Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

14 files changed, 87 insertions, 56 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 803b91135ca0..71473c19093d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5587,16 +5587,17 @@ static int update_stack_depth(struct bpf_verifier_env *env,
  * Since recursion is prevented by check_cfg() this algorithm
  * only needs a local stack of MAX_CALL_FRAMES to remember callsites
  */
-static int check_max_stack_depth(struct bpf_verifier_env *env)
+static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx)
 {
-	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
+	int depth = 0, frame = 0, i, subprog_end;
 	bool tail_call_reachable = false;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
 	int j;
 
+	i = subprog[idx].start;
 process_func:
 	/* protect against potential stack overflow that might happen when
 	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
@@ -5635,7 +5636,7 @@ process_func:
 continue_func:
 	subprog_end = subprog[idx + 1].start;
 	for (; i < subprog_end; i++) {
-		int next_insn;
+		int next_insn, sidx;
 
 		if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
 			continue;
@@ -5645,14 +5646,14 @@ continue_func:
 
 		/* find the callee */
 		next_insn = i + insn[i].imm + 1;
-		idx = find_subprog(env, next_insn);
-		if (idx < 0) {
+		sidx = find_subprog(env, next_insn);
+		if (sidx < 0) {
 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
 				  next_insn);
 			return -EFAULT;
 		}
-		if (subprog[idx].is_async_cb) {
-			if (subprog[idx].has_tail_call) {
+		if (subprog[sidx].is_async_cb) {
+			if (subprog[sidx].has_tail_call) {
 				verbose(env, "verifier bug. subprog has tail_call and async cb\n");
 				return -EFAULT;
 			}
@@ -5661,6 +5662,7 @@ continue_func:
 				continue;
 		}
 		i = next_insn;
+		idx = sidx;
 
 		if (subprog[idx].has_tail_call)
 			tail_call_reachable = true;
@@ -5696,6 +5698,22 @@ continue_func:
 	goto continue_func;
 }
 
+static int check_max_stack_depth(struct bpf_verifier_env *env)
+{
+	struct bpf_subprog_info *si = env->subprog_info;
+	int ret;
+
+	for (int i = 0; i < env->subprog_cnt; i++) {
+		if (!i || si[i].is_async_cb) {
+			ret = check_max_stack_depth_subprog(env, i);
+			if (ret < 0)
+				return ret;
+		}
+		continue;
+	}
+	return 0;
+}
+
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 static int get_callee_stack_depth(struct bpf_verifier_env *env,
 				  const struct bpf_insn *insn, int idx)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index bfe3cd8ccf36..f55a40db065f 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3730,7 +3730,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_psi(cgrp);
-	new = psi_trigger_create(psi, buf, res, of->file);
+	new = psi_trigger_create(psi, buf, res, of->file, of);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 7982cc9d497c..016d997131d4 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -174,11 +174,10 @@ static bool cleanup_symbol_name(char *s)
 	 * LLVM appends various suffixes for local functions and variables that
 	 * must be promoted to global scope as part of LTO.  This can break
 	 * hooking of static functions with kprobes. '.' is not a valid
-	 * character in an identifier in C. Suffixes observed:
+	 * character in an identifier in C. Suffixes only in LLVM LTO observed:
 	 * - foo.llvm.[0-9a-f]+
-	 * - foo.[0-9a-f]+
 	 */
-	res = strchr(s, '.');
+	res = strstr(s, ".llvm.");
 	if (res) {
 		*res = '\0';
 		return true;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f62e89d0d906..e1b4bfa938dd 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -1179,6 +1179,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
 		unsigned maj, min, offset;
 		char *p, dummy;
 
+		error = 0;
 		if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 ||
 		    sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset,
 				&dummy) == 3) {
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index af51ed6d45ef..782d3b41c1f3 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -426,6 +426,11 @@ late_initcall(cpu_latency_qos_init);
 
 /* Definitions related to the frequency QoS below. */
 
+static inline bool freq_qos_value_invalid(s32 value)
+{
+	return value < 0 && value != PM_QOS_DEFAULT_VALUE;
+}
+
 /**
  * freq_constraints_init - Initialize frequency QoS constraints.
  * @qos: Frequency QoS constraints to initialize.
@@ -531,7 +536,7 @@ int freq_qos_add_request(struct freq_constraints *qos,
 {
 	int ret;
 
