Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf after rc6

Cross-merge BPF and other fixes after downstream PR.

No conflicts.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

17 files changed, 73 insertions, 74 deletions

diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index e64ce21f9a80..2ee603a98813 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -134,6 +134,7 @@ config CRASH_DM_CRYPT
 	depends on KEXEC_FILE
 	depends on CRASH_DUMP
 	depends on DM_CRYPT
+	depends on KEYS
 	help
 	  With this option enabled, user space can intereact with
 	  /sys/kernel/config/crash_dm_crypt_keys to make the dm crypt keys
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 3d33181d5e67..6b4877e85a68 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -881,6 +881,13 @@ int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args,
 		if (fmt[i] == 'p') {
 			sizeof_cur_arg = sizeof(long);
 
+			if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
+			    ispunct(fmt[i + 1])) {
+				if (tmp_buf)
+					cur_arg = raw_args[num_spec];
+				goto nocopy_fmt;
+			}
+
 			if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') &&
 			    fmt[i + 2] == 's') {
 				fmt_ptype = fmt[i + 1];
@@ -888,11 +895,9 @@ int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args,
 				goto fmt_str;
 			}
 
-			if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
-			    ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' ||
+			if (fmt[i + 1] == 'K' ||
 			    fmt[i + 1] == 'x' || fmt[i + 1] == 's' ||
 			    fmt[i + 1] == 'S') {
-				/* just kernel pointers */
 				if (tmp_buf)
 					cur_arg = raw_args[num_spec];
 				i++;
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 941d0d2427e3..8e61dc555415 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -21,7 +21,7 @@ static int btf_sysfs_vmlinux_mmap(struct file *filp, struct kobject *kobj,
 {
 	unsigned long pages = PAGE_ALIGN(attr->size) >> PAGE_SHIFT;
 	size_t vm_size = vma->vm_end - vma->vm_start;
-	phys_addr_t addr = virt_to_phys(__start_BTF);
+	phys_addr_t addr = __pa_symbol(__start_BTF);
 	unsigned long pfn = addr >> PAGE_SHIFT;
 
 	if (attr->private != __start_BTF || !PAGE_ALIGNED(addr))
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 8df0dfaaca18..67af8a55185d 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -222,7 +222,10 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	if (size_cmdline != -1) {
 		selected_size = size_cmdline;
 		selected_base = base_cmdline;
-		selected_limit = min_not_zero(limit_cmdline, limit);
+
+		/* Hornor the user setup dma address limit */
+		selected_limit = limit_cmdline ?: limit;
+
 		if (base_cmdline + size_cmdline == limit_cmdline)
 			fixed = true;
 	} else {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1f746469fda5..22fdf0c187cd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -951,8 +951,6 @@ static void perf_cgroup_switch(struct task_struct *task)
 	if (READ_ONCE(cpuctx->cgrp) == NULL)
 		return;
 
-	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
-
 	cgrp = perf_cgroup_from_task(task, NULL);
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
 		return;
@@ -964,6 +962,8 @@ static void perf_cgroup_switch(struct task_struct *task)
 	if (READ_ONCE(cpuctx->cgrp) == NULL)
 		return;
 
+	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+
 	perf_ctx_disable(&cpuctx->ctx, true);
 
 	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -7204,18 +7204,18 @@ void perf_event_wakeup(struct perf_event *event)
 static void perf_sigtrap(struct perf_event *event)
 {
 	/*
-	 * We'd expect this to only occur if the irq_work is delayed and either
-	 * ctx->task or current has changed in the meantime. This can be the
-	 * case on architectures that do not implement arch_irq_work_raise().
+	 * Both perf_pending_task() and perf_pending_irq() can race with the
+	 * task exiting.
 	 */
-	if (WARN_ON_ONCE(event->ctx->task != current))
+	if (current->flags & PF_EXITING)
 		return;
 
