19 files changed, 183 insertions, 197 deletions

diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 2f0597320b6d..6639640523c0 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -125,8 +125,12 @@ static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key,
 
 	fd = *(int *)key;
 	f = fget_raw(fd);
-	if (!f || !inode_storage_ptr(f->f_inode))
+	if (!f)
+		return -EBADF;
+	if (!inode_storage_ptr(f->f_inode)) {
+		fput(f);
 		return -EBADF;
+	}
 
 	sdata = bpf_local_storage_update(f->f_inode,
 					 (struct bpf_local_storage_map *)map,
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 70e5e0b6d69d..1622a44d1617 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -149,7 +149,11 @@ BTF_ID(func, bpf_lsm_file_ioctl)
 BTF_ID(func, bpf_lsm_file_lock)
 BTF_ID(func, bpf_lsm_file_open)
 BTF_ID(func, bpf_lsm_file_receive)
+
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_inet_conn_established)
+#endif /* CONFIG_SECURITY_NETWORK */
+
 BTF_ID(func, bpf_lsm_inode_create)
 BTF_ID(func, bpf_lsm_inode_free_security)
 BTF_ID(func, bpf_lsm_inode_getattr)
@@ -166,7 +170,11 @@ BTF_ID(func, bpf_lsm_inode_symlink)
 BTF_ID(func, bpf_lsm_inode_unlink)
 BTF_ID(func, bpf_lsm_kernel_module_request)
 BTF_ID(func, bpf_lsm_kernfs_init_security)
+
+#ifdef CONFIG_KEYS
 BTF_ID(func, bpf_lsm_key_free)
+#endif /* CONFIG_KEYS */
+
 BTF_ID(func, bpf_lsm_mmap_file)
 BTF_ID(func, bpf_lsm_netlink_send)
 BTF_ID(func, bpf_lsm_path_notify)
@@ -181,6 +189,8 @@ BTF_ID(func, bpf_lsm_sb_show_options)
 BTF_ID(func, bpf_lsm_sb_statfs)
 BTF_ID(func, bpf_lsm_sb_umount)
 BTF_ID(func, bpf_lsm_settime)
+
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_socket_accept)
 BTF_ID(func, bpf_lsm_socket_bind)
 BTF_ID(func, bpf_lsm_socket_connect)
@@ -195,6 +205,8 @@ BTF_ID(func, bpf_lsm_socket_recvmsg)
 BTF_ID(func, bpf_lsm_socket_sendmsg)
 BTF_ID(func, bpf_lsm_socket_shutdown)
 BTF_ID(func, bpf_lsm_socket_socketpair)
+#endif /* CONFIG_SECURITY_NETWORK */
+
 BTF_ID(func, bpf_lsm_syslog)
 BTF_ID(func, bpf_lsm_task_alloc)
 BTF_ID(func, bpf_lsm_task_getsecid)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 96555a8a2c54..6aa9e10c6335 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1442,6 +1442,11 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 			goto out;
 		}
 
+		if (ctx.optlen < 0) {
+			ret = -EFAULT;
+			goto out;
+		}
+
 		if (copy_from_user(ctx.optval, optval,
 				   min(ctx.optlen, max_optlen)) != 0) {
 			ret = -EFAULT;
@@ -1459,7 +1464,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		goto out;
 	}
 
-	if (ctx.optlen > max_optlen) {
+	if (ctx.optlen > max_optlen || ctx.optlen < 0) {
 		ret = -EFAULT;
 		goto out;
 	}
diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile
index 23ee310b6eb4..1951332dd15f 100644
--- a/kernel/bpf/preload/Makefile
+++ b/kernel/bpf/preload/Makefile
@@ -4,8 +4,11 @@ LIBBPF_SRCS = $(srctree)/tools/lib/bpf/
 LIBBPF_A = $(obj)/libbpf.a
 LIBBPF_OUT = $(abspath $(obj))
 
+# Although not in use by libbpf's Makefile, set $(O) so that the "dummy" test
+# in tools/scripts/Makefile.include always succeeds when building the kernel
+# with $(O) pointing to a relative path, as in "make O=build bindeb-pkg".
 $(LIBBPF_A):
-	$(Q)$(MAKE) -C $(LIBBPF_SRCS) OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a
+	$(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a
 
 userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \
 	-I $(srctree)/tools/lib/ -Wno-unused-result
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index aea96b638473..bfafbf115bf3 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -115,6 +115,8 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 
 	/* hash table size must be power of 2 */
 	n_buckets = roundup_pow_of_two(attr->max_entries);
+	if (!n_buckets)
+		return ERR_PTR(-E2BIG);
 
