Merge remote-tracking branch 'torvalds/master' into perf-tools-next

To pick up fixes sent via perf-tools, by Namhyung Kim.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

37 files changed, 457 insertions, 173 deletions

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 368c5d86b5b7..e497011261b8 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -4,7 +4,7 @@ ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
 # ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
 cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
 endif
-CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
+CFLAGS_core.o += -Wno-override-init $(cflags-nogcse-yy)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 86571e760dd6..343c3456c8dd 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -38,7 +38,7 @@
 
 /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */
 #define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8)
-#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ)
+#define KERN_VM_SZ (SZ_4G + GUARD_SZ)
 
 struct bpf_arena {
 	struct bpf_map map;
@@ -110,7 +110,7 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-EINVAL);
 
 	vm_range = (u64)attr->max_entries * PAGE_SIZE;
-	if (vm_range > (1ull << 32))
+	if (vm_range > SZ_4G)
 		return ERR_PTR(-E2BIG);
 
 	if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32))
@@ -301,7 +301,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad
 
 	if (pgoff)
 		return -EINVAL;
-	if (len > (1ull << 32))
+	if (len > SZ_4G)
 		return -E2BIG;
 
 	/* if user_vm_start was specified at arena creation time */
@@ -322,7 +322,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad
 	if (WARN_ON_ONCE(arena->user_vm_start))
 		/* checks at map creation time should prevent this */
 		return -EFAULT;
-	return round_up(ret, 1ull << 32);
+	return round_up(ret, SZ_4G);
 }
 
 static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
@@ -346,7 +346,7 @@ static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 		return -EBUSY;
 
 	/* Earlier checks should prevent this */
-	if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff))
+	if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > SZ_4G || vma->vm_pgoff))
 		return -EFAULT;
 
 	if (remember_vma(arena, vma))
@@ -420,7 +420,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 		if (uaddr & ~PAGE_MASK)
 			return 0;
 		pgoff = compute_pgoff(arena, uaddr);
-		if (pgoff + page_cnt > page_cnt_max)
+		if (pgoff > page_cnt_max - page_cnt)
 			/* requested address will be outside of user VMA */
 			return 0;
 	}
@@ -447,7 +447,13 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 		goto out;
 
 	uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE);
-	/* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */
+	/* Earlier checks made sure that uaddr32 + page_cnt * PAGE_SIZE - 1
+	 * will not overflow 32-bit. Lower 32-bit need to represent
+	 * contiguous user address range.
+	 * Map these pages at kern_vm_start base.
+	 * kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE - 1 can overflow
+	 * lower 32-bit and it's ok.
+	 */
 	ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32,
 				kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages);
 	if (ret) {
@@ -510,6 +516,11 @@ static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt)
 		if (!page)
 			continue;
 		if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */
+			/* Optimization for the common case of page_cnt==1:
+			 * If page wasn't mapped into some user vma there
+			 * is no need to call zap_pages which is slow. When
+			 * page_cnt is big it's faster to do the batched zap.
+			 */
 			zap_pages(arena, full_uaddr, 1);
 		vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE);
 		__free_page(page);
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index addf3dd57b59..35e1ddca74d2 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -80,6 +80,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key
 	return -EOPNOTSUPP;
 }
 
+/* Called from syscall */
+static int bloom_map_alloc_check(union bpf_attr *attr)
+{
+	if (attr->value_size > KMALLOC_MAX_SIZE)
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements.
+		 */
+		return -E2BIG;
+
+	return 0;
+}
+
 static struct bpf_map *bloom_map_alloc(union bpf_attr *attr)
 {
 	u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits;
@@ -191,6 +203,7 @@ static u64 bloom_map_mem_usage(const struct bpf_map *map)
 BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter)
 const struct bpf_map_ops bloom_filter_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = bloom_map_alloc_check,
 	.map_alloc = bloom_map_alloc,
 	.map_free = bloom_map_free,
 	.map_get_next_key = bloom_map_get_next_key,
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 9ee8da477465..a8e34416e960 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -263,6 +263,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 static int cpu_map_kthread_run(void *data)
 {
 	struct bpf_cpu_map_entry *rcpu = data;
+	unsigned long last_qs = jiffies;
 
 	complete(&rcpu->kthread_running);
 	set_current_state(TASK_INTERRUPTIBLE);
@@ -288,10 +289,12 @@ static int cpu_map_kthread_run(void *data)
 			if (__ptr_ring_empty(rcpu->queue)) {
 				schedule();
 				sched = 1;
+				last_qs = jiffies;
 			} else {
 				__set_current_state(TASK_RUNNING);
 			}
 		} else {
+			rcu_softirq_qs_periodic(last_qs);
 			sched = cond_resched();
 		}
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a89587859571..449b9a5d3fe3 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2548,7 +2548,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
 BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
 #endif
 BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ae2ff73bde7e..c287925471f6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3024,17 +3024,46 @@ void bpf_link_inc(struct bpf_link *link)
 	atomic64_inc(&link->refcnt);
 }
 
+static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
+{
+	struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
+
+	/* free bpf_link and its containing memory */
+	link->ops->dealloc_deferred(link);
+}
+
+static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
+{
+	if (rcu_trace_implies_rcu_gp())
+		bpf_link_defer_dealloc_rcu_gp(rcu);
+	else
+		call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp);
+}
+
 /* bpf_link_free is guaranteed to be called from process context */
 static void bpf_link_free(struct bpf_link *link)
 {
+	bool sleepable = false;
+
 	bpf_link_free_id(link->id);
 	if (link->prog) {
+		sleepable = link->prog->sleepable;
 		/* detach BPF program, clean up used resources */
 		link->ops->release(link);
 		bpf_prog_put(link->prog);
 	}
-	/* free bpf_link and its containing memory */
-	link->ops->dealloc(link);
+	if (link->ops->dealloc_deferred) {
+		/* schedule BPF link deallocation; if underlying BPF program
+		 * is sleepable, we need to first wait for RCU tasks trace
+		 * sync, then go through "classic" RCU grace period
+		 */
+		if (sleepable)
+			call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
+		else
+			call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
+	}
+	if (link->ops->dealloc)
+		link->ops->dealloc(link);
 }
 
 static void bpf_link_put_deferred(struct work_struct *work)
@@ -3544,7 +3573,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 
 static const struct bpf_link_ops bpf_raw_tp_link_lops = {
 	.release = bpf_raw_tp_link_release,
-	.dealloc = bpf_raw_tp_link_dealloc,
+	.dealloc_deferred = bpf_raw_tp_link_dealloc,
 	.show_fdinfo = bpf_raw_tp_link_show_fdinfo,
 	.fill_link_info = bpf_raw_tp_link_fill_link_info,
 };
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 63749ad5ac6b..98188379d5c7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5682,6 +5682,13 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
 	return reg->type == PTR_TO_FLOW_KEYS;
 }
 
