Merge branch 'nfsd-5.8' of git://linux-nfs.org/~cel/cel-2.6 into for-5.8-incoming

Highlights of this series:
* Remove serialization of sending RPC/RDMA Replies
* Convert the TCP socket send path to use xdr_buf::bvecs (pre-requisite for
RPC-on-TLS)
* Fix svcrdma backchannel sendto return code
* Convert a number of dprintk call sites to use tracepoints
* Fix the "suggest braces around empty body in an 'else' statement" warning

kernel/bpf/arraymap.c

@@ -486,7 +486,12 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 	if (!(map->map_flags & BPF_F_MMAPABLE))
 		return -EINVAL;
 
-	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
+	if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) >
+	    PAGE_ALIGN((u64)array->map.max_entries * array->elem_size))
+		return -EINVAL;
+
+	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array),
+				   vma->vm_pgoff + pgoff);
 }
 
 const struct bpf_map_ops array_map_ops = {

kernel/bpf/syscall.c

@@ -1485,8 +1485,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (err)
 		goto free_value;
 
-	if (copy_to_user(uvalue, value, value_size) != 0)
+	if (copy_to_user(uvalue, value, value_size) != 0) {
+		err = -EFAULT;
 		goto free_value;
+	}
 
 	err = 0;
 

kernel/bpf/verifier.c

@@ -4340,7 +4340,9 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 
 	if (ret_type != RET_INTEGER ||
 	    (func_id != BPF_FUNC_get_stack &&
-	     func_id != BPF_FUNC_probe_read_str))
+	     func_id != BPF_FUNC_probe_read_str &&
+	     func_id != BPF_FUNC_probe_read_kernel_str &&
+	     func_id != BPF_FUNC_probe_read_user_str))
 		return;
 
 	ret_reg->smax_value = meta->msize_max_value;
@@ -7059,6 +7061,23 @@ static int check_return_code(struct bpf_verifier_env *env)
 			return 0;
 		range = tnum_const(0);
 		break;
+	case BPF_PROG_TYPE_TRACING:
+		switch (env->prog->expected_attach_type) {
+		case BPF_TRACE_FENTRY:
+		case BPF_TRACE_FEXIT:
+			range = tnum_const(0);
+			break;
+		case BPF_TRACE_RAW_TP:
+		case BPF_MODIFY_RETURN:
+			return 0;
+		default:
+			return -ENOTSUPP;
+		}
+		break;
+	case BPF_PROG_TYPE_EXT:
+		/* freplace program can return anything as its return value
+		 * depends on the to-be-replaced kernel func or bpf program.
+		 */
 	default:
 		return 0;
 	}

kernel/fork.c

@@ -2486,11 +2486,11 @@ long do_fork(unsigned long clone_flags,
 	      int __user *child_tidptr)
 {
 	struct kernel_clone_args args = {
-		.flags		= (clone_flags & ~CSIGNAL),
+		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
 		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
-		.exit_signal	= (clone_flags & CSIGNAL),
+		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
 		.stack		= stack_start,
 		.stack_size	= stack_size,
 	};
@@ -2508,8 +2508,9 @@ long do_fork(unsigned long clone_flags,
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
 	struct kernel_clone_args args = {
-		.flags		= ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL),
-		.exit_signal	= (flags & CSIGNAL),
+		.flags		= ((lower_32_bits(flags) | CLONE_VM |
+				    CLONE_UNTRACED) & ~CSIGNAL),
+		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
 		.stack		= (unsigned long)fn,
 		.stack_size	= (unsigned long)arg,
 	};
@@ -2570,11 +2571,11 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 #endif
 {
 	struct kernel_clone_args args = {
-		.flags		= (clone_flags & ~CSIGNAL),
+		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
 		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
-		.exit_signal	= (clone_flags & CSIGNAL),
+		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
 		.stack		= newsp,
 		.tls		= tls,
 	};

kernel/kcov.c

@@ -740,8 +740,8 @@ static const struct file_operations kcov_fops = {
  * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an
  * arbitrary 4-byte non-zero number as the instance id). This common handle
  * then gets saved into the task_struct of the process that issued the
- * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn
- * kernel threads, the common handle must be retrived via kcov_common_handle()
+ * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn
+ * kernel threads, the common handle must be retrieved via kcov_common_handle()
  * and passed to the spawned threads via custom annotations. Those kernel
  * threads must in turn be annotated with kcov_remote_start(common_handle) and
  * kcov_remote_stop(). All of the threads that are spawned by the same process

kernel/trace/Kconfig

@@ -466,7 +466,6 @@ config PROFILE_ANNOTATED_BRANCHES
 config PROFILE_ALL_BRANCHES
 	bool "Profile all if conditionals" if !FORTIFY_SOURCE
 	select TRACE_BRANCH_PROFILING
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  This tracer profiles all branch conditions. Every if ()
 	  taken in the kernel is recorded whether it hit or miss.