 	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
 	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e7368c5eacb7..37581919e050 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6877,7 +6877,7 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
 	case BPF_JSGT:
 		if (reg->s32_min_value > sval)
 			return 1;
-		else if (reg->s32_max_value < sval)
+		else if (reg->s32_max_value <= sval)
 			return 0;
 		break;
 	case BPF_JLT:
@@ -6950,7 +6950,7 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 	case BPF_JSGT:
 		if (reg->smin_value > sval)
 			return 1;
-		else if (reg->smax_value < sval)
+		else if (reg->smax_value <= sval)
 			return 0;
 		break;
 	case BPF_JLT:
@@ -8590,7 +8590,11 @@ static bool range_within(struct bpf_reg_state *old,
 	return old->umin_value <= cur->umin_value &&
 	       old->umax_value >= cur->umax_value &&
 	       old->smin_value <= cur->smin_value &&
-	       old->smax_value >= cur->smax_value;
+	       old->smax_value >= cur->smax_value &&
+	       old->u32_min_value <= cur->u32_min_value &&
+	       old->u32_max_value >= cur->u32_max_value &&
+	       old->s32_min_value <= cur->s32_min_value &&
+	       old->s32_max_value >= cur->s32_max_value;
 }
 
 /* Maximum number of register states that can exist at once */
@@ -10999,30 +11003,28 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 		    insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
 		    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
 			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
-			struct bpf_insn mask_and_div[] = {
-				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
+			bool isdiv = BPF_OP(insn->code) == BPF_DIV;
+			struct bpf_insn *patchlet;
+			struct bpf_insn chk_and_div[] = {
 				/* Rx div 0 -> 0 */
-				BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2),
+				BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
+					     BPF_JNE | BPF_K, insn->src_reg,
+					     0, 2, 0),
 				BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg),
 				BPF_JMP_IMM(BPF_JA, 0, 0, 1),
 				*insn,
 			};
-			struct bpf_insn mask_and_mod[] = {
-				BPF_MOV32_REG(insn->src_reg, insn->src_reg),
+			struct bpf_insn chk_and_mod[] = {
 				/* Rx mod 0 -> Rx */
-				BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1),
+				BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
+					     BPF_JEQ | BPF_K, insn->src_reg,
+					     0, 1, 0),
 				*insn,
 			};
-			struct bpf_insn *patchlet;
 
-			if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
-			    insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
-				patchlet = mask_and_div + (is64 ? 1 : 0);
-				cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0);
-			} else {
-				patchlet = mask_and_mod + (is64 ? 1 : 0);
-				cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0);
-			}
+			patchlet = isdiv ? chk_and_div : chk_and_mod;
+			cnt = isdiv ? ARRAY_SIZE(chk_and_div) :
+				      ARRAY_SIZE(chk_and_mod);
 
 			new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
 			if (!new_prog)
diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index b1496e744c68..da95df381483 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -36,7 +36,7 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u64 expansion[10];	/* For future use */
+	__u8 expansion[84];	/* For future use */
 };
 
 struct map_benchmark_data {
@@ -147,8 +147,10 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 	atomic64_set(&map->sum_sq_unmap, 0);
 	atomic64_set(&map->loops, 0);
 
-	for (i = 0; i < threads; i++)
+	for (i = 0; i < threads; i++) {
+		get_task_struct(tsk[i]);
 		wake_up_process(tsk[i]);
+	}
 
 	msleep_interruptible(map->bparam.seconds * 1000);
 
@@ -183,6 +185,8 @@ static int do_map_benchmark(struct map_benchmark_data *map)
 	}
 
 out:
+	for (i = 0; i < threads; i++)
+		put_task_struct(tsk[i]);
 	put_device(map->dev);
 	kfree(tsk);
 	return ret;
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 378341642f94..f9d491b17b78 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -209,26 +209,18 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 	lockdep_sys_exit();
 }
 
-#ifndef _TIF_SINGLESTEP
-static inline bool report_single_step(unsigned long work)
-{
-	return false;
-}
-#else
 /*
  * If SYSCALL_EMU is set, then the only reason to report is when
- * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
  * instruction has been already reported in syscall_enter_from_user_mode().
  */
 static inline bool report_single_step(unsigned long work)
 {
-	if (!(work & SYSCALL_WORK_SYSCALL_EMU))
+	if (work & SYSCALL_WORK_SYSCALL_EMU)
 		return false;
 
