Merge branch 'perf/urgent' into perf/core

Conflicts:
	kernel/events/hw_breakpoint.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

16 files changed, 144 insertions, 91 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e24aa3241387..43f95d190eea 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1845,7 +1845,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	union bpf_attr attr = {};
 	int err;
 
-	if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
+	if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	err = check_uarg_tail_zero(uattr, sizeof(attr), size);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8cda3bc3ae22..4bfb2908ec15 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3183,6 +3183,16 @@ static int cgroup_enable_threaded(struct cgroup *cgrp)
 	if (cgroup_is_threaded(cgrp))
 		return 0;
 
+	/*
+	 * If @cgroup is populated or has domain controllers enabled, it
+	 * can't be switched.  While the below cgroup_can_be_thread_root()
+	 * test can catch the same conditions, that's only when @parent is
+	 * not mixable, so let's check it explicitly.
+	 */
+	if (cgroup_is_populated(cgrp) ||
+	    cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask)
+		return -EOPNOTSUPP;
+
 	/* we're joining the parent's domain, ensure its validity */
 	if (!cgroup_is_valid_domain(dom_cgrp) ||
 	    !cgroup_can_be_thread_root(dom_cgrp))
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6253d5519cd8..6e28d2866be5 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -492,13 +492,9 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
  * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
  * @bp: the breakpoint structure to modify
  * @attr: new breakpoint attributes
- * @triggered: callback to trigger when we hit the breakpoint
- * @tsk: pointer to 'task_struct' of the process to which the address belongs
  */
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
-	int err;
-
 	/*
 	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
 	 * will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -510,17 +506,14 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	else
 		perf_event_disable(bp);
 
-	err = modify_user_hw_breakpoint_check(bp, attr, false);
-
-	if (err) {
-		if (!bp->attr.disabled)
-			perf_event_enable(bp);
+	if (!attr->disabled) {
+		int err = modify_user_hw_breakpoint_check(bp, attr, false);
 
-		return err;
-	}
-
-	if (!attr->disabled)
+		if (err)
+			return err;
 		perf_event_enable(bp);
+		bp->attr.disabled = 0;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 21b0122cb39c..1d5632d8bbcc 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -14,6 +14,15 @@
 
 static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs);
 
+static void fei_post_handler(struct kprobe *kp, struct pt_regs *regs,
+			     unsigned long flags)
+{
+	/*
+	 * A dummy post handler is required to prohibit optimizing, because
+	 * jump optimization does not support execution path overriding.
+	 */
+}
+
 struct fei_attr {
 	struct list_head list;
 	struct kprobe kp;
@@ -56,6 +65,7 @@ static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr)
 			return NULL;
 		}
 		attr->kp.pre_handler = fei_kprobe_handler;
+		attr->kp.post_handler = fei_post_handler;
 		attr->retval = adjust_error_retval(addr, 0);
 		INIT_LIST_HEAD(&attr->list);
 	}
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index e7214093dcd1..01ebdf1f9f40 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -16,6 +16,7 @@
 #include <linux/jump_label_ratelimit.h>
 #include <linux/bug.h>
 #include <linux/cpu.h>
+#include <asm/sections.h>
 
 #ifdef HAVE_JUMP_LABEL
 
@@ -421,15 +422,15 @@ void __init jump_label_init(void)
 	cpus_read_unlock();
 }
 
-/* Disable any jump label entries in __init code */
-void __init jump_label_invalidate_init(void)
+/* Disable any jump label entries in __init/__exit code */
+void __init jump_label_invalidate_initmem(void)
 {
 	struct jump_entry *iter_start = __start___jump_table;
 	struct jump_entry *iter_stop = __stop___jump_table;
 	struct jump_entry *iter;
 
 	for (iter = iter_start; iter < iter_stop; iter++) {
-		if (init_kernel_text(iter->code))
+		if (init_section_contains((void *)(unsigned long)iter->code, 1))
 			iter->code = 0;
 	}
 }
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 858a07590e39..2048359f33d2 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -1082,15 +1082,16 @@ static noinline int __sched
 __mutex_lock_interruptible_slowpath(struct mutex *lock);
 
 /**
- * mutex_lock_interruptible - acquire the mutex, interruptible
- * @lock: the mutex to be acquired
+ * mutex_lock_interruptible() - Acquire the mutex, interruptible by signals.
+ * @lock: The mutex to be acquired.
  *
- * Lock the mutex like mutex_lock(), and return 0 if the mutex has
- * been acquired or sleep until the mutex becomes available. If a
- * signal arrives while waiting for the lock then this function
- * returns -EINTR.
+ * Lock the mutex like mutex_lock().  If a signal is delivered while the
+ * process is sleeping, this function will return without acquiring the
+ * mutex.
  *
- * This function is similar to (but not equivalent to) down_interruptible().
+ * Context: Process context.
+ * Return: 0 if the lock was successfully acquired or %-EINTR if a
+ * signal arrived.
  */
 int __sched mutex_lock_interruptible(struct mutex *lock)
 {
@@ -1104,6 +1105,18 @@ int __sched mutex_lock_interruptible(struct mutex *lock)
 