 	/*
-	 * Both perf_pending_task() and perf_pending_irq() can race with the
-	 * task exiting.
+	 * We'd expect this to only occur if the irq_work is delayed and either
+	 * ctx->task or current has changed in the meantime. This can be the
+	 * case on architectures that do not implement arch_irq_work_raise().
 	 */
-	if (current->flags & PF_EXITING)
+	if (WARN_ON_ONCE(event->ctx->task != current))
 		return;
 
 	send_sig_perf((void __user *)event->pending_addr,
@@ -7251,15 +7251,15 @@ static void __perf_pending_disable(struct perf_event *event)
 	 *  CPU-A			CPU-B
 	 *
 	 *  perf_event_disable_inatomic()
-	 *    @pending_disable = CPU-A;
+	 *    @pending_disable = 1;
 	 *    irq_work_queue();
 	 *
 	 *  sched-out
-	 *    @pending_disable = -1;
+	 *    @pending_disable = 0;
 	 *
 	 *				sched-in
 	 *				perf_event_disable_inatomic()
-	 *				  @pending_disable = CPU-B;
+	 *				  @pending_disable = 1;
 	 *				  irq_work_queue(); // FAILS
 	 *
 	 *  irq_work_run()
@@ -11116,7 +11116,7 @@ static int perf_uprobe_event_init(struct perf_event *event)
 	if (event->attr.type != perf_uprobe.type)
 		return -ENOENT;
 
-	if (!perfmon_capable())
+	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
 	/*
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index d2aef87c7e9f..aa9a759e824f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -441,7 +441,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		 * store that will be enabled on successful return
 		 */
 		if (!handle->size) { /* A, matches D */
-			event->pending_disable = smp_processor_id();
+			perf_event_disable_inatomic(handle->event);
 			perf_output_wakeup(handle);
 			WRITE_ONCE(rb->aux_nest, 0);
 			goto err_put;
@@ -526,7 +526,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
-			handle->event->pending_disable = smp_processor_id();
+			perf_event_disable_inatomic(handle->event);
 		perf_output_wakeup(handle);
 	}
 
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 9c59fa480b0b..3a9a9f240dbc 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1136,6 +1136,7 @@ int kernel_kexec(void)
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
  Resume_console:
+		pm_restore_gfp_mask();
 		console_resume_all();
 		thaw_processes();
  Restore_console:
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 413ac6ea3702..c2c08007029d 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1573,8 +1573,14 @@ static int apply_relocations(struct module *mod, const struct load_info *info)
 		if (infosec >= info->hdr->e_shnum)
 			continue;
 
-		/* Don't bother with non-allocated sections */
-		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC))
+		/*
+		 * Don't bother with non-allocated sections.
+		 * An exception is the percpu section, which has separate allocations
+		 * for individual CPUs. We relocate the percpu section in the initial
+		 * ELF template and subsequently copy it to the per-CPU destinations.
+		 */
+		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC) &&
+		    (!infosec || infosec != info->index.pcpu))
 			continue;
 
 		if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH)
@@ -2696,9 +2702,8 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 
 static int move_module(struct module *mod, struct load_info *info)
 {
-	int i;
-	enum mod_mem_type t = 0;
-	int ret = -ENOMEM;
+	int i, ret;
+	enum mod_mem_type t = MOD_MEM_NUM_TYPES;
 	bool codetag_section_found = false;
 
 	for_each_mod_mem_type(type) {
@@ -2776,7 +2781,7 @@ static int move_module(struct module *mod, struct load_info *info)
 	return 0;
 out_err:
 	module_memory_restore_rox(mod);
-	for (t--; t >= 0; t--)
+	while (t--)
 		module_memory_free(mod, t);
 	if (codetag_section_found)
 		codetag_free_module_sections(mod);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 519fb09de5e0..9216e3b91d3b 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -423,7 +423,6 @@ int hibernation_snapshot(int platform_mode)
 	}
 
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 
 	error = dpm_suspend(PMSG_FREEZE);
 