+static bool is_arena_reg(struct bpf_verifier_env *env, int regno)
+{
+	const struct bpf_reg_state *reg = reg_state(env, regno);
+
+	return reg->type == PTR_TO_ARENA;
+}
+
 static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
 #ifdef CONFIG_NET
 	[PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
@@ -6694,6 +6701,11 @@ static int check_stack_access_within_bounds(
 	err = check_stack_slot_within_bounds(env, min_off, state, type);
 	if (!err && max_off > 0)
 		err = -EINVAL; /* out of stack access into non-negative offsets */
+	if (!err && access_size < 0)
+		/* access_size should not be negative (or overflow an int); others checks
+		 * along the way should have prevented such an access.
+		 */
+		err = -EFAULT; /* invalid negative access size; integer overflow? */
 
 	if (err) {
 		if (tnum_is_const(reg->var_off)) {
@@ -7019,7 +7031,8 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg) ||
 	    is_flow_key_reg(env, insn->dst_reg) ||
-	    is_sk_reg(env, insn->dst_reg)) {
+	    is_sk_reg(env, insn->dst_reg) ||
+	    is_arena_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
 			insn->dst_reg,
 			reg_type_str(env, reg_state(env, insn->dst_reg)->type));
@@ -14014,6 +14027,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n");
 					return -EINVAL;
 				}
+				if (!env->prog->aux->arena) {
+					verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n");
+					return -EINVAL;
+				}
 			} else {
 				if ((insn->off != 0 && insn->off != 8 && insn->off != 16 &&
 				     insn->off != 32) || insn->imm) {
@@ -14046,8 +14063,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				if (insn->imm) {
 					/* off == BPF_ADDR_SPACE_CAST */
 					mark_reg_unknown(env, regs, insn->dst_reg);
-					if (insn->imm == 1) /* cast from as(1) to as(0) */
+					if (insn->imm == 1) { /* cast from as(1) to as(0) */
 						dst_reg->type = PTR_TO_ARENA;
+						/* PTR_TO_ARENA is 32-bit */
+						dst_reg->subreg_def = env->insn_idx + 1;
+					}
 				} else if (insn->off == 0) {
 					/* case: R1 = R2
 					 * copy register state to dest reg
@@ -18359,15 +18379,18 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 				}
 				if (!env->prog->jit_requested) {
 					verbose(env, "JIT is required to use arena\n");
+					fdput(f);
 					return -EOPNOTSUPP;
 				}
 				if (!bpf_jit_supports_arena()) {
 					verbose(env, "JIT doesn't support arena\n");
+					fdput(f);
 					return -EOPNOTSUPP;
 				}
 				env->prog->aux->arena = (void *)map;
 				if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) {
 					verbose(env, "arena's user address must be set via map_extra or mmap()\n");
+					fdput(f);
 					return -EINVAL;
 				}
 			}
@@ -19601,8 +19624,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			    (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) {
 				/* convert to 32-bit mov that clears upper 32-bit */
 				insn->code = BPF_ALU | BPF_MOV | BPF_X;
-				/* clear off, so it's a normal 'wX = wY' from JIT pov */
+				/* clear off and imm, so it's a normal 'wX = wY' from JIT pov */
 				insn->off = 0;
+				insn->imm = 0;
 			} /* cast from as(0) to as(1) should be handled by JIT */
 			goto next_insn;
 		}
diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config
index 7a5bbfc024b7..4b4cfcba3190 100644
--- a/kernel/configs/hardening.config
+++ b/kernel/configs/hardening.config
@@ -39,11 +39,12 @@ CONFIG_UBSAN=y
 CONFIG_UBSAN_TRAP=y
 CONFIG_UBSAN_BOUNDS=y
 # CONFIG_UBSAN_SHIFT is not set
-# CONFIG_UBSAN_DIV_ZERO
-# CONFIG_UBSAN_UNREACHABLE
-# CONFIG_UBSAN_BOOL
-# CONFIG_UBSAN_ENUM
-# CONFIG_UBSAN_ALIGNMENT
+# CONFIG_UBSAN_DIV_ZERO is not set
+# CONFIG_UBSAN_UNREACHABLE is not set
+# CONFIG_UBSAN_SIGNED_WRAP is not set
+# CONFIG_UBSAN_BOOL is not set
+# CONFIG_UBSAN_ENUM is not set
+# CONFIG_UBSAN_ALIGNMENT is not set
 
 # Sampling-based heap out-of-bounds and use-after-free detection.
 CONFIG_KFENCE=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8f6affd051f7..07ad53b7f119 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3207,7 +3207,8 @@ enum cpu_mitigations {
 };
 
 static enum cpu_mitigations cpu_mitigations __ro_after_init =
-	CPU_MITIGATIONS_AUTO;
+	IS_ENABLED(CONFIG_SPECULATION_MITIGATIONS) ? CPU_MITIGATIONS_AUTO :
+						     CPU_MITIGATIONS_OFF;
 
 static int __init mitigations_parse_cmdline(char *arg)
 {
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index bbb6c3cb00e4..066668799f75 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -366,8 +366,10 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)
 
 	crashk_low_res.start = low_base;
 	crashk_low_res.end   = low_base + low_size - 1;
+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 	insert_resource(&iomem_resource, &crashk_low_res);
 #endif
+#endif
 	return 0;
 }
 
@@ -448,8 +450,12 @@ retry:
 
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
+	insert_resource(&iomem_resource, &crashk_res);
+#endif
 }
 
+#ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 static __init int insert_crashkernel_resources(void)
 {
 	if (crashk_res.start < crashk_res.end)
@@ -462,3 +468,4 @@ static __init int insert_crashkernel_resources(void)
 }
 early_initcall(insert_crashkernel_resources);
 #endif
+#endif
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 77974cea3e69..a5e0dfc44d24 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -69,11 +69,14 @@
  * @alloc_size:	Size of the allocated buffer.
  * @list:	The free list describing the number of free entries available
  *		from each index.
+ * @pad_slots:	Number of preceding padding slots. Valid only in the first
+ *		allocated non-padding slot.
  */
 struct io_tlb_slot {
 	phys_addr_t orig_addr;
 	size_t alloc_size;
-	unsigned int list;
+	unsigned short list;
+	unsigned short pad_slots;
 };
 
 static bool swiotlb_force_bounce;
@@ -287,6 +290,7 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
 					 mem->nslabs - i);
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
+		mem->slots[i].pad_slots = 0;
 	}
 
 	memset(vaddr, 0, bytes);
@@ -821,12 +825,30 @@ void swiotlb_dev_init(struct device *dev)
 #endif
 }
 
-/*
- * Return the offset into a iotlb slot required to keep the device happy.
+/**
+ * swiotlb_align_offset() - Get required offset into an IO TLB allocation.
+ * @dev:         Owning device.
+ * @align_mask:  Allocation alignment mask.
+ * @addr:        DMA address.
+ *
+ * Return the minimum offset from the start of an IO TLB allocation which is
+ * required for a given buffer address and allocation alignment to keep the
+ * device happy.
+ *
+ * First, the address bits covered by min_align_mask must be identical in the
+ * original address and the bounce buffer address. High bits are preserved by
+ * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra
+ * padding bytes before the bounce buffer.
+ *
+ * Second, @align_mask specifies which bits of the first allocated slot must
+ * be zero. This may require allocating additional padding slots, and then the
+ * offset (in bytes) from the first such padding slot is returned.
  */
-static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+static unsigned int swiotlb_align_offset(struct device *dev,
+					 unsigned int align_mask, u64 addr)
 {
-	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+	return addr & dma_get_min_align_mask(dev) &
+		(align_mask | (IO_TLB_SIZE - 1));
 }
 