kernel/trace/bpf_trace.c

@@ -323,17 +323,15 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
 
 /*
  * Only limited trace_printk() conversion specifiers allowed:
- * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
  */
 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 	   u64, arg2, u64, arg3)
 {
+	int i, mod[3] = {}, fmt_cnt = 0;
+	char buf[64], fmt_ptype;
+	void *unsafe_ptr = NULL;
 	bool str_seen = false;
-	int mod[3] = {};
-	int fmt_cnt = 0;
-	u64 unsafe_addr;
-	char buf[64];
-	int i;
 
 	/*
 	 * bpf_check()->check_func_arg()->check_stack_boundary()
@@ -359,40 +357,71 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		if (fmt[i] == 'l') {
 			mod[fmt_cnt]++;
 			i++;
-		} else if (fmt[i] == 'p' || fmt[i] == 's') {
+		} else if (fmt[i] == 'p') {
 			mod[fmt_cnt]++;
+			if ((fmt[i + 1] == 'k' ||
+			     fmt[i + 1] == 'u') &&
+			    fmt[i + 2] == 's') {
+				fmt_ptype = fmt[i + 1];
+				i += 2;
+				goto fmt_str;
+			}
+
 			/* disallow any further format extensions */
 			if (fmt[i + 1] != 0 &&
 			    !isspace(fmt[i + 1]) &&
 			    !ispunct(fmt[i + 1]))
 				return -EINVAL;
-			fmt_cnt++;
-			if (fmt[i] == 's') {
-				if (str_seen)
-					/* allow only one '%s' per fmt string */
-					return -EINVAL;
-				str_seen = true;
 
-				switch (fmt_cnt) {
-				case 1:
-					unsafe_addr = arg1;
-					arg1 = (long) buf;
-					break;
-				case 2:
-					unsafe_addr = arg2;
-					arg2 = (long) buf;
-					break;
-				case 3:
-					unsafe_addr = arg3;
-					arg3 = (long) buf;
-					break;
-				}
-				buf[0] = 0;
-				strncpy_from_unsafe(buf,
-						    (void *) (long) unsafe_addr,
-						    sizeof(buf));
+			goto fmt_next;
+		} else if (fmt[i] == 's') {
+			mod[fmt_cnt]++;
+			fmt_ptype = fmt[i];
+fmt_str:
+			if (str_seen)
+				/* allow only one '%s' per fmt string */
+				return -EINVAL;
+			str_seen = true;
+
+			if (fmt[i + 1] != 0 &&
+			    !isspace(fmt[i + 1]) &&
+			    !ispunct(fmt[i + 1]))
+				return -EINVAL;
+
+			switch (fmt_cnt) {
+			case 0:
+				unsafe_ptr = (void *)(long)arg1;
+				arg1 = (long)buf;
+				break;
+			case 1:
+				unsafe_ptr = (void *)(long)arg2;
+				arg2 = (long)buf;
+				break;
+			case 2:
+				unsafe_ptr = (void *)(long)arg3;
+				arg3 = (long)buf;
+				break;
 			}
-			continue;
+
+			buf[0] = 0;
+			switch (fmt_ptype) {
+			case 's':
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+				strncpy_from_unsafe(buf, unsafe_ptr,
+						    sizeof(buf));
+				break;
+#endif
+			case 'k':
+				strncpy_from_unsafe_strict(buf, unsafe_ptr,
+							   sizeof(buf));
+				break;
+			case 'u':
+				strncpy_from_unsafe_user(buf,
+					(__force void __user *)unsafe_ptr,
+							 sizeof(buf));
+				break;
+			}
+			goto fmt_next;
 		}
 
 		if (fmt[i] == 'l') {
@@ -403,6 +432,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		if (fmt[i] != 'i' && fmt[i] != 'd' &&
 		    fmt[i] != 'u' && fmt[i] != 'x')
 			return -EINVAL;
+fmt_next:
 		fmt_cnt++;
 	}
 
@@ -825,14 +855,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
 		return &bpf_probe_read_kernel_proto;
-	case BPF_FUNC_probe_read:
-		return &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_user_str:
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
 		return &bpf_probe_read_kernel_str_proto;
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	case BPF_FUNC_probe_read:
+		return &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_str:
 		return &bpf_probe_read_compat_str_proto;
+#endif
 #ifdef CONFIG_CGROUPS
 	case BPF_FUNC_get_current_cgroup_id:
 		return &bpf_get_current_cgroup_id_proto;

kernel/trace/ftrace_internal.h

@@ -4,28 +4,6 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-/*
- * Traverse the ftrace_global_list, invoking all entries.  The reason that we
- * can use rcu_dereference_raw_check() is that elements removed from this list
- * are simply leaked, so there is no need to interact with a grace-period
- * mechanism.  The rcu_dereference_raw_check() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
- *
- * Silly Alpha and silly pointer-speculation compiler optimizations!
- */
-#define do_for_each_ftrace_op(op, list)			\
-	op = rcu_dereference_raw_check(list);			\
-	do
-
-/*
- * Optimized for just a single item in the list (as that is the normal case).
- */
-#define while_for_each_ftrace_op(op)				\
-	while (likely(op = rcu_dereference_raw_check((op)->next)) &&	\
-	       unlikely((op) != &ftrace_list_end))
-
-extern struct ftrace_ops __rcu *ftrace_ops_list;
-extern struct ftrace_ops ftrace_list_end;
 extern struct mutex ftrace_lock;
 extern struct ftrace_ops global_ops;
 

kernel/trace/preemptirq_delay_test.c

@@ -16,6 +16,7 @@
 #include <linux/printk.h>
 #include <linux/string.h>
 #include <linux/sysfs.h>
+#include <linux/completion.h>
 
 static ulong delay = 100;
 static char test_mode[12] = "irq";
@@ -28,6 +29,8 @@ MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)");
 MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)");
 MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)");
 
+static struct completion done;
+
 #define MIN(x, y) ((x) < (y) ? (x) : (y))
 
 static void busy_wait(ulong time)
@@ -113,22 +116,47 @@ static int preemptirq_delay_run(void *data)
 
 	for (i = 0; i < s; i++)
 		(testfuncs[i])(i);
+
+	complete(&done);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+
+	__set_current_state(TASK_RUNNING);
+
 	return 0;
 }
 
-static struct task_struct *preemptirq_start_test(void)
+static int preemptirq_run_test(void)
 {
+	struct task_struct *task;
 	char task_name[50];
 
+	init_completion(&done);
+
 	snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
-	return kthread_run(preemptirq_delay_run, NULL, task_name);
+	task =  kthread_run(preemptirq_delay_run, NULL, task_name);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	if (task) {
+		wait_for_completion(&done);
+		kthread_stop(task);
+	}
+	return 0;
 }
 
 
 static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr,
 			 const char *buf, size_t count)
 {
-	preemptirq_start_test();
+	ssize_t ret;
+
+	ret = preemptirq_run_test();
+	if (ret)
+		return ret;
 	return count;
 }
 
@@ -148,11 +176,9 @@ static struct kobject *preemptirq_delay_kobj;
 
 static int __init preemptirq_delay_init(void)
 {
-	struct task_struct *test_task;
 	int retval;
 
-	test_task = preemptirq_start_test();
-	retval = PTR_ERR_OR_ZERO(test_task);
+	retval = preemptirq_run_test();
 	if (retval != 0)
 		return retval;
 

kernel/trace/ring_buffer.c

@@ -193,7 +193,7 @@ rb_event_length(struct ring_buffer_event *event)
 	case RINGBUF_TYPE_DATA:
 		return rb_event_data_length(event);
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 	/* not hit */
 	return 0;
@@ -249,7 +249,7 @@ rb_event_data(struct ring_buffer_event *event)
 {
 	if (extended_time(event))
 		event = skip_time_extend(event);
-	BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+	WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
 	/* If length is in len field, then array[0] has the data */
 	if (event->type_len)
 		return (void *)&event->array[0];
@@ -3727,7 +3727,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		return;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 	return;
 }
@@ -3757,7 +3757,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 		return;
 
 	default:
-		BUG();
+		RB_WARN_ON(iter->cpu_buffer, 1);
 	}
 	return;
 }
@@ -4020,7 +4020,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
 		return event;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 
 	return NULL;
@@ -4034,7 +4034,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
 	int nr_loops = 0;
-	bool failed = false;
 
 	if (ts)
 		*ts = 0;
@@ -4056,19 +4055,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return NULL;
 