@@ -559,7 +558,6 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
@@ -571,7 +569,6 @@ int hibernation_restore(int platform_mode)
 		BUG_ON(!error);
 	}
 	dpm_resume_end(PMSG_RECOVER);
-	pm_restore_gfp_mask();
 	console_resume_all();
 	pm_restore_console();
 	return error;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index cb1d71562002..7ccd709af93f 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -239,11 +239,6 @@ static inline void suspend_test_finish(const char *label) {}
 /* kernel/power/main.c */
 extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
 extern int pm_notifier_call_chain(unsigned long val);
-void pm_restrict_gfp_mask(void);
-void pm_restore_gfp_mask(void);
-#else
-static inline void pm_restrict_gfp_mask(void) {}
-static inline void pm_restore_gfp_mask(void) {}
 #endif
 
 #ifdef CONFIG_HIGHMEM
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 76b141b9aac0..b4ca17c2fecf 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -384,6 +384,7 @@ static int suspend_prepare(suspend_state_t state)
 		return 0;
 
 	dpm_save_failed_step(SUSPEND_FREEZE);
+	filesystems_thaw();
 	pm_notifier_call_chain(PM_POST_SUSPEND);
  Restore:
 	pm_restore_console();
@@ -592,8 +593,6 @@ static int enter_state(suspend_state_t state)
 		ksys_sync_helper();
 		trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 	}
-	if (filesystem_freeze_enabled)
-		filesystems_freeze();
 
 	pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
 	pm_suspend_clear_flags();
@@ -606,16 +605,13 @@ static int enter_state(suspend_state_t state)
 
 	trace_suspend_resume(TPS("suspend_enter"), state, false);
 	pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]);
-	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
-	pm_restore_gfp_mask();
 
  Finish:
 	events_check_enabled = false;
 	pm_pr_dbg("Finishing wakeup.\n");
 	suspend_finish();
  Unlock:
-	filesystems_thaw();
 	mutex_unlock(&system_transition_mutex);
 	return error;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8988d38d46a3..81c6df746df1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3362,10 +3362,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
-	__schedstat_inc(p->stats.numa_task_swapped);
-	count_vm_numa_event(NUMA_TASK_SWAP);
-	count_memcg_event_mm(p->mm, NUMA_TASK_SWAP);
-
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
 		struct rq_flags srf, drf;
@@ -3943,6 +3939,11 @@ static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 	if (!scx_allow_ttwu_queue(p))
 		return false;
 
+#ifdef CONFIG_SMP
+	if (p->sched_class == &stop_sched_class)
+		return false;
+#endif
+
 	/*
 	 * Do not complicate things with the async wake_list while the CPU is
 	 * in hotplug state.
@@ -7663,7 +7664,7 @@ const char *preempt_model_str(void)
 
 		if (IS_ENABLED(CONFIG_PREEMPT_DYNAMIC)) {
 			seq_buf_printf(&s, "(%s)%s",
-				       preempt_dynamic_mode > 0 ?
+				       preempt_dynamic_mode >= 0 ?
 				       preempt_modes[preempt_dynamic_mode] : "undef",
 				       brace ? "}" : "");
 			return seq_buf_str(&s);
@@ -7934,9 +7935,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
-	__schedstat_inc(p->stats.numa_task_migrated);
-	count_vm_numa_event(NUMA_TASK_MIGRATE);
-	count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE);
+	/* TODO: This is not properly updating schedstats */
+
 	trace_sched_move_numa(p, curr_cpu, target_cpu);
 	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ad45a8fea245..89019a140826 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1504,7 +1504,9 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 	if (dl_entity_is_special(dl_se))
 		return;
 
-	scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
+	scaled_delta_exec = delta_exec;
+	if (!dl_server(dl_se))
+		scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
 
 	dl_se->runtime -= scaled_delta_exec;
 
@@ -1611,7 +1613,7 @@ throttle:
  */
 void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 {
-	s64 delta_exec, scaled_delta_exec;
+	s64 delta_exec;
 
 	if (!rq->fair_server.dl_defer)
 		return;
@@ -1624,9 +1626,7 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 	if (delta_exec < 0)
 		return;
 
