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

14 files changed, 90 insertions, 76 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index cabaf7db8efc..be35bfb7fb13 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -114,6 +114,8 @@ 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 785d25392ead..1cffd4e84725 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6918,7 +6918,7 @@ 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:
@@ -6991,7 +6991,7 @@ 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:
@@ -8631,7 +8631,11 @@ 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 */
@@ -11117,30 +11121,28 @@ 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 1b1b8ff875cb..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 {
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 6dd82be60df8..f9d491b17b78 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -209,15 +209,9 @@ 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)
@@ -225,10 +219,8 @@ static inline bool report_single_step(unsigned long work)
 	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/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/kprobes.c b/kernel/kprobes.c
index f7fb5d135930..d5a3eb74a657 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1954,28 +1954,48 @@ bool __weak arch_kprobe_on_func_entry(unsigned long offset)
 	return !offset;
 }
 
-bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+/**
+ * kprobe_on_func_entry() -- check whether given address is function entry
+ * @addr: Target address
+ * @sym:  Target symbol name
+ * @offset: The offset from the symbol or the address
+ *
+ * This checks whether the given @addr+@offset or @sym+@offset is on the
+ * function entry address or not.
+ * This returns 0 if it is the function entry, or -EINVAL if it is not.
+ * And also it returns -ENOENT if it fails the symbol or address lookup.
+ * Caller must pass @addr or @sym (either one must be NULL), or this
+ * returns -EINVAL.
+ */
+int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
 {
 	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
 
 	if (IS_ERR(kp_addr))
-		return false;
+		return PTR_ERR(kp_addr);
 
-	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
-						!arch_kprobe_on_func_entry(offset))
-		return false;
+	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset))
+		return -ENOENT;
 
-	return true;
+	if (!arch_kprobe_on_func_entry(offset))
+		return -EINVAL;
+
+	return 0;
 }
 
 int register_kretprobe(struct kretprobe *rp)
 {
-	int ret = 0;
+	int ret;
 	struct kretprobe_instance *inst;
 	int i;
 	void *addr;
 
-	if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
+	ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset);
+	if (ret)
+		return ret;
+
+	/* If only rp->kp.addr is specified, check reregistering kprobes */
+	if (rp->kp.addr && check_kprobe_rereg(&rp->kp))
 		return -EINVAL;
 
 	if (kretprobe_blacklist_size) {
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)) {
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 73edb9e4f354..29a6ebeebc9e 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -394,7 +394,6 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 		}
 
 		if (t->ret_stack == NULL) {
-			atomic_set(&t->tracing_graph_pause, 0);
 			atomic_set(&t->trace_overrun, 0);
 			t->curr_ret_stack = -1;
 			t->curr_ret_depth = -1;
@@ -489,7 +488,6 @@ static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
 static void
 graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
 {
-	atomic_set(&t->tracing_graph_pause, 0);
 	atomic_set(&t->trace_overrun, 0);
 	t->ftrace_timestamp = 0;
 	/* make curr_ret_stack visible before we add the ret_stack */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e9d28eeccb7e..d387b774ceeb 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1212,7 +1212,8 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 	mutex_lock(&event_mutex);
 	list_for_each_entry(file, &tr->events, list) {
 		call = file->event_call;
-		if (!trace_event_name(call) || !call->class || !call->class->reg)
+		if ((call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) ||
+		    !trace_event_name(call) || !call->class || !call->class->reg)
 			continue;
 
 		if (system && strcmp(call->class->system, system->name) != 0)
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index d06aab4dcbb8..6756379b661f 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -562,6 +562,8 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
 	/* non overwrite screws up the latency tracers */
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
+	/* without pause, we will produce garbage if another latency occurs */
+	set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, 1);
 
 	tr->max_latency = 0;
 	irqsoff_trace = tr;
@@ -583,11 +585,13 @@ static void __irqsoff_tracer_reset(struct trace_array *tr)
 {
 	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
 	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+	int pause_flag = save_flags & TRACE_ITER_PAUSE_ON_TRACE;
 
 	stop_irqsoff_tracer(tr, is_graph(tr));
 
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
+	set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, pause_flag);
 	ftrace_reset_array_ops(tr);
 
 	irqsoff_busy = false;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index e6fba1798771..56c7fbff7bd7 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -221,9 +221,9 @@ bool trace_kprobe_on_func_entry(struct trace_event_call *call)
 {
 	struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);
 
-	return tk ? kprobe_on_func_entry(tk->rp.kp.addr,
+	return tk ? (kprobe_on_func_entry(tk->rp.kp.addr,
 			tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name,
-			tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false;
+			tk->rp.kp.addr ? 0 : tk->rp.kp.offset) == 0) : false;
 }
 
 bool trace_kprobe_error_injectable(struct trace_event_call *call)
@@ -828,9 +828,11 @@ static int trace_kprobe_create(int argc, const char *argv[])
 		}
 		if (is_return)
 			flags |= TPARG_FL_RETURN;
-		if (kprobe_on_func_entry(NULL, symbol, offset))
+		ret = kprobe_on_func_entry(NULL, symbol, offset);
+		if (ret == 0)
 			flags |= TPARG_FL_FENTRY;
-		if (offset && is_return && !(flags & TPARG_FL_FENTRY)) {
+		/* Defer the ENOENT case until register kprobe */
+		if (ret == -EINVAL && is_return) {
 			trace_probe_log_err(0, BAD_RETPROBE);
 			goto parse_error;
 		}