 EXPORT_SYMBOL(mutex_lock_interruptible);
 
+/**
+ * mutex_lock_killable() - Acquire the mutex, interruptible by fatal signals.
+ * @lock: The mutex to be acquired.
+ *
+ * Lock the mutex like mutex_lock().  If a signal which will be fatal to
+ * the current process is delivered while the process is sleeping, this
+ * function will return without acquiring the mutex.
+ *
+ * Context: Process context.
+ * Return: 0 if the lock was successfully acquired or %-EINTR if a
+ * fatal signal arrived.
+ */
 int __sched mutex_lock_killable(struct mutex *lock)
 {
 	might_sleep();
@@ -1115,6 +1128,16 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
+/**
+ * mutex_lock_io() - Acquire the mutex and mark the process as waiting for I/O
+ * @lock: The mutex to be acquired.
+ *
+ * Lock the mutex like mutex_lock().  While the task is waiting for this
+ * mutex, it will be accounted as being in the IO wait state by the
+ * scheduler.
+ *
+ * Context: Process context.
+ */
 void __sched mutex_lock_io(struct mutex *lock)
 {
 	int token;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 4dd4274cabe2..895e6b76b25e 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -427,7 +427,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
  err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res, pgoff);
-	devres_free(pgmap);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL(devm_memremap_pages);
diff --git a/kernel/module.c b/kernel/module.c
index ad2d420024f6..e42764acedb4 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4228,7 +4228,7 @@ static int modules_open(struct inode *inode, struct file *file)
 		m->private = kallsyms_show_value() ? NULL : (void *)8ul;
 	}
 
-	return 0;
+	return err;
 }
 
 static const struct file_operations proc_modules_operations = {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e7c535eee0a6..c94895bc5a2c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6683,13 +6683,18 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 		parent_quota = parent_b->hierarchical_quota;
 
 		/*
-		 * Ensure max(child_quota) <= parent_quota, inherit when no
+		 * Ensure max(child_quota) <= parent_quota.  On cgroup2,
+		 * always take the min.  On cgroup1, only inherit when no
 		 * limit is set:
 		 */
-		if (quota == RUNTIME_INF)
-			quota = parent_quota;
-		else if (parent_quota != RUNTIME_INF && quota > parent_quota)
-			return -EINVAL;
+		if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
+			quota = min(quota, parent_quota);
+		} else {
+			if (quota == RUNTIME_INF)
+				quota = parent_quota;
+			else if (parent_quota != RUNTIME_INF && quota > parent_quota)
+				return -EINVAL;
+		}
 	}
 	cfs_b->hierarchical_quota = quota;
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 1ca0130ed4f9..72c401b3b15c 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -32,7 +32,7 @@ static DEFINE_SPINLOCK(sched_debug_lock);
 	if (m)					\
 		seq_printf(m, x);		\
 	else					\
-		printk(x);			\
+		pr_cont(x);			\
  } while (0)
 
 /*
@@ -501,12 +501,12 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 {
 	struct task_struct *g, *p;
 
-	SEQ_printf(m,
-	"\nrunnable tasks:\n"
-	" S           task   PID         tree-key  switches  prio"
-	"     wait-time             sum-exec        sum-sleep\n"
-	"-------------------------------------------------------"
-	"----------------------------------------------------\n");
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, "runnable tasks:\n");
+	SEQ_printf(m, " S           task   PID         tree-key  switches  prio"
+		   "     wait-time             sum-exec        sum-sleep\n");
+	SEQ_printf(m, "-------------------------------------------------------"
+		   "----------------------------------------------------\n");
 
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
@@ -527,9 +527,11 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	unsigned long flags;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, "cfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));
 #else
-	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, "cfs_rq[%d]:\n", cpu);
 #endif
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
 			SPLIT_NS(cfs_rq->exec_clock));
@@ -595,9 +597,11 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
-	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg));
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, "rt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg));
 #else
-	SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, "rt_rq[%d]:\n", cpu);
 #endif
 
 #define P(x) \
@@ -624,7 +628,8 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 {
 	struct dl_bw *dl_bw;
 
-	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, "dl_rq[%d]:\n", cpu);
 
 #define PU(x) \
 	SEQ_printf(m, "  .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x))
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 75043046914e..10b7186d0638 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -50,6 +50,7 @@
 #include <linux/export.h>
 #include <linux/hashtable.h>
 #include <linux/compat.h>
+#include <linux/nospec.h>
 
 #include "timekeeping.h"
 #include "posix-timers.h"
@@ -1346,11 +1347,15 @@ static const struct k_clock * const posix_clocks[] = {
 
 static const struct k_clock *clockid_to_kclock(const clockid_t id)
 {
-	if (id < 0)
+	clockid_t idx = id;
+
+	if (id < 0) {
 		return (id & CLOCKFD_MASK) == CLOCKFD ?
 			&clock_posix_dynamic : &clock_posix_cpu;
+	}
 