-	scaled_delta_exec = dl_scaled_delta_exec(rq, &rq->fair_server, delta_exec);
-
-	rq->fair_server.runtime -= scaled_delta_exec;
+	rq->fair_server.runtime -= delta_exec;
 
 	if (rq->fair_server.runtime < 0) {
 		rq->fair_server.dl_defer_running = 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9d71baf08075..557246880a7e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1210,10 +1210,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P_SCHEDSTAT(nr_failed_migrations_running);
 		P_SCHEDSTAT(nr_failed_migrations_hot);
 		P_SCHEDSTAT(nr_forced_migrations);
-#ifdef CONFIG_NUMA_BALANCING
-		P_SCHEDSTAT(numa_task_migrated);
-		P_SCHEDSTAT(numa_task_swapped);
-#endif
 		P_SCHEDSTAT(nr_wakeups);
 		P_SCHEDSTAT(nr_wakeups_sync);
 		P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 5d2d0562115b..3fe6b0c99f3d 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -82,18 +82,15 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done)
 }
 
 static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
-					struct cpu_stop_work *work,
-					struct wake_q_head *wakeq)
+				  struct cpu_stop_work *work)
 {
 	list_add_tail(&work->list, &stopper->works);
-	wake_q_add(wakeq, stopper->thread);
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
 static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-	DEFINE_WAKE_Q(wakeq);
 	unsigned long flags;
 	bool enabled;
 
@@ -101,12 +98,13 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	raw_spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
-		__cpu_stop_queue_work(stopper, work, &wakeq);
+		__cpu_stop_queue_work(stopper, work);
 	else if (work->done)
 		cpu_stop_signal_done(work->done);
 	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 
-	wake_up_q(&wakeq);
+	if (enabled)
+		wake_up_process(stopper->thread);
 	preempt_enable();
 
 	return enabled;
@@ -264,7 +262,6 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 {
 	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
-	DEFINE_WAKE_Q(wakeq);
 	int err;
 
 retry:
@@ -300,8 +297,8 @@ retry:
 	}
 
 	err = 0;
-	__cpu_stop_queue_work(stopper1, work1, &wakeq);
-	__cpu_stop_queue_work(stopper2, work2, &wakeq);
+	__cpu_stop_queue_work(stopper1, work1);
+	__cpu_stop_queue_work(stopper2, work2);
 
 unlock:
 	raw_spin_unlock(&stopper2->lock);
@@ -316,7 +313,10 @@ unlock:
 		goto retry;
 	}
 
-	wake_up_q(&wakeq);
+	if (!err) {
+		wake_up_process(stopper1->thread);
+		wake_up_process(stopper2->thread);
+	}
 	preempt_enable();
 
 	return err;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 08141f105c95..3885aadc434d 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1436,13 +1436,6 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
 
 	INIT_LIST_HEAD(&head->list);
 
-	item = kmalloc(sizeof(*item), GFP_KERNEL);
-	if (!item)
-		goto free_now;
-
-	item->filter = filter;
-	list_add_tail(&item->list, &head->list);
-
 	list_for_each_entry(file, &tr->events, list) {
 		if (file->system != dir)
 			continue;
@@ -1454,6 +1447,13 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
 		event_clear_filter(file);
 	}
 
+	item = kmalloc(sizeof(*item), GFP_KERNEL);
+	if (!item)
+		goto free_now;
+
+	item->filter = filter;
+	list_add_tail(&item->list, &head->list);
+
 	delay_free_filter(head);
 	return;
  free_now:
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 424751cdf31f..40830a3ecd96 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -657,7 +657,7 @@ static int parse_btf_arg(char *varname,
 		ret = query_btf_context(ctx);
 		if (ret < 0 || ctx->nr_params == 0) {
 			trace_probe_log_err(ctx->offset, NO_BTF_ENTRY);
-			return PTR_ERR(params);
+			return -ENOENT;
 		}
 	}
 	params = ctx->params;