 /*
@@ -841,27 +863,23 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	size_t alloc_size = mem->slots[index].alloc_size;
 	unsigned long pfn = PFN_DOWN(orig_addr);
 	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
-	unsigned int tlb_offset, orig_addr_offset;
+	int tlb_offset;
 
 	if (orig_addr == INVALID_PHYS_ADDR)
 		return;
 
-	tlb_offset = tlb_addr & (IO_TLB_SIZE - 1);
-	orig_addr_offset = swiotlb_align_offset(dev, orig_addr);
-	if (tlb_offset < orig_addr_offset) {
-		dev_WARN_ONCE(dev, 1,
-			"Access before mapping start detected. orig offset %u, requested offset %u.\n",
-			orig_addr_offset, tlb_offset);
-		return;
-	}
-
-	tlb_offset -= orig_addr_offset;
-	if (tlb_offset > alloc_size) {
-		dev_WARN_ONCE(dev, 1,
-			"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n",
-			alloc_size, size, tlb_offset);
-		return;
-	}
+	/*
+	 * It's valid for tlb_offset to be negative. This can happen when the
+	 * "offset" returned by swiotlb_align_offset() is non-zero, and the
+	 * tlb_addr is pointing within the first "offset" bytes of the second
+	 * or subsequent slots of the allocated swiotlb area. While it's not
+	 * valid for tlb_addr to be pointing within the first "offset" bytes
+	 * of the first slot, there's no way to check for such an error since
+	 * this function can't distinguish the first slot from the second and
+	 * subsequent slots.
+	 */
+	tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) -
+		     swiotlb_align_offset(dev, 0, orig_addr);
 
 	orig_addr += tlb_offset;
 	alloc_size -= tlb_offset;
@@ -1003,10 +1021,9 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	dma_addr_t tbl_dma_addr =
 		phys_to_dma_unencrypted(dev, pool->start) & boundary_mask;
 	unsigned long max_slots = get_max_slots(boundary_mask);
-	unsigned int iotlb_align_mask =
-		dma_get_min_align_mask(dev) | alloc_align_mask;
+	unsigned int iotlb_align_mask = dma_get_min_align_mask(dev);
 	unsigned int nslots = nr_slots(alloc_size), stride;
-	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr);
 	unsigned int index, slots_checked, count = 0, i;
 	unsigned long flags;
 	unsigned int slot_base;
@@ -1016,18 +1033,29 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	BUG_ON(area_index >= pool->nareas);
 
 	/*
-	 * For allocations of PAGE_SIZE or larger only look for page aligned
-	 * allocations.
+	 * Historically, swiotlb allocations >= PAGE_SIZE were guaranteed to be
+	 * page-aligned in the absence of any other alignment requirements.
+	 * 'alloc_align_mask' was later introduced to specify the alignment
+	 * explicitly, however this is passed as zero for streaming mappings
+	 * and so we preserve the old behaviour there in case any drivers are
+	 * relying on it.
+	 */
+	if (!alloc_align_mask && !iotlb_align_mask && alloc_size >= PAGE_SIZE)
+		alloc_align_mask = PAGE_SIZE - 1;
+
+	/*
+	 * Ensure that the allocation is at least slot-aligned and update
+	 * 'iotlb_align_mask' to ignore bits that will be preserved when
+	 * offsetting into the allocation.
 	 */
-	if (alloc_size >= PAGE_SIZE)
-		iotlb_align_mask |= ~PAGE_MASK;
-	iotlb_align_mask &= ~(IO_TLB_SIZE - 1);
+	alloc_align_mask |= (IO_TLB_SIZE - 1);
+	iotlb_align_mask &= ~alloc_align_mask;
 
 	/*
 	 * For mappings with an alignment requirement don't bother looping to
 	 * unaligned slots once we found an aligned one.
 	 */
-	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
+	stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask));
 
 	spin_lock_irqsave(&area->lock, flags);
 	if (unlikely(nslots > pool->area_nslabs - area->used))
@@ -1037,11 +1065,14 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
 	index = area->index;
 
 	for (slots_checked = 0; slots_checked < pool->area_nslabs; ) {
+		phys_addr_t tlb_addr;
+
 		slot_index = slot_base + index;
+		tlb_addr = slot_addr(tbl_dma_addr, slot_index);
 
-		if (orig_addr &&
-		    (slot_addr(tbl_dma_addr, slot_index) &
-		     iotlb_align_mask) != (orig_addr & iotlb_align_mask)) {
+		if ((tlb_addr & alloc_align_mask) ||
+		    (orig_addr && (tlb_addr & iotlb_align_mask) !=
+				  (orig_addr & iotlb_align_mask))) {
 			index = wrap_area_index(pool, index + 1);
 			slots_checked++;
 			continue;
@@ -1315,11 +1346,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		unsigned long attrs)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
-	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+	unsigned int offset;
 	struct io_tlb_pool *pool;
 	unsigned int i;
 	int index;
 	phys_addr_t tlb_addr;
+	unsigned short pad_slots;
 
 	if (!mem || !mem->nslabs) {
 		dev_warn_ratelimited(dev,
@@ -1336,6 +1368,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
+	offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr);
 	index = swiotlb_find_slots(dev, orig_addr,
 				   alloc_size + offset, alloc_align_mask, &pool);
 	if (index == -1) {
@@ -1351,6 +1384,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	 * This is needed when we sync the memory.  Then we sync the buffer if
 	 * needed.
 	 */
+	pad_slots = offset >> IO_TLB_SHIFT;
+	offset &= (IO_TLB_SIZE - 1);
+	index += pad_slots;
+	pool->slots[index].pad_slots = pad_slots;
 	for (i = 0; i < nr_slots(alloc_size + offset); i++)
 		pool->slots[index + i].orig_addr = slot_addr(orig_addr, i);
 	tlb_addr = slot_addr(pool->start, index) + offset;
@@ -1371,13 +1408,17 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 {
 	struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
 	unsigned long flags;
-	unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
-	int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
-	int nslots = nr_slots(mem->slots[index].alloc_size + offset);
-	int aindex = index / mem->area_nslabs;
-	struct io_tlb_area *area = &mem->areas[aindex];
+	unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr);
+	int index, nslots, aindex;
+	struct io_tlb_area *area;
 	int count, i;
 
+	index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
+	index -= mem->slots[index].pad_slots;
+	nslots = nr_slots(mem->slots[index].alloc_size + offset);
+	aindex = index / mem->area_nslabs;
+	area = &mem->areas[aindex];
+
 	/*
 	 * Return the buffer to the free list by setting the corresponding
 	 * entries to indicate the number of contiguous entries available.
@@ -1400,6 +1441,7 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 		mem->slots[i].list = ++count;
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
+		mem->slots[i].pad_slots = 0;
 	}
 