-	return !!(current_thread_info()->flags & _TIF_SINGLESTEP);
+	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
 }
-#endif
-
 
 static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index b0338a5625d9..c240302f56e2 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -50,10 +50,10 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 		if (unlikely(__get_user(state, sd->selector)))
 			do_exit(SIGSEGV);
 
-		if (likely(state == PR_SYS_DISPATCH_OFF))
+		if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW))
 			return false;
 
-		if (state != PR_SYS_DISPATCH_ON)
+		if (state != SYSCALL_DISPATCH_FILTER_BLOCK)
 			do_exit(SIGSYS);
 	}
 
diff --git a/kernel/futex.c b/kernel/futex.c
index c47d1015d759..45a13eb8894e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -763,6 +763,29 @@ static struct futex_pi_state *alloc_pi_state(void)
 	return pi_state;
 }
 
+static void pi_state_update_owner(struct futex_pi_state *pi_state,
+				  struct task_struct *new_owner)
+{
+	struct task_struct *old_owner = pi_state->owner;
+
+	lockdep_assert_held(&pi_state->pi_mutex.wait_lock);
+
+	if (old_owner) {
+		raw_spin_lock(&old_owner->pi_lock);
+		WARN_ON(list_empty(&pi_state->list));
+		list_del_init(&pi_state->list);
+		raw_spin_unlock(&old_owner->pi_lock);
+	}
+
+	if (new_owner) {
+		raw_spin_lock(&new_owner->pi_lock);
+		WARN_ON(!list_empty(&pi_state->list));
+		list_add(&pi_state->list, &new_owner->pi_state_list);
+		pi_state->owner = new_owner;
+		raw_spin_unlock(&new_owner->pi_lock);
+	}
+}
+
 static void get_pi_state(struct futex_pi_state *pi_state)
 {
 	WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount));
@@ -785,17 +808,11 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 	 * and has cleaned up the pi_state already
 	 */
 	if (pi_state->owner) {
-		struct task_struct *owner;
 		unsigned long flags;
 
 		raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
-		owner = pi_state->owner;
-		if (owner) {
-			raw_spin_lock(&owner->pi_lock);
-			list_del_init(&pi_state->list);
-			raw_spin_unlock(&owner->pi_lock);
-		}
-		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
+		pi_state_update_owner(pi_state, NULL);
+		rt_mutex_proxy_unlock(&pi_state->pi_mutex);
 		raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
 	}
 
@@ -941,7 +958,8 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
  *	FUTEX_OWNER_DIED bit. See [4]
  *
  * [10] There is no transient state which leaves owner and user space
- *	TID out of sync.
+ *	TID out of sync. Except one error case where the kernel is denied
+ *	write access to the user address, see fixup_pi_state_owner().
  *
  *
  * Serialization and lifetime rules:
@@ -1521,26 +1539,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 			ret = -EINVAL;
 	}
 
-	if (ret)
-		goto out_unlock;
-
-	/*
-	 * This is a point of no return; once we modify the uval there is no
-	 * going back and subsequent operations must not fail.
-	 */
-
-	raw_spin_lock(&pi_state->owner->pi_lock);
-	WARN_ON(list_empty(&pi_state->list));
-	list_del_init(&pi_state->list);
-	raw_spin_unlock(&pi_state->owner->pi_lock);
-
-	raw_spin_lock(&new_owner->pi_lock);
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &new_owner->pi_state_list);
-	pi_state->owner = new_owner;
-	raw_spin_unlock(&new_owner->pi_lock);
-
-	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+	if (!ret) {
+		/*
+		 * This is a point of no return; once we modified the uval
+		 * there is no going back and subsequent operations must
+		 * not fail.
+		 */
+		pi_state_update_owner(pi_state, new_owner);
+		postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+	}
 
 out_unlock:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
@@ -2323,18 +2330,13 @@ static void unqueue_me_pi(struct futex_q *q)
 	spin_unlock(q->lock_ptr);
 }
 