-	if (id >= ARRAY_SIZE(posix_clocks) || !posix_clocks[id])
+	if (id >= ARRAY_SIZE(posix_clocks))
 		return NULL;
-	return posix_clocks[id];
+
+	return posix_clocks[array_index_nospec(idx, ARRAY_SIZE(posix_clocks))];
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c0a9e310d715..01e6b3a38871 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -661,7 +661,41 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
+static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto_tp;
+	case BPF_FUNC_get_stackid:
+		return &bpf_get_stackid_proto_tp;
+	default:
+		return tracing_func_proto(func_id);
+	}
+}
+
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+				    struct bpf_insn_access_aux *info)
+{
+	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
+		return false;
+	if (type != BPF_READ)
+		return false;
+	if (off % size != 0)
+		return false;
+
+	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64));
+	return true;
+}
+
+const struct bpf_verifier_ops tracepoint_verifier_ops = {
+	.get_func_proto  = tp_prog_func_proto,
+	.is_valid_access = tp_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops tracepoint_prog_ops = {
+};
+
+BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx,
 	   struct bpf_perf_event_value *, buf, u32, size)
 {
 	int err = -EINVAL;
@@ -678,8 +712,8 @@ clear:
 	return err;
 }
 
-static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
-         .func           = bpf_perf_prog_read_value_tp,
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
+         .func           = bpf_perf_prog_read_value,
          .gpl_only       = true,
          .ret_type       = RET_INTEGER,
          .arg1_type      = ARG_PTR_TO_CTX,
@@ -687,7 +721,7 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
          .arg3_type      = ARG_CONST_SIZE,
 };
 
-static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
@@ -695,34 +729,12 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_tp;
 	case BPF_FUNC_perf_prog_read_value:
-		return &bpf_perf_prog_read_value_proto_tp;
+		return &bpf_perf_prog_read_value_proto;
 	default:
 		return tracing_func_proto(func_id);
 	}
 }
 
-static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
-				    struct bpf_insn_access_aux *info)
-{
-	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
-		return false;
-	if (type != BPF_READ)
-		return false;
-	if (off % size != 0)
-		return false;
-
-	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64));
-	return true;
-}
-
-const struct bpf_verifier_ops tracepoint_verifier_ops = {
-	.get_func_proto  = tp_prog_func_proto,
-	.is_valid_access = tp_prog_is_valid_access,
-};
-
-const struct bpf_prog_ops tracepoint_prog_ops = {
-};
-
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -779,7 +791,7 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 }
 
 const struct bpf_verifier_ops perf_event_verifier_ops = {
-	.get_func_proto		= tp_prog_func_proto,
+	.get_func_proto		= pe_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5ce9b8cf7be3..1cd3fb4d70f8 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -667,7 +667,7 @@ static int create_trace_kprobe(int argc, char **argv)
 	char *symbol = NULL, *event = NULL, *group = NULL;
 	int maxactive = 0;
 	char *arg;
-	unsigned long offset = 0;
+	long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
 
@@ -755,7 +755,7 @@ static int create_trace_kprobe(int argc, char **argv)
 		symbol = argv[1];
 		/* TODO: support .init module functions */
 		ret = traceprobe_split_symbol_offset(symbol, &offset);
-		if (ret) {
+		if (ret || offset < 0 || offset > UINT_MAX) {
 			pr_info("Failed to parse either an address or a symbol.\n");
 			return ret;
 		}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index d59357308677..daf54bda4dc8 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -320,7 +320,7 @@ static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
 }
 
 /* Split symbol and offset. */
-int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
+int traceprobe_split_symbol_offset(char *symbol, long *offset)
 {
 	char *tmp;
 	int ret;
@@ -328,13 +328,11 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
 	if (!offset)
 		return -EINVAL;
 
-	tmp = strchr(symbol, '+');
+	tmp = strpbrk(symbol, "+-");
 	if (tmp) {
-		/* skip sign because kstrtoul doesn't accept '+' */
-		ret = kstrtoul(tmp + 1, 0, offset);
+		ret = kstrtol(tmp, 0, offset);
 		if (ret)
 			return ret;
-
 		*tmp = '\0';
 	} else
 		*offset = 0;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0745f895f780..75daff22ccea 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -365,7 +365,7 @@ extern int traceprobe_conflict_field_name(const char *name,
 extern void traceprobe_update_arg(struct probe_arg *arg);
 extern void traceprobe_free_probe_arg(struct probe_arg *arg);
 
-extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset);
+extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
 
 /* Sum up total data length for dynamic arraies (strings) */
 static nokprobe_inline int
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bb9a519cbf50..6ec6ba65127b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3018,14 +3018,6 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork)
 	return ret;
 }
 
-/*
- * See cancel_delayed_work()
- */
-bool cancel_work(struct work_struct *work)
-{
-	return __cancel_work(work, false);
-}
-
 /**
  * cancel_delayed_work - cancel a delayed work
  * @dwork: delayed_work to cancel
@@ -5337,7 +5329,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 
 	ret = device_register(&wq_dev->dev);
 	if (ret) {
-		kfree(wq_dev);
+		put_device(&wq_dev->dev);
 		wq->wq_dev = NULL;
 		return ret;
 	}