 	/*
@@ -1634,9 +1676,6 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get,
 static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 					 const char *dirname)
 {
-	atomic_long_set(&mem->total_used, 0);
-	atomic_long_set(&mem->used_hiwater, 0);
-
 	mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
 	if (!mem->nslabs)
 		return;
@@ -1647,7 +1686,6 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 	debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem,
 			&fops_io_tlb_hiwater);
 #ifdef CONFIG_SWIOTLB_DYNAMIC
-	atomic_long_set(&mem->transient_nslabs, 0);
 	debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs,
 			    mem, &fops_io_tlb_transient_used);
 #endif
@@ -1677,16 +1715,24 @@ struct page *swiotlb_alloc(struct device *dev, size_t size)
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
 	struct io_tlb_pool *pool;
 	phys_addr_t tlb_addr;
+	unsigned int align;
 	int index;
 
 	if (!mem)
 		return NULL;
 
-	index = swiotlb_find_slots(dev, 0, size, 0, &pool);
+	align = (1 << (get_order(size) + PAGE_SHIFT)) - 1;
+	index = swiotlb_find_slots(dev, 0, size, align, &pool);
 	if (index == -1)
 		return NULL;
 
 	tlb_addr = slot_addr(pool->start, index);
+	if (unlikely(!PAGE_ALIGNED(tlb_addr))) {
+		dev_WARN_ONCE(dev, 1, "Cannot allocate pages from non page-aligned swiotlb addr 0x%pa.\n",
+			      &tlb_addr);
+		swiotlb_release_slots(dev, tlb_addr);
+		return NULL;
+	}
 
 	return pfn_to_page(PFN_DOWN(tlb_addr));
 }
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 88cb3c88aaa5..90843cc38588 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -57,8 +57,14 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	/* Either of the above might have changed the syscall number */
 	syscall = syscall_get_nr(current, regs);
 
-	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
 		trace_sys_enter(regs, syscall);
+		/*
+		 * Probes or BPF hooks in the tracepoint may have changed the
+		 * system call number as well.
+		 */
+		syscall = syscall_get_nr(current, regs);
+	}
 
 	syscall_enter_audit(regs, syscall);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 39a5046c2f0b..aebb3e6c96dc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -714,6 +714,23 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		} else if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		vm_flags_clear(tmp, VM_LOCKED_MASK);
+		/*
+		 * Copy/update hugetlb private vma information.
+		 */
+		if (is_vm_hugetlb_page(tmp))
+			hugetlb_dup_vma_private(tmp);
+
+		/*
+		 * Link the vma into the MT. After using __mt_dup(), memory
+		 * allocation is not necessary here, so it cannot fail.
+		 */
+		vma_iter_bulk_store(&vmi, tmp);
+
+		mm->map_count++;
+
+		if (tmp->vm_ops && tmp->vm_ops->open)
+			tmp->vm_ops->open(tmp);
+
 		file = tmp->vm_file;
 		if (file) {
 			struct address_space *mapping = file->f_mapping;
@@ -730,25 +747,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			i_mmap_unlock_write(mapping);
 		}
 
-		/*
-		 * Copy/update hugetlb private vma information.
-		 */
-		if (is_vm_hugetlb_page(tmp))
-			hugetlb_dup_vma_private(tmp);
-
-		/*
-		 * Link the vma into the MT. After using __mt_dup(), memory
-		 * allocation is not necessary here, so it cannot fail.
-		 */
-		vma_iter_bulk_store(&vmi, tmp);
-
-		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
 			retval = copy_page_range(tmp, mpnt);
 
-		if (tmp->vm_ops && tmp->vm_ops->open)
-			tmp->vm_ops->open(tmp);
-
 		if (retval) {
 			mpnt = vma_next(&vmi);
 			goto loop_out;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ad3eaf2ab959..bf9ae8a8686f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1643,8 +1643,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		}
 
 		if (!((old->flags & new->flags) & IRQF_SHARED) ||
-		    (oldtype != (new->flags & IRQF_TRIGGER_MASK)) ||
-		    ((old->flags ^ new->flags) & IRQF_ONESHOT))
+		    (oldtype != (new->flags & IRQF_TRIGGER_MASK)))
+			goto mismatch;
+
+		if ((old->flags & IRQF_ONESHOT) &&
+		    (new->flags & IRQF_COND_ONESHOT))
+			new->flags |= IRQF_ONESHOT;
+		else if ((old->flags ^ new->flags) & IRQF_ONESHOT)
 			goto mismatch;
 
 		/* All handlers must agree on per-cpuness */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9d9095e81792..65adc815fc6e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1567,10 +1567,17 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	jump_label_lock();
 	preempt_disable();
 
-	/* Ensure it is not in reserved area nor out of text */
-	if (!(core_kernel_text((unsigned long) p->addr) ||
-	    is_module_text_address((unsigned long) p->addr)) ||
-	    in_gate_area_no_mm((unsigned long) p->addr) ||
+	/* Ensure the address is in a text area, and find a module if exists. */
+	*probed_mod = NULL;
+	if (!core_kernel_text((unsigned long) p->addr)) {
+		*probed_mod = __module_text_address((unsigned long) p->addr);
+		if (!(*probed_mod)) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+	/* Ensure it is not in reserved area. */
+	if (in_gate_area_no_mm((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
 	    static_call_text_reserved(p->addr, p->addr) ||
@@ -1580,8 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
 		goto out;
 	}
 
-	/* Check if 'p' is probing a module. */
-	*probed_mod = __module_text_address((unsigned long) p->addr);
+	/* Get module refcount and reject __init functions for loaded modules. */
 	if (*probed_mod) {
 		/*
 		 * We must hold a refcount of the probed module while updating
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index fe7a517fc4ab..495b69a71a5d 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -39,7 +39,7 @@ static struct kobj_attribute _name##_attr = __ATTR_RW(_name)
 static ssize_t uevent_seqnum_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
 {
-	return sysfs_emit(buf, "%llu\n", (unsigned long long)uevent_seqnum);
+	return sysfs_emit(buf, "%llu\n", (u64)atomic64_read(&uevent_seqnum));
 }
 KERNEL_ATTR_RO(uevent_seqnum);
 
diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index 0ea1b2970a23..f3e0329337f6 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -236,6 +236,10 @@ choice
 	  possible to load a signed module containing the algorithm to check
 	  the signature on that module.
 