-static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *argowner)
+static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
+				  struct task_struct *argowner)
 {
 	struct futex_pi_state *pi_state = q->pi_state;
-	u32 uval, curval, newval;
 	struct task_struct *oldowner, *newowner;
-	u32 newtid;
-	int ret, err = 0;
-
-	lockdep_assert_held(q->lock_ptr);
-
-	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+	u32 uval, curval, newval, newtid;
+	int err = 0;
 
 	oldowner = pi_state->owner;
 
@@ -2368,14 +2370,12 @@ retry:
 			 * We raced against a concurrent self; things are
 			 * already fixed up. Nothing to do.
 			 */
-			ret = 0;
-			goto out_unlock;
+			return 0;
 		}
 
 		if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
-			/* We got the lock after all, nothing to fix. */
-			ret = 0;
-			goto out_unlock;
+			/* We got the lock. pi_state is correct. Tell caller. */
+			return 1;
 		}
 
 		/*
@@ -2402,8 +2402,7 @@ retry:
 			 * We raced against a concurrent self; things are
 			 * already fixed up. Nothing to do.
 			 */
-			ret = 0;
-			goto out_unlock;
+			return 1;
 		}
 		newowner = argowner;
 	}
@@ -2433,22 +2432,9 @@ retry:
 	 * We fixed up user space. Now we need to fix the pi_state
 	 * itself.
 	 */
-	if (pi_state->owner != NULL) {
-		raw_spin_lock(&pi_state->owner->pi_lock);
-		WARN_ON(list_empty(&pi_state->list));
-		list_del_init(&pi_state->list);
-		raw_spin_unlock(&pi_state->owner->pi_lock);
-	}
+	pi_state_update_owner(pi_state, newowner);
 
-	pi_state->owner = newowner;
-
-	raw_spin_lock(&newowner->pi_lock);
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &newowner->pi_state_list);
-	raw_spin_unlock(&newowner->pi_lock);
-	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-
-	return 0;
+	return argowner == current;
 
 	/*
 	 * In order to reschedule or handle a page fault, we need to drop the
@@ -2469,17 +2455,16 @@ handle_err:
 
 	switch (err) {
 	case -EFAULT:
-		ret = fault_in_user_writeable(uaddr);
+		err = fault_in_user_writeable(uaddr);
 		break;
 
 	case -EAGAIN:
 		cond_resched();
-		ret = 0;
+		err = 0;
 		break;
 
 	default:
 		WARN_ON_ONCE(1);
-		ret = err;
 		break;
 	}
 
@@ -2489,17 +2474,44 @@ handle_err:
 	/*
 	 * Check if someone else fixed it for us:
 	 */
-	if (pi_state->owner != oldowner) {
-		ret = 0;
-		goto out_unlock;
-	}
+	if (pi_state->owner != oldowner)
+		return argowner == current;
 
-	if (ret)
-		goto out_unlock;
+	/* Retry if err was -EAGAIN or the fault in succeeded */
+	if (!err)
+		goto retry;
 
-	goto retry;
+	/*
+	 * fault_in_user_writeable() failed so user state is immutable. At
+	 * best we can make the kernel state consistent but user state will
+	 * be most likely hosed and any subsequent unlock operation will be
+	 * rejected due to PI futex rule [10].
+	 *
+	 * Ensure that the rtmutex owner is also the pi_state owner despite
+	 * the user space value claiming something different. There is no
+	 * point in unlocking the rtmutex if current is the owner as it
+	 * would need to wait until the next waiter has taken the rtmutex
+	 * to guarantee consistent state. Keep it simple. Userspace asked
+	 * for this wreckaged state.
+	 *
+	 * The rtmutex has an owner - either current or some other
+	 * task. See the EAGAIN loop above.
+	 */
+	pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex));
 
-out_unlock:
+	return err;
+}
+
+static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
+				struct task_struct *argowner)
+{
+	struct futex_pi_state *pi_state = q->pi_state;
+	int ret;
+
+	lockdep_assert_held(q->lock_ptr);
+
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+	ret = __fixup_pi_state_owner(uaddr, q, argowner);
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	return ret;
 }
@@ -2523,8 +2535,6 @@ static long futex_wait_restart(struct restart_block *restart);
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	int ret = 0;
-
 	if (locked) {
 		/*
 		 * Got the lock. We might not be the anticipated owner if we
@@ -2535,8 +2545,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * stable state, anything else needs more attention.
 		 */
 		if (q->pi_state->owner != current)
-			ret = fixup_pi_state_owner(uaddr, q, current);
-		return ret ? ret : locked;
+			return fixup_pi_state_owner(uaddr, q, current);
+		return 1;
 	}
 