-	if (IS_ERR_OR_NULL(qos) || !req || value < 0)
+	if (IS_ERR_OR_NULL(qos) || !req || freq_qos_value_invalid(value))
 		return -EINVAL;
 
 	if (WARN(freq_qos_request_active(req),
@@ -563,7 +568,7 @@ EXPORT_SYMBOL_GPL(freq_qos_add_request);
  */
 int freq_qos_update_request(struct freq_qos_request *req, s32 new_value)
 {
-	if (!req || new_value < 0)
+	if (!req || freq_qos_value_invalid(new_value))
 		return -EINVAL;
 
 	if (WARN(!freq_qos_request_active(req),
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a80a73909dc2..b3e25be58e2b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7174,7 +7174,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
-	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+	    cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) &&
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
 		return recent_used_cpu;
 	}
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 81fca77397f6..9bb3f2b3ccfc 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -493,8 +493,12 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
 			continue;
 
 		/* Generate an event */
-		if (cmpxchg(&t->event, 0, 1) == 0)
-			wake_up_interruptible(&t->event_wait);
+		if (cmpxchg(&t->event, 0, 1) == 0) {
+			if (t->of)
+				kernfs_notify(t->of->kn);
+			else
+				wake_up_interruptible(&t->event_wait);
+		}
 		t->last_event_time = now;
 		/* Reset threshold breach flag once event got generated */
 		t->pending_event = false;
@@ -1271,8 +1275,9 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 	return 0;
 }
 
-struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, enum psi_res res, struct file *file)
+struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
+				       enum psi_res res, struct file *file,
+				       struct kernfs_open_file *of)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
@@ -1331,7 +1336,9 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 
 	t->event = 0;
 	t->last_event_time = 0;
-	init_waitqueue_head(&t->event_wait);
+	t->of = of;
+	if (!of)
+		init_waitqueue_head(&t->event_wait);
 	t->pending_event = false;
 	t->aggregator = privileged ? PSI_POLL : PSI_AVGS;
 
@@ -1388,7 +1395,10 @@ void psi_trigger_destroy(struct psi_trigger *t)
 	 * being accessed later. Can happen if cgroup is deleted from under a
 	 * polling process.
 	 */
-	wake_up_pollfree(&t->event_wait);
+	if (t->of)
+		kernfs_notify(t->of->kn);
+	else
+		wake_up_interruptible(&t->event_wait);
 
 	if (t->aggregator == PSI_AVGS) {
 		mutex_lock(&group->avgs_lock);
@@ -1465,7 +1475,10 @@ __poll_t psi_trigger_poll(void **trigger_ptr,
 	if (!t)
 		return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
 
-	poll_wait(file, &t->event_wait, wait);
+	if (t->of)
+		kernfs_generic_poll(t->of, wait);
+	else
+		poll_wait(file, &t->event_wait, wait);
 
 	if (cmpxchg(&t->event, 1, 0) == 1)
 		ret |= EPOLLPRI;
@@ -1535,7 +1548,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, res, file);
+	new = psi_trigger_create(&psi_system, buf, res, file, NULL);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);
diff --git a/kernel/sys.c b/kernel/sys.c
index 05f838929e72..2410e3999ebe 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2535,11 +2535,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			else
 				return -EINVAL;
 			break;
-	case PR_GET_AUXV:
-		if (arg4 || arg5)
-			return -EINVAL;
-		error = prctl_get_auxv((void __user *)arg2, arg3);
-		break;
 		default:
 			return -EINVAL;
 		}
@@ -2694,6 +2689,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SET_VMA:
 		error = prctl_set_vma(arg2, arg3, arg4, arg5);
 		break;
+	case PR_GET_AUXV:
+		if (arg4 || arg5)
+			return -EINVAL;
+		error = prctl_get_auxv((void __user *)arg2, arg3);
+		break;
 #ifdef CONFIG_KSM
 	case PR_SET_MEMORY_MERGE:
 		if (arg3 || arg4 || arg5)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index b70de44e6d3d..3b21f4063258 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -100,6 +100,12 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
 		return;
 	}
 
+	/*
+	 * This user handler is shared with other kprobes and is not expected to be
+	 * called recursively. So if any other kprobe handler is running, this will
+	 * exit as kprobe does. See the section 'Share the callbacks with kprobes'
+	 * in Documentation/trace/fprobe.rst for more information.
+	 */
 	if (unlikely(kprobe_running())) {
 		fp->nmissed++;
 		goto recursion_unlock;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ed7906b13f09..e1edc2197fc8 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -113,6 +113,8 @@ enum trace_type {
 #define MEM_FAIL(condition, fmt, ...)					\
 	DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__)
 