+config MODULE_SIG_SHA1
+	bool "Sign modules with SHA-1"
+	select CRYPTO_SHA1
+
 config MODULE_SIG_SHA256
 	bool "Sign modules with SHA-256"
 	select CRYPTO_SHA256
@@ -265,6 +269,7 @@ endchoice
 config MODULE_SIG_HASH
 	string
 	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
+	default "sha1" if MODULE_SIG_SHA1
 	default "sha256" if MODULE_SIG_SHA256
 	default "sha384" if MODULE_SIG_SHA384
 	default "sha512" if MODULE_SIG_SHA512
@@ -362,8 +367,7 @@ config MODPROBE_PATH
 	  userspace can still load modules explicitly).
 
 config TRIM_UNUSED_KSYMS
-	bool "Trim unused exported kernel symbols" if EXPERT
-	depends on !COMPILE_TEST
+	bool "Trim unused exported kernel symbols"
 	help
 	  The kernel and some modules make many symbols available for
 	  other modules to use via EXPORT_SYMBOL() and variants. Depending
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index e3ae93bbcb9b..09f8397bae15 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -106,6 +106,12 @@ static void s2idle_enter(void)
 	swait_event_exclusive(s2idle_wait_head,
 		    s2idle_state == S2IDLE_STATE_WAKE);
 
+	/*
+	 * Kick all CPUs to ensure that they resume their timers and restore
+	 * consistent system state.
+	 */
+	wake_up_all_idle_cpus();
+
 	cpus_read_unlock();
 
 	raw_spin_lock_irq(&s2idle_lock);
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index b663a97f5867..d4856ec61570 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -201,7 +201,7 @@ static int __init test_suspend(void)
 	}
 
 	/* RTCs have initialized by now too ... can we use one? */
-	dev = class_find_device(rtc_class, NULL, NULL, has_wakealarm);
+	dev = class_find_device(&rtc_class, NULL, NULL, has_wakealarm);
 	if (dev) {
 		rtc = rtc_class_open(dev_name(dev));
 		put_device(dev);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a000bef51177..adf99c05adca 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2009,6 +2009,12 @@ static int console_trylock_spinning(void)
 	 */
 	mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_);
 
+	/*
+	 * Update @console_may_schedule for trylock because the previous
+	 * owner may have been schedulable.
+	 */
+	console_may_schedule = 0;
+
 	return 1;
 }
 
@@ -3269,6 +3275,21 @@ static int __init keep_bootcon_setup(char *str)
 
 early_param("keep_bootcon", keep_bootcon_setup);
 
+static int console_call_setup(struct console *newcon, char *options)
+{
+	int err;
+
+	if (!newcon->setup)
+		return 0;
+
+	/* Synchronize with possible boot console. */
+	console_lock();
+	err = newcon->setup(newcon, options);
+	console_unlock();
+
+	return err;
+}
+
 /*
  * This is called by register_console() to try to match
  * the newly registered console with any of the ones selected
@@ -3304,8 +3325,8 @@ static int try_enable_preferred_console(struct console *newcon,
 			if (_braille_register_console(newcon, c))
 				return 0;
 
-			if (newcon->setup &&
-			    (err = newcon->setup(newcon, c->options)) != 0)
+			err = console_call_setup(newcon, c->options);
+			if (err)
 				return err;
 		}
 		newcon->flags |= CON_ENABLED;
@@ -3331,7 +3352,7 @@ static void try_enable_default_console(struct console *newcon)
 	if (newcon->index < 0)
 		newcon->index = 0;
 
-	if (newcon->setup && newcon->setup(newcon, NULL) != 0)
+	if (console_call_setup(newcon, NULL) != 0)
 		return;
 
 	newcon->flags |= CON_ENABLED;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d44efa0d0611..7019a40457a6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6647,7 +6647,9 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 	 *     if (signal_pending_state())	    if (p->state & @state)
 	 *
 	 * Also, the membarrier system call requires a full memory barrier
-	 * after coming from user-space, before storing to rq->curr.
+	 * after coming from user-space, before storing to rq->curr; this
+	 * barrier matches a full barrier in the proximity of the membarrier
+	 * system call exit.
 	 */
 	rq_lock(rq, &rf);
 	smp_mb__after_spinlock();
@@ -6718,12 +6720,20 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		 *
 		 * Here are the schemes providing that barrier on the
 		 * various architectures:
-		 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
-		 *   switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
+		 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC,
+		 *   RISC-V.  switch_mm() relies on membarrier_arch_switch_mm()
+		 *   on PowerPC and on RISC-V.
 		 * - finish_lock_switch() for weakly-ordered
 		 *   architectures where spin_unlock is a full barrier,
 		 * - switch_to() for arm64 (weakly-ordered, spin_unlock
 		 *   is a RELEASE barrier),
+		 *
+		 * The barrier matches a full barrier in the proximity of
+		 * the membarrier system call entry.
+		 *
+		 * On RISC-V, this barrier pairing is also needed for the
+		 * SYNC_CORE command when switching between processes, cf.
+		 * the inline comments in membarrier_arch_switch_mm().
 		 */
 		++*switch_count;
 
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 4e715b9b278e..809194cd779f 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -254,7 +254,7 @@ static int membarrier_global_expedited(void)
 		return 0;
 
 	/*
-	 * Matches memory barriers around rq->curr modification in
+	 * Matches memory barriers after rq->curr modification in
 	 * scheduler.
 	 */
 	smp_mb();	/* system call entry is not a mb. */
@@ -304,7 +304,7 @@ static int membarrier_global_expedited(void)
 
 	/*
 	 * Memory barrier on the caller thread _after_ we finished
-	 * waiting for the last IPI. Matches memory barriers around
+	 * waiting for the last IPI. Matches memory barriers before
 	 * rq->curr modification in scheduler.
 	 */
 	smp_mb();	/* exit from system call is not a mb */
@@ -324,6 +324,7 @@ static int membarrier_private_expedited(int flags, int cpu_id)
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
 			return -EPERM;
 		ipi_func = ipi_sync_core;
+		prepare_sync_core_cmd(mm);
 	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
 		if (!IS_ENABLED(CONFIG_RSEQ))
 			return -EINVAL;
@@ -343,8 +344,12 @@ static int membarrier_private_expedited(int flags, int cpu_id)
 		return 0;
 
 	/*
-	 * Matches memory barriers around rq->curr modification in
+	 * Matches memory barriers after rq->curr modification in
 	 * scheduler.
+	 *
+	 * On RISC-V, this barrier pairing is also needed for the
+	 * SYNC_CORE command when switching between processes, cf.
+	 * the inline comments in membarrier_arch_switch_mm().
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
@@ -420,7 +425,7 @@ out:
 
 	/*
 	 * Memory barrier on the caller thread _after_ we finished
-	 * waiting for the last IPI. Matches memory barriers around
+	 * waiting for the last IPI. Matches memory barriers before
 	 * rq->curr modification in scheduler.
 	 */
 	smp_mb();	/* exit from system call is not a mb */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d2242679239e..ae50f212775e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -79,6 +79,8 @@
 # include <asm/paravirt_api_clock.h>
 #endif
 
+#include <asm/barrier.h>
+
 #include "cpupri.h"
 #include "cpudeadline.h"
 
@@ -3445,13 +3447,19 @@ static inline void switch_mm_cid(struct rq *rq,
 		 * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
 		 * Provide it here.
 		 */
-		if (!prev->mm)                          // from kernel
+		if (!prev->mm) {                        // from kernel
 			smp_mb();
-		/*
-		 * user -> user transition guarantees a memory barrier through
-		 * switch_mm() when current->mm changes. If current->mm is
-		 * unchanged, no barrier is needed.
-		 */
+		} else {				// from user
+			/*
+			 * user->user transition relies on an implicit
+			 * memory barrier in switch_mm() when
+			 * current->mm changes. If the architecture
+			 * switch_mm() does not have an implicit memory
+			 * barrier, it is emitted here.  If current->mm
+			 * is unchanged, no barrier is needed.
+			 */
+			smp_mb__after_switch_mm();
+		}
 	}
 	if (prev->mm_cid_active) {
 		mm_cid_snapshot_time(rq, prev->mm);
diff --git a/kernel/sys.c b/kernel/sys.c
index f8e543f1e38a..8bb106a56b3a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2408,8 +2408,11 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
 	if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
 		return -EINVAL;
 