 	/*
@@ -2547,23 +2557,17 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 	 * Another speculative read; pi_state->owner == current is unstable
 	 * but needs our attention.
 	 */
-	if (q->pi_state->owner == current) {
-		ret = fixup_pi_state_owner(uaddr, q, NULL);
-		return ret;
-	}
+	if (q->pi_state->owner == current)
+		return fixup_pi_state_owner(uaddr, q, NULL);
 
 	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
-	 * the owner of the rt_mutex.
+	 * the owner of the rt_mutex. Warn and establish consistent state.
 	 */
-	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
-		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
-				"pi-state %p\n", ret,
-				q->pi_state->pi_mutex.owner,
-				q->pi_state->owner);
-	}
+	if (WARN_ON_ONCE(rt_mutex_owner(&q->pi_state->pi_mutex) == current))
+		return fixup_pi_state_owner(uaddr, q, current);
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -2771,7 +2775,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 			 ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct futex_pi_state *pi_state = NULL;
 	struct task_struct *exiting = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
@@ -2907,23 +2910,8 @@ no_block:
 	if (res)
 		ret = (res < 0) ? res : 0;
 
-	/*
-	 * If fixup_owner() faulted and was unable to handle the fault, unlock
-	 * it and return the fault to userspace.
-	 */
-	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) {
-		pi_state = q.pi_state;
-		get_pi_state(pi_state);
-	}
-
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
-
-	if (pi_state) {
-		rt_mutex_futex_unlock(&pi_state->pi_mutex);
-		put_pi_state(pi_state);
-	}
-
 	goto out;
 
 out_unlock_put_key:
@@ -3183,7 +3171,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				 u32 __user *uaddr2)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
@@ -3261,16 +3248,17 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
-			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
-				pi_state = q.pi_state;
-				get_pi_state(pi_state);
-			}
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
 			 */
 			put_pi_state(q.pi_state);
 			spin_unlock(q.lock_ptr);
+			/*
+			 * Adjust the return value. It's either -EFAULT or
+			 * success (1) but the caller expects 0 for success.
+			 */
+			ret = ret < 0 ? ret : 0;
 		}
 	} else {
 		struct rt_mutex *pi_mutex;
@@ -3301,25 +3289,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
-		/*
-		 * If fixup_pi_state_owner() faulted and was unable to handle
-		 * the fault, unlock the rt_mutex and return the fault to
-		 * userspace.
-		 */
-		if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
-			pi_state = q.pi_state;
-			get_pi_state(pi_state);
-		}
-
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	if (pi_state) {
-		rt_mutex_futex_unlock(&pi_state->pi_mutex);
-		put_pi_state(pi_state);
-	}
-
 	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index 3110c77230c7..f62de2dea8a3 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -4,7 +4,7 @@ menu "GCOV-based kernel profiling"
 config GCOV_KERNEL
 	bool "Enable gcov-based kernel profiling"
 	depends on DEBUG_FS
-	select CONSTRUCTORS if !UML
+	select CONSTRUCTORS
 	default n
 	help
 	This option enables gcov-based code profiling (e.g. for code coverage
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index dc0e2d7fbdfd..b338d622f26e 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -436,22 +436,22 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 
 	can_reserve = msi_check_reservation_mode(domain, info, dev);
 
-	for_each_msi_entry(desc, dev) {
-		virq = desc->irq;
-		if (desc->nvec_used == 1)
-			dev_dbg(dev, "irq %d for MSI\n", virq);
-		else
+	/*
+	 * This flag is set by the PCI layer as we need to activate
+	 * the MSI entries before the PCI layer enables MSI in the
+	 * card. Otherwise the card latches a random msi message.
+	 */
+	if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
+		goto skip_activate;
+
+	for_each_msi_vector(desc, i, dev) {
+		if (desc->irq == i) {
+			virq = desc->irq;
 			dev_dbg(dev, "irq [%d-%d] for MSI\n",
 				virq, virq + desc->nvec_used - 1);
-		/*
-		 * This flag is set by the PCI layer as we need to activate
-		 * the MSI entries before the PCI layer enables MSI in the
-		 * card. Otherwise the card latches a random msi message.
-		 */
-		if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
-			continue;
+		}
 