 	/*
-	 * We repeat when a time extend is encountered or we hit
-	 * the end of the page. Since the time extend is always attached
-	 * to a data event, we should never loop more than three times.
-	 * Once for going to next page, once on time extend, and
-	 * finally once to get the event.
-	 * We should never hit the following condition more than thrice,
-	 * unless the buffer is very small, and there's a writer
-	 * that is causing the reader to fail getting an event.
+	 * As the writer can mess with what the iterator is trying
+	 * to read, just give up if we fail to get an event after
+	 * three tries. The iterator is not as reliable when reading
+	 * the ring buffer with an active write as the consumer is.
+	 * Do not warn if the three failures is reached.
 	 */
-	if (++nr_loops > 3) {
-		RB_WARN_ON(cpu_buffer, !failed);
+	if (++nr_loops > 3)
 		return NULL;
-	}
 
 	if (rb_per_cpu_empty(cpu_buffer))
 		return NULL;
@@ -4079,10 +4073,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	}
 
 	event = rb_iter_head_event(iter);
-	if (!event) {
-		failed = true;
+	if (!event)
 		goto again;
-	}
 
 	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
@@ -4117,7 +4109,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return event;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 
 	return NULL;

kernel/trace/trace.c

@@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str)
 EXPORT_SYMBOL_GPL(__trace_bputs);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data)
+static void tracing_snapshot_instance_cond(struct trace_array *tr,
+					   void *cond_data)
 {
 	struct tracer *tracer = tr->current_trace;
 	unsigned long flags;
@@ -8525,6 +8526,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	 */
 	allocate_snapshot = false;
 #endif
+
+	/*
+	 * Because of some magic with the way alloc_percpu() works on
+	 * x86_64, we need to synchronize the pgd of all the tables,
+	 * otherwise the trace events that happen in x86_64 page fault
+	 * handlers can't cope with accessing the chance that a
+	 * alloc_percpu()'d memory might be touched in the page fault trace
+	 * event. Oh, and we need to audit all other alloc_percpu() and vmalloc()
+	 * calls in tracing, because something might get triggered within a
+	 * page fault trace event!
+	 */
+	vmalloc_sync_mappings();
+
 	return 0;
 }
 

kernel/trace/trace_boot.c

@@ -95,23 +95,19 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 	struct xbc_node *anode;
 	char buf[MAX_BUF_LEN];
 	const char *val;
-	int ret;
-
-	kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
-
-	ret = kprobe_event_gen_cmd_start(&cmd, event, NULL);
-	if (ret)
-		return ret;
+	int ret = 0;
 
 	xbc_node_for_each_array_value(node, "probes", anode, val) {
-		ret = kprobe_event_add_field(&cmd, val);
-		if (ret)
-			return ret;
-	}
+		kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
 
-	ret = kprobe_event_gen_cmd_end(&cmd);
-	if (ret)
-		pr_err("Failed to add probe: %s\n", buf);
+		ret = kprobe_event_gen_cmd_start(&cmd, event, val);
+		if (ret)
+			break;
+
+		ret = kprobe_event_gen_cmd_end(&cmd);
+		if (ret)
+			pr_err("Failed to add probe: %s\n", buf);
+	}
 
 	return ret;
 }

kernel/trace/trace_kprobe.c

@@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr)
 
 static bool within_notrace_func(struct trace_kprobe *tk)
 {
-	unsigned long addr = addr = trace_kprobe_address(tk);
+	unsigned long addr = trace_kprobe_address(tk);
 	char symname[KSYM_NAME_LEN], *p;
 
 	if (!__within_notrace_func(addr))
@@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init);
  * complete command or only the first part of it; in the latter case,
  * kprobe_event_add_fields() can be used to add more fields following this.
  *
+ * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This
+ * returns -EINVAL if @loc == NULL.
+ *
  * Return: 0 if successful, error otherwise.
  */
 int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
@@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
 	if (cmd->type != DYNEVENT_TYPE_KPROBE)
 		return -EINVAL;
 
+	if (!loc)
+		return -EINVAL;
+
 	if (kretprobe)
 		snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name);
 	else

kernel/umh.c

@@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info)
 {
 	struct umh_info *umh_info = info->data;
 
+	/* cleanup if umh_pipe_setup() was successful but exec failed */
+	if (info->pid && info->retval) {
+		fput(umh_info->pipe_to_umh);
+		fput(umh_info->pipe_from_umh);
+	}
+
 	argv_free(info->argv);
 	umh_info->pid = info->pid;
 }
@@ -544,6 +550,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob);
  * Runs a user-space application.  The application is started
  * asynchronously if wait is not set, and runs as a child of system workqueues.
  * (ie. it runs with full root capabilities and optimized affinity).
+ *
+ * Note: successful return value does not guarantee the helper was called at
+ * all. You can't rely on sub_info->{init,cleanup} being called even for
+ * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers
+ * into a successful no-op.
  */
 int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 {