-	/* PARISC cannot allow mdwe as it needs writable stacks */
-	if (IS_ENABLED(CONFIG_PARISC))
+	/*
+	 * EOPNOTSUPP might be more appropriate here in principle, but
+	 * existing userspace depends on EINVAL specifically.
+	 */
+	if (!arch_memory_deny_write_exec_supported())
 		return -EINVAL;
 
 	current_bits = get_current_mdwe();
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 4657cb8e8b1f..5abfa4390673 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -134,7 +134,7 @@ static struct class_interface alarmtimer_rtc_interface = {
 
 static int alarmtimer_rtc_interface_setup(void)
 {
-	alarmtimer_rtc_interface.class = rtc_class;
+	alarmtimer_rtc_interface.class = &rtc_class;
 	return class_interface_register(&alarmtimer_rtc_interface);
 }
 static void alarmtimer_rtc_interface_remove(void)
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 9de66bbbb3d1..4782edcbe7b9 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -129,15 +129,17 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 		goto out;
 	}
 	pccontext->clk = clk;
-	fp->private_data = pccontext;
-	if (clk->ops.open)
+	if (clk->ops.open) {
 		err = clk->ops.open(pccontext, fp->f_mode);
-	else
-		err = 0;
-
-	if (!err) {
-		get_device(clk->dev);
+		if (err) {
+			kfree(pccontext);
+			goto out;
+		}
 	}
+
+	fp->private_data = pccontext;
+	get_device(clk->dev);
+	err = 0;
 out:
 	up_read(&clk->rwsem);
 	return err;
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index fb0fdec8719a..d88b13076b79 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -7,6 +7,7 @@
  * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
  * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
  */
+#include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
@@ -84,7 +85,7 @@ int tick_is_oneshot_available(void)
  */
 static void tick_periodic(int cpu)
 {
-	if (tick_do_timer_cpu == cpu) {
+	if (READ_ONCE(tick_do_timer_cpu) == cpu) {
 		raw_spin_lock(&jiffies_lock);
 		write_seqcount_begin(&jiffies_seq);
 
@@ -215,8 +216,8 @@ static void tick_setup_device(struct tick_device *td,
 		 * If no cpu took the do_timer update, assign it to
 		 * this cpu:
 		 */
-		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
-			tick_do_timer_cpu = cpu;
+		if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) {
+			WRITE_ONCE(tick_do_timer_cpu, cpu);
 			tick_next_period = ktime_get();
 #ifdef CONFIG_NO_HZ_FULL
 			/*
@@ -232,7 +233,7 @@ static void tick_setup_device(struct tick_device *td,
 						!tick_nohz_full_cpu(cpu)) {
 			tick_take_do_timer_from_boot();
 			tick_do_timer_boot_cpu = -1;
-			WARN_ON(tick_do_timer_cpu != cpu);
+			WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu);
 #endif
 		}
 
@@ -406,10 +407,10 @@ void tick_assert_timekeeping_handover(void)
 int tick_cpu_dying(unsigned int dying_cpu)
 {
 	/*
-	 * If the current CPU is the timekeeper, it's the only one that
-	 * can safely hand over its duty. Also all online CPUs are in
-	 * stop machine, guaranteed not to be idle, therefore it's safe
-	 * to pick any online successor.
+	 * If the current CPU is the timekeeper, it's the only one that can
+	 * safely hand over its duty. Also all online CPUs are in stop
+	 * machine, guaranteed not to be idle, therefore there is no
+	 * concurrency and it's safe to pick any online successor.
 	 */
 	if (tick_do_timer_cpu == dying_cpu)
 		tick_do_timer_cpu = cpumask_first(cpu_online_mask);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 269e21590df5..71a792cd8936 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -8,6 +8,7 @@
  *
  *  Started by: Thomas Gleixner and Ingo Molnar
  */
+#include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
@@ -204,7 +205,7 @@ static inline void tick_sched_flag_clear(struct tick_sched *ts,
 
 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 {
-	int cpu = smp_processor_id();
+	int tick_cpu, cpu = smp_processor_id();
 
 	/*
 	 * Check if the do_timer duty was dropped. We don't care about
@@ -216,16 +217,18 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	 * If nohz_full is enabled, this should not happen because the
 	 * 'tick_do_timer_cpu' CPU never relinquishes.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) &&
-	    unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+	tick_cpu = READ_ONCE(tick_do_timer_cpu);
+
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) {
 #ifdef CONFIG_NO_HZ_FULL
 		WARN_ON_ONCE(tick_nohz_full_running);
 #endif
-		tick_do_timer_cpu = cpu;
+		WRITE_ONCE(tick_do_timer_cpu, cpu);
+		tick_cpu = cpu;
 	}
 
 	/* Check if jiffies need an update */
-	if (tick_do_timer_cpu == cpu)
+	if (tick_cpu == cpu)
 		tick_do_update_jiffies64(now);
 
 	/*
@@ -610,7 +613,7 @@ bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
 	 * timers, workqueues, timekeeping, ...) on behalf of full dynticks
 	 * CPUs. It must remain online when nohz full is enabled.
 	 */
-	if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
+	if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu)
 		return false;
 	return true;
 }
@@ -697,6 +700,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu)
 
 /**
  * tick_nohz_update_jiffies - update jiffies when idle was interrupted
+ * @now: current ktime_t
  *
  * Called from interrupt entry when the CPU was idle
  *
@@ -794,7 +798,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
  * This time is measured via accounting rather than sampling,
  * and is as accurate as ktime_get() is.
  *
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu
  */
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
@@ -820,7 +824,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
  * This time is measured via accounting rather than sampling,
  * and is as accurate as ktime_get() is.
  *
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu
  */
 u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 {
@@ -890,6 +894,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 {
 	u64 basemono, next_tick, delta, expires;
 	unsigned long basejiff;
+	int tick_cpu;
 
 	basemono = get_jiffies_update(&basejiff);
 	ts->last_jiffies = basejiff;
@@ -946,9 +951,9 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	 * Otherwise we can sleep as long as we want.
 	 */
 	delta = timekeeping_max_deferment();
-	if (cpu != tick_do_timer_cpu &&
-	    (tick_do_timer_cpu != TICK_DO_TIMER_NONE ||
-	     !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
+	tick_cpu = READ_ONCE(tick_do_timer_cpu);
+	if (tick_cpu != cpu &&
+	    (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
 		delta = KTIME_MAX;
 
 	/* Calculate the next expiry time */
@@ -969,6 +974,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	unsigned long basejiff = ts->last_jiffies;
 	u64 basemono = ts->timer_expires_base;
 	bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
+	int tick_cpu;
 	u64 expires;
 
 	/* Make sure we won't be trying to stop it twice in a row. */
@@ -1006,10 +1012,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	 * do_timer() never gets invoked. Keep track of the fact that it
 	 * was the one which had the do_timer() duty last.
 	 */
-	if (cpu == tick_do_timer_cpu) {
-		tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+	tick_cpu = READ_ONCE(tick_do_timer_cpu);
+	if (tick_cpu == cpu) {
+		WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE);
 		tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST);
-	} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+	} else if (tick_cpu != TICK_DO_TIMER_NONE) {
 		tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST);
 	}
 
@@ -1172,15 +1179,17 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		return false;
 
 	if (tick_nohz_full_enabled()) {
+		int tick_cpu = READ_ONCE(tick_do_timer_cpu);
+
 		/*
 		 * Keep the tick alive to guarantee timekeeping progression
 		 * if there are full dynticks CPUs around
 		 */
-		if (tick_do_timer_cpu == cpu)
+		if (tick_cpu == cpu)
 			return false;
 
 		/* Should not happen for nohz-full */
-		if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
+		if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE))
 			return false;
 	}
 
@@ -1287,6 +1296,8 @@ void tick_nohz_irq_exit(void)
 
 /**
  * tick_nohz_idle_got_tick - Check whether or not the tick handler has run
+ *
+ * Return: %true if the tick handler has run, otherwise %false
  */
 bool tick_nohz_idle_got_tick(void)
 {
@@ -1305,6 +1316,8 @@ bool tick_nohz_idle_got_tick(void)
  * stopped, it returns the next hrtimer.
  *
  * Called from power state control code with interrupts disabled
+ *
+ * Return: the next expiration time
  */
 ktime_t tick_nohz_get_next_hrtimer(void)
 {
@@ -1320,6 +1333,8 @@ ktime_t tick_nohz_get_next_hrtimer(void)
  * The return value of this function and/or the value returned by it through the
  * @delta_next pointer can be negative which must be taken into account by its
  * callers.
+ *
+ * Return: the expected length of the current sleep
  */
 ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 {
@@ -1357,8 +1372,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 /**
  * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
  * for a particular CPU.
+ * @cpu: target CPU number
  *
  * Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for @cpu
  */
 unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
 {
@@ -1371,6 +1389,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
  * tick_nohz_get_idle_calls - return the current idle calls counter value
  *
  * Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for the current CPU
  */
 unsigned long tick_nohz_get_idle_calls(void)
 {
@@ -1559,7 +1579,7 @@ early_param("skew_tick", skew_tick);
 
 /**
  * tick_setup_sched_timer - setup the tick emulation timer
- * @mode: tick_nohz_mode to setup for
+ * @hrtimer: whether to use the hrtimer or not
  */
 void tick_setup_sched_timer(bool hrtimer)
 {
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index e11c4dc65bcb..b4a7822f495d 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -46,8 +46,8 @@ struct tick_device {
  * @next_tick:		Next tick to be fired when in dynticks mode.
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_waketime:	Time when the idle was interrupted
+ * @idle_sleeptime_seq:	sequence counter for data consistency
  * @idle_entrytime:	Time when the idle call was entered
- * @nohz_mode:		Mode - one state of tick_nohz_mode
  * @last_jiffies:	Base jiffies snapshot when next event was last computed
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
  * @timer_expires:	Anticipated timer expiration time (in case sched tick is stopped)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index e69e75d3858c..3baf2fbe6848 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -64,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64);
 
 /*
  * The timer wheel has LVL_DEPTH array levels. Each level provides an array of
- * LVL_SIZE buckets. Each level is driven by its own clock and therefor each
+ * LVL_SIZE buckets. Each level is driven by its own clock and therefore each
  * level has a different granularity.
  *
- * The level granularity is:		LVL_CLK_DIV ^ lvl
+ * The level granularity is:		LVL_CLK_DIV ^ level
  * The level clock frequency is:	HZ / (LVL_CLK_DIV ^ level)
  *
  * The array level of a newly armed timer depends on the relative expiry
  * time. The farther the expiry time is away the higher the array level and
- * therefor the granularity becomes.
+ * therefore the granularity becomes.
  *
  * Contrary to the original timer wheel implementation, which aims for 'exact'
  * expiry of the timers, this implementation removes the need for recascading
@@ -207,7 +207,7 @@ EXPORT_SYMBOL(jiffies_64);
  * struct timer_base - Per CPU timer base (number of base depends on config)
  * @lock:		Lock protecting the timer_base
  * @running_timer:	When expiring timers, the lock is dropped. To make
- *			sure not to race agains deleting/modifying a
+ *			sure not to race against deleting/modifying a
  *			currently running timer, the pointer is set to the
  *			timer, which expires at the moment. If no timer is
  *			running, the pointer is NULL.
@@ -642,7 +642,8 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 	 * the base lock:
 	 */
 	if (base->is_idle) {
-		WARN_ON_ONCE(!(timer->flags & TIMER_PINNED));
+		WARN_ON_ONCE(!(timer->flags & TIMER_PINNED ||
+			       tick_nohz_full_cpu(base->cpu)));
 		wake_up_nohz_cpu(base->cpu);
 	}
 }
@@ -736,7 +737,7 @@ static bool timer_is_static_object(void *addr)
 }
 
 /*
- * fixup_init is called when:
+ * timer_fixup_init is called when:
  * - an active object is initialized
  */
 static bool timer_fixup_init(void *addr, enum debug_obj_state state)
@@ -760,7 +761,7 @@ static void stub_timer(struct timer_list *unused)
 }
 
 /*
- * fixup_activate is called when:
+ * timer_fixup_activate is called when:
  * - an active object is activated
  * - an unknown non-static object is activated
  */
@@ -782,7 +783,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
 }
 
 /*
- * fixup_free is called when:
+ * timer_fixup_free is called when:
  * - an active object is freed
  */
 static bool timer_fixup_free(void *addr, enum debug_obj_state state)
@@ -800,7 +801,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state)
 }
 
 /*
- * fixup_assert_init is called when:
+ * timer_fixup_assert_init is called when:
  * - an untracked/uninit-ed object is found
  */
 static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
@@ -913,7 +914,7 @@ static void do_init_timer(struct timer_list *timer,
  * @key: lockdep class key of the fake lock used for tracking timer
  *       sync lock dependencies
  *
- * init_timer_key() must be done to a timer prior calling *any* of the
+ * init_timer_key() must be done to a timer prior to calling *any* of the
  * other timer functions.
  */
 void init_timer_key(struct timer_list *timer,
@@ -1416,7 +1417,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown)
 	 * If @shutdown is set then the lock has to be taken whether the
 	 * timer is pending or not to protect against a concurrent rearm
 	 * which might hit between the lockless pending check and the lock
-	 * aquisition. By taking the lock it is ensured that such a newly
+	 * acquisition. By taking the lock it is ensured that such a newly
 	 * enqueued timer is dequeued and cannot end up with
 	 * timer->function == NULL in the expiry code.
 	 *
@@ -2292,13 +2293,20 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem,
 		 */
 		if (!base_local->is_idle && time_after(nextevt, basej + 1)) {
 			base_local->is_idle = true;
+			/*
+			 * Global timers queued locally while running in a task
+			 * in nohz_full mode need a self-IPI to kick reprogramming
+			 * in IRQ tail.
+			 */
+			if (tick_nohz_full_cpu(base_local->cpu))
+				base_global->is_idle = true;
 			trace_timer_base_idle(true, base_local->cpu);
 		}
 		*idle = base_local->is_idle;
 
 		/*
 		 * When timer base is not set idle, undo the effect of
-		 * tmigr_cpu_deactivate() to prevent inconsitent states - active
+		 * tmigr_cpu_deactivate() to prevent inconsistent states - active
 		 * timer base but inactive timer migration hierarchy.
 		 *
 		 * When timer base was already marked idle, nothing will be
@@ -2364,6 +2372,8 @@ void timer_clear_idle(void)
 	 * path. Required for BASE_LOCAL only.
 	 */
 	__this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false);
+	if (tick_nohz_full_cpu(smp_processor_id()))
+		__this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false);
 	trace_timer_base_idle(false, smp_processor_id());
 
 	/* Activate without holding the timer_base->lock */
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 611cd904f035..ccba875d2234 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -751,6 +751,33 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 
 		first_childevt = evt = data->evt;
 
+		/*
+		 * Walking the hierarchy is required in any case when a
+		 * remote expiry was done before. This ensures to not lose
+		 * already queued events in non active groups (see section
+		 * "Required event and timerqueue update after a remote
+		 * expiry" in the documentation at the top).
+		 *
+		 * The two call sites which are executed without a remote expiry
+		 * before, are not prevented from propagating changes through
+		 * the hierarchy by the return:
+		 *  - When entering this path by tmigr_new_timer(), @evt->ignore
+		 *    is never set.
+		 *  - tmigr_inactive_up() takes care of the propagation by
+		 *    itself and ignores the return value. But an immediate
+		 *    return is possible if there is a parent, sparing group
+		 *    locking at this level, because the upper walking call to
+		 *    the parent will take care about removing this event from
+		 *    within the group and update next_expiry accordingly.
+		 *
+		 * However if there is no parent, ie: the hierarchy has only a
+		 * single level so @group is the top level group, make sure the
+		 * first event information of the group is updated properly and
+		 * also handled properly, so skip this fast return path.
+		 */
+		if (evt->ignore && !remote && group->parent)
+			return true;
+
 		raw_spin_lock(&group->lock);
 
 		childstate.state = 0;
@@ -762,8 +789,11 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 	 * queue when the expiry time changed only or when it could be ignored.
 	 */
 	if (timerqueue_node_queued(&evt->nextevt)) {
-		if ((evt->nextevt.expires == nextexp) && !evt->ignore)
+		if ((evt->nextevt.expires == nextexp) && !evt->ignore) {
+			/* Make sure not to miss a new CPU event with the same expiry */
+			evt->cpu = first_childevt->cpu;
 			goto check_toplvl;
+		}
 
 		if (!timerqueue_del(&group->events, &evt->nextevt))
 			WRITE_ONCE(group->next_expiry, KTIME_MAX);
@@ -1038,8 +1068,15 @@ void tmigr_handle_remote(void)
 	 * in tmigr_handle_remote_up() anyway. Keep this check to speed up the
 	 * return when nothing has to be done.
 	 */
-	if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask))
-		return;
+	if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) {
+		/*
+		 * If this CPU was an idle migrator, make sure to clear its wakeup
+		 * value so it won't chase timers that have already expired elsewhere.
+		 * This avoids endless requeue from tmigr_new_timer().
+		 */
+		if (READ_ONCE(tmc->wakeup) == KTIME_MAX)
+			return;
+	}
 
 	data.now = get_jiffies_update(&data.basej);
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61c541c36596..47345bf1d4a9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -965,7 +965,7 @@ config FTRACE_RECORD_RECURSION
 
 config FTRACE_RECORD_RECURSION_SIZE
 	int "Max number of recursed functions to record"
-	default	128
+	default 128
 	depends on FTRACE_RECORD_RECURSION
 	help
 	  This defines the limit of number of functions that can be
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0a5c4efc73c3..9dc605f08a23 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2728,7 +2728,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
 
 static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
 	.release = bpf_kprobe_multi_link_release,
-	.dealloc = bpf_kprobe_multi_link_dealloc,
+	.dealloc_deferred = bpf_kprobe_multi_link_dealloc,
 	.fill_link_info = bpf_kprobe_multi_link_fill_link_info,
 };
 
@@ -3157,6 +3157,9 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link)
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
 	bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+	if (umulti_link->task)
+		put_task_struct(umulti_link->task);
+	path_put(&umulti_link->path);
 }
 
 static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
@@ -3164,9 +3167,6 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
 	struct bpf_uprobe_multi_link *umulti_link;
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
-	if (umulti_link->task)
-		put_task_struct(umulti_link->task);
-	path_put(&umulti_link->path);
 	kvfree(umulti_link->uprobes);
 	kfree(umulti_link);
 }
@@ -3242,7 +3242,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
 
 static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
 	.release = bpf_uprobe_multi_link_release,
-	.dealloc = bpf_uprobe_multi_link_dealloc,
+	.dealloc_deferred = bpf_uprobe_multi_link_dealloc,
 	.fill_link_info = bpf_uprobe_multi_link_fill_link_info,
 };
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 25476ead681b..6511dc3a00da 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1393,7 +1393,6 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 	old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
 	old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
 
-	local_inc(&cpu_buffer->pages_touched);
 	/*
 	 * Just make sure we have seen our old_write and synchronize
 	 * with any interrupts that come in.
@@ -1430,8 +1429,9 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		local_set(&next_page->page->commit, 0);
 
-		/* Again, either we update tail_page or an interrupt does */
-		(void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page);
+		/* Either we update tail_page or an interrupt does */
+		if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page))
+			local_inc(&cpu_buffer->pages_touched);
 	}
 }
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7c364b87352e..52f75c36bbca 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1670,6 +1670,7 @@ static int trace_format_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+#ifdef CONFIG_PERF_EVENTS
 static ssize_t
 event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
@@ -1684,6 +1685,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
 }
+#endif
 
 static ssize_t
 event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
@@ -2152,10 +2154,12 @@ static const struct file_operations ftrace_event_format_fops = {
 	.release = seq_release,
 };
 
+#ifdef CONFIG_PERF_EVENTS
 static const struct file_operations ftrace_event_id_fops = {
 	.read = event_id_read,
 	.llseek = default_llseek,
 };
+#endif
 
 static const struct file_operations ftrace_event_filter_fops = {
 	.open = tracing_open_file_tr,
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 217169de0920..dfe3ee6035ec 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -839,7 +839,7 @@ out:
 void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs)
 {
 	struct probe_entry_arg *earg = tp->entry_arg;
-	unsigned long val;
+	unsigned long val = 0;
 	int i;
 
 	if (!earg)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bf2bdac46843..0066c8f6c154 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7080,7 +7080,7 @@ static struct device_attribute wq_sysfs_unbound_attrs[] = {
 	__ATTR_NULL,
 };
 
-static struct bus_type wq_subsys = {
+static const struct bus_type wq_subsys = {
 	.name				= "workqueue",
 	.dev_groups			= wq_sysfs_groups,
 };