-		irq_data = irq_domain_get_irq_data(domain, desc->irq);
+		irq_data = irq_domain_get_irq_data(domain, i);
 		if (!can_reserve) {
 			irqd_clr_can_reserve(irq_data);
 			if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
@@ -462,28 +462,24 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			goto cleanup;
 	}
 
+skip_activate:
 	/*
 	 * If these interrupts use reservation mode, clear the activated bit
 	 * so request_irq() will assign the final vector.
 	 */
 	if (can_reserve) {
-		for_each_msi_entry(desc, dev) {
-			irq_data = irq_domain_get_irq_data(domain, desc->irq);
+		for_each_msi_vector(desc, i, dev) {
+			irq_data = irq_domain_get_irq_data(domain, i);
 			irqd_clr_activated(irq_data);
 		}
 	}
 	return 0;
 
 cleanup:
-	for_each_msi_entry(desc, dev) {
-		struct irq_data *irqd;
-
-		if (desc->irq == virq)
-			break;
-
-		irqd = irq_domain_get_irq_data(domain, desc->irq);
-		if (irqd_is_activated(irqd))
-			irq_domain_deactivate_irq(irqd);
+	for_each_msi_vector(desc, i, dev) {
+		irq_data = irq_domain_get_irq_data(domain, i);
+		if (irqd_is_activated(irq_data))
+			irq_domain_deactivate_irq(irq_data);
 	}
 	msi_domain_free_irqs(domain, dev);
 	return ret;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 4f8efc278aa7..aa919585c24b 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1134,7 +1134,6 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
-		lock_system_sleep();
 		pm_prepare_console();
 		error = freeze_processes();
 		if (error) {
@@ -1197,7 +1196,6 @@ int kernel_kexec(void)
 		thaw_processes();
  Restore_console:
 		pm_restore_console();
-		unlock_system_sleep();
 	}
 #endif
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index cfdd5b93264d..2f8cd616d3b2 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1716,8 +1716,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
  * possible because it belongs to the pi_state which is about to be freed
  * and it is not longer visible to other tasks.
  */
-void rt_mutex_proxy_unlock(struct rt_mutex *lock,
-			   struct task_struct *proxy_owner)
+void rt_mutex_proxy_unlock(struct rt_mutex *lock)
 {
 	debug_rt_mutex_proxy_unlock(lock);
 	rt_mutex_set_owner(lock, NULL);
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index d1d62f942be2..ca6fb489007b 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -133,8 +133,7 @@ enum rtmutex_chainwalk {
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
-extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
-				  struct task_struct *proxy_owner);
+extern void rt_mutex_proxy_unlock(struct rt_mutex *lock);
 extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
 extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index c73f2e295167..72e33054a2e1 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -497,10 +497,10 @@ static int swap_writer_finish(struct swap_map_handle *handle,
 		unsigned int flags, int error)
 {
 	if (!error) {
-		flush_swap_writer(handle);
 		pr_info("S");
 		error = mark_swapfiles(handle, flags);
 		pr_cont("|\n");
+		flush_swap_writer(handle);
 	}
 
 	if (error)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 6639a0cfe0ac..5a95c688621f 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1398,7 +1398,7 @@ static size_t record_print_text(struct printk_record *r, bool syslog,
 	 * not counted in the return value.
 	 */
 	if (buf_size > 0)
-		text[len] = 0;
+		r->text_buf[len] = 0;
 
 	return len;
 }
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 87389b9e21ab..5247afd7f345 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -502,7 +502,7 @@ static struct hrtimer sync_hrtimer;
 
 static enum hrtimer_restart sync_timer_callback(struct hrtimer *timer)
 {
-	queue_work(system_power_efficient_wq, &sync_work);
+	queue_work(system_freezable_power_efficient_wq, &sync_work);
 
 	return HRTIMER_NORESTART;
 }
@@ -668,7 +668,7 @@ void ntp_notify_cmos_timer(void)
 	 * just a pointless work scheduled.
 	 */
 	if (ntp_synced() && !hrtimer_is_queued(&sync_hrtimer))
-		queue_work(system_power_efficient_wq, &sync_work);
+		queue_work(system_freezable_power_efficient_wq, &sync_work);
 }
 
 static void __init ntp_init_cmos_sync(void)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6c0018abe68a..764400260eb6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -96,9 +96,6 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
 	unsigned int ret;
 
-	if (in_nmi()) /* not supported yet */
-		return 1;
-
 	cant_sleep();
 
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {