..59f30a981c6f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -78,20 +78,6 @@ static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp,
 		lruvec_del_folio(*lruvecp, folio);
 		__folio_clear_lru_flags(folio);
 	}
-
-	/*
-	 * In rare cases, when truncation or holepunching raced with
-	 * munlock after VM_LOCKED was cleared, Mlocked may still be
-	 * found set here.  This does not indicate a problem, unless
-	 * "unevictable_pgs_cleared" appears worryingly large.
-	 */
-	if (unlikely(folio_test_mlocked(folio))) {
-		long nr_pages = folio_nr_pages(folio);
-
-		__folio_clear_mlocked(folio);
-		zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages);
-		count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
-	}
 }
 
 /*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 46bd4b1a3c07..9c85bd46ab7f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -929,7 +929,7 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
 		si->highest_bit = 0;
 		del_from_avail_list(si);
 
-		if (vm_swap_full())
+		if (si->cluster_info && vm_swap_full())
 			schedule_work(&si->reclaim_work);
 	}
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b5a4cea423e1..ac6a5aa34eab 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1415,6 +1415,8 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_SWAP
 	"swap_ra",
 	"swap_ra_hit",
+	"swpin_zero",
+	"swpout_zero",
 #ifdef CONFIG_KSM
 	"ksm_swpin_copy",
 #endif
diff --git a/mm/zswap.c b/mm/zswap.c
index 162013952074..0030ce8fecfc 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1053,7 +1053,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 
 	count_vm_event(ZSWPWB);
 	if (entry->objcg)
-		count_objcg_event(entry->objcg, ZSWPWB);
+		count_objcg_events(entry->objcg, ZSWPWB, 1);
 
 	zswap_entry_free(entry);
 
@@ -1483,7 +1483,7 @@ bool zswap_store(struct folio *folio)
 
 	if (objcg) {
 		obj_cgroup_charge_zswap(objcg, entry->length);
-		count_objcg_event(objcg, ZSWPOUT);
+		count_objcg_events(objcg, ZSWPOUT, 1);
 	}
 
 	/*
@@ -1577,7 +1577,7 @@ bool zswap_load(struct folio *folio)
 
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
-		count_objcg_event(entry->objcg, ZSWPIN);
+		count_objcg_events(entry->objcg, ZSWPIN, 1);
 
 	if (swapcache) {
 		zswap_entry_free(entry);
diff --git a/net/core/filter.c b/net/core/filter.c
index e31ee8be2de0..fb56567c551e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2249,7 +2249,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
 		rcu_read_unlock();
 		return ret;
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	if (dst)
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 out_drop:
diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
index 156cc278e2fc..7c881bca9af5 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
@@ -57,9 +57,15 @@ __description("null pointer")
 __success __retval(0)
 int null_pointer(void)
 {
-	int nr = 0;
+	struct bpf_iter_bits iter;
+	int err, nr = 0;
 	int *bit;
 
+	err = bpf_iter_bits_new(&iter, NULL, 1);
+	bpf_iter_bits_destroy(&iter);
+	if (err != -EINVAL)
+		return 1;
+
 	bpf_for_each(bits, bit, NULL, 1)
 		nr++;
 	return nr;
@@ -194,15 +200,33 @@ __description("bad words")
 __success __retval(0)
 int bad_words(void)
 {
-	void *bad_addr = (void *)(3UL << 30);
-	int nr = 0;
+	void *bad_addr = (void *)-4095;
+	struct bpf_iter_bits iter;
+	volatile int nr;
 	int *bit;
+	int err;
+
+	err = bpf_iter_bits_new(&iter, bad_addr, 1);
+	bpf_iter_bits_destroy(&iter);
+	if (err != -EFAULT)
+		return 1;
 
+	nr = 0;
 	bpf_for_each(bits, bit, bad_addr, 1)
 		nr++;
+	if (nr != 0)
+		return 2;
 
+	err = bpf_iter_bits_new(&iter, bad_addr, 4);
+	bpf_iter_bits_destroy(&iter);
+	if (err != -EFAULT)
+		return 3;
+
+	nr = 0;
 	bpf_for_each(bits, bit, bad_addr, 4)
 		nr++;
+	if (nr != 0)
+		return 4;
 
-	return nr;
+	return 0;
 }
diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c
index 60001c142ce9..432d5af15e66 100644
--- a/tools/testing/selftests/mm/hugetlb_dio.c
+++ b/tools/testing/selftests/mm/hugetlb_dio.c
@@ -44,6 +44,13 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
 	if (fd < 0)
 		ksft_exit_fail_perror("Error opening file\n");
 
+	/* Get the free huge pages before allocation */
+	free_hpage_b = get_free_hugepages();
+	if (free_hpage_b == 0) {
+		close(fd);
+		ksft_exit_skip("No free hugepage, exiting!\n");
+	}
+
 	/* Allocate a hugetlb page */
 	orig_buffer = mmap(NULL, h_pagesize, mmap_prot, mmap_flags, -1, 0);
 	if (orig_buffer == MAP_FAILED) {