+#define FAULT_STRING "(fault)"
+
 #define HIST_STACKTRACE_DEPTH	16
 #define HIST_STACKTRACE_SIZE	(HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
 #define HIST_STACKTRACE_SKIP	5
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 7ba371da0926..b2b726bea1f9 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -67,7 +67,7 @@ int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, void *data, void *ent)
 	int len = *(u32 *)data >> 16;
 
 	if (!len)
-		trace_seq_puts(s, "(fault)");
+		trace_seq_puts(s, FAULT_STRING);
 	else
 		trace_seq_printf(s, "\"%s\"",
 				 (const char *)get_loc_data(data, ent));
diff --git a/kernel/trace/trace_probe_kernel.h b/kernel/trace/trace_probe_kernel.h
index c4e1d4c03a85..bb723eefd7b7 100644
--- a/kernel/trace/trace_probe_kernel.h
+++ b/kernel/trace/trace_probe_kernel.h
@@ -2,8 +2,6 @@
 #ifndef __TRACE_PROBE_KERNEL_H_
 #define __TRACE_PROBE_KERNEL_H_
 
-#define FAULT_STRING "(fault)"
-
 /*
  * This depends on trace_probe.h, but can not include it due to
  * the way trace_probe_tmpl.h is used by trace_kprobe.c and trace_eprobe.c.
@@ -15,16 +13,8 @@ static nokprobe_inline int
 fetch_store_strlen_user(unsigned long addr)
 {
 	const void __user *uaddr =  (__force const void __user *)addr;
-	int ret;
 
-	ret = strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
-	/*
-	 * strnlen_user_nofault returns zero on fault, insert the
-	 * FAULT_STRING when that occurs.
-	 */
-	if (ret <= 0)
-		return strlen(FAULT_STRING) + 1;
-	return ret;
+	return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
 }
 
 /* Return the length of string -- including null terminal byte */
@@ -44,18 +34,14 @@ fetch_store_strlen(unsigned long addr)
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
-	/* For faults, return enough to hold the FAULT_STRING */
-	return (ret < 0) ? strlen(FAULT_STRING) + 1 : len;
+	return (ret < 0) ? ret : len;
 }
 
-static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base, int len)
+static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base)
 {
-	if (ret >= 0) {
-		*(u32 *)dest = make_data_loc(ret, __dest - base);
-	} else {
-		strscpy(__dest, FAULT_STRING, len);
-		ret = strlen(__dest) + 1;
-	}
+	if (ret < 0)
+		ret = 0;
+	*(u32 *)dest = make_data_loc(ret, __dest - base);
 }
 
 /*
@@ -76,7 +62,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
 	__dest = get_loc_data(dest, base);
 
 	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
-	set_data_loc(ret, dest, __dest, base, maxlen);
+	set_data_loc(ret, dest, __dest, base);
 
 	return ret;
 }
@@ -107,7 +93,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 	 * probing.
 	 */
 	ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
-	set_data_loc(ret, dest, __dest, base, maxlen);
+	set_data_loc(ret, dest, __dest, base);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 00707630788d..3935b347f874 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -156,11 +156,11 @@ stage3:
 			code++;
 			goto array;
 		case FETCH_OP_ST_USTRING:
-			ret += fetch_store_strlen_user(val + code->offset);
+			ret = fetch_store_strlen_user(val + code->offset);
 			code++;
 			goto array;
 		case FETCH_OP_ST_SYMSTR:
-			ret += fetch_store_symstrlen(val + code->offset);
+			ret = fetch_store_symstrlen(val + code->offset);
 			code++;
 			goto array;
 		default:
@@ -204,6 +204,8 @@ stage3:
 array:
 	/* the last stage: Loop on array */
 	if (code->op == FETCH_OP_LP_ARRAY) {
+		if (ret < 0)
+			ret = 0;
 		total += ret;
 		if (++i < code->param) {
 			code = s3;
@@ -265,9 +267,7 @@ store_trace_args(void *data, struct trace_probe *tp, void *rec,
 		if (unlikely(arg->dynamic))
 			*dl = make_data_loc(maxlen, dyndata - base);
 		ret = process_fetch_insn(arg->code, rec, dl, base);
-		if (unlikely(ret < 0 && arg->dynamic)) {
-			*dl = make_data_loc(0, dyndata - base);
-		} else {
+		if (arg->dynamic && likely(ret > 0)) {
 			dyndata += ret;
 			maxlen -= ret;
 		}
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index eaa800530e92..555c223c3232 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -170,7 +170,8 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 			 */
 			ret++;
 		*(u32 *)dest = make_data_loc(ret, (void *)dst - base);
-	}
+	} else
+		*(u32 *)dest = make_data_loc(0, (void *)dst - base);
 
 	return ret;
 }