summary refs log tree commit diff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/arraymap.c3
-rw-r--r--kernel/bpf/sockmap.c99
-rw-r--r--kernel/bpf/syscall.c4
-rw-r--r--kernel/events/uprobes.c7
-rw-r--r--kernel/module.c3
-rw-r--r--kernel/sysctl_binary.c20
-rw-r--r--kernel/time/hrtimer.c16
-rw-r--r--kernel/time/posix-stubs.c2
-rw-r--r--kernel/time/posix-timers.c26
-rw-r--r--kernel/time/tick-common.c15
-rw-r--r--kernel/time/tick-internal.h6
-rw-r--r--kernel/time/tick-sched.c19
-rw-r--r--kernel/time/timekeeping.c78
-rw-r--r--kernel/time/timekeeping.h1
-rw-r--r--kernel/trace/trace.c2
-rw-r--r--kernel/trace/trace_events_hist.c12
-rw-r--r--kernel/trace/trace_uprobe.c35
-rw-r--r--kernel/tracepoint.c4
18 files changed, 186 insertions, 166 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 14750e7c5ee4..027107f4be53 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -476,7 +476,7 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -495,6 +495,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+	.map_release_uref = bpf_fd_array_map_clear,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index a3b21385e947..098eca568c2b 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -43,6 +43,7 @@
 #include <net/tcp.h>
 #include <linux/ptr_ring.h>
 #include <net/inet_common.h>
+#include <linux/sched/signal.h>
 
 #define SOCK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -325,6 +326,9 @@ retry:
 			if (ret > 0) {
 				if (apply)
 					apply_bytes -= ret;
+
+				sg->offset += ret;
+				sg->length -= ret;
 				size -= ret;
 				offset += ret;
 				if (uncharge)
@@ -332,8 +336,6 @@ retry:
 				goto retry;
 			}
 
-			sg->length = size;
-			sg->offset = offset;
 			return ret;
 		}
 
@@ -391,7 +393,8 @@ static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 	} while (i != md->sg_end);
 }
 
-static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+static void free_bytes_sg(struct sock *sk, int bytes,
+			  struct sk_msg_buff *md, bool charge)
 {
 	struct scatterlist *sg = md->sg_data;
 	int i = md->sg_start, free;
@@ -401,11 +404,13 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (bytes < free) {
 			sg[i].length -= bytes;
 			sg[i].offset += bytes;
-			sk_mem_uncharge(sk, bytes);
+			if (charge)
+				sk_mem_uncharge(sk, bytes);
 			break;
 		}
 
-		sk_mem_uncharge(sk, sg[i].length);
+		if (charge)
+			sk_mem_uncharge(sk, sg[i].length);
 		put_page(sg_page(&sg[i]));
 		bytes -= sg[i].length;
 		sg[i].length = 0;
@@ -416,6 +421,7 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (i == MAX_SKB_FRAGS)
 			i = 0;
 	}
+	md->sg_start = i;
 }
 
 static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
@@ -523,8 +529,6 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 	i = md->sg_start;
 
 	do {
-		r->sg_data[i] = md->sg_data[i];
-
 		size = (apply && apply_bytes < md->sg_data[i].length) ?
 			apply_bytes : md->sg_data[i].length;
 
@@ -535,6 +539,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 		}
 
 		sk_mem_charge(sk, size);
+		r->sg_data[i] = md->sg_data[i];
 		r->sg_data[i].length = size;
 		md->sg_data[i].length -= size;
 		md->sg_data[i].offset += size;
@@ -575,10 +580,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 				       struct sk_msg_buff *md,
 				       int flags)
 {
+	bool ingress = !!(md->flags & BPF_F_INGRESS);
 	struct smap_psock *psock;
 	struct scatterlist *sg;
-	int i, err, free = 0;
-	bool ingress = !!(md->flags & BPF_F_INGRESS);
+	int err = 0;
 
 	sg = md->sg_data;
 
@@ -606,16 +611,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 out_rcu:
 	rcu_read_unlock();
 out:
-	i = md->sg_start;
-	while (sg[i].length) {
-		free += sg[i].length;
-		put_page(sg_page(&sg[i]));
-		sg[i].length = 0;
-		i++;
-		if (i == MAX_SKB_FRAGS)
-			i = 0;
-	}
-	return free;
+	free_bytes_sg(NULL, send, md, false);
+	return err;
 }
 
 static inline void bpf_md_init(struct smap_psock *psock)
@@ -700,19 +697,26 @@ more_data:
 		err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
 		lock_sock(sk);
 
+		if (unlikely(err < 0)) {
+			free_start_sg(sk, m);
+			psock->sg_size = 0;
+			if (!cork)
+				*copied -= send;
+		} else {
+			psock->sg_size -= send;
+		}
+
 		if (cork) {
 			free_start_sg(sk, m);
+			psock->sg_size = 0;
 			kfree(m);
 			m = NULL;
+			err = 0;
 		}
-		if (unlikely(err))
-			*copied -= err;
-		else
-			psock->sg_size -= send;
 		break;
 	case __SK_DROP:
 	default:
-		free_bytes_sg(sk, send, m);
+		free_bytes_sg(sk, send, m, true);
 		apply_bytes_dec(psock, send);
 		*copied -= send;
 		psock->sg_size -= send;
@@ -732,6 +736,26 @@ out_err:
 	return err;
 }
 
+static int bpf_wait_data(struct sock *sk,
+			 struct smap_psock *psk, int flags,
+			 long timeo, int *err)
+{
+	int rc;
+
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	rc = sk_wait_event(sk, &timeo,
+			   !list_empty(&psk->ingress) ||
+			   !skb_queue_empty(&sk->sk_receive_queue),
+			   &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	return rc;
+}
+
 static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			   int nonblock, int flags, int *addr_len)
 {
@@ -755,6 +779,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	lock_sock(sk);
+bytes_ready:
 	while (copied != len) {
 		struct scatterlist *sg;
 		struct sk_msg_buff *md;
@@ -809,6 +834,28 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 	}
 
+	if (!copied) {
+		long timeo;
+		int data;
+		int err = 0;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+		if (data) {
+			if (!skb_queue_empty(&sk->sk_receive_queue)) {
+				release_sock(sk);
+				smap_release_sock(psock, sk);
+				copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+				return copied;
+			}
+			goto bytes_ready;
+		}
+
+		if (err)
+			copied = err;
+	}
+
 	release_sock(sk);
 	smap_release_sock(psock, sk);
 	return copied;
@@ -1831,7 +1878,7 @@ static int sock_map_update_elem(struct bpf_map *map,
 	return err;
 }
 
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+static void sock_map_release(struct bpf_map *map)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
 	struct bpf_prog *orig;
@@ -1855,7 +1902,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_get_next_key = sock_map_get_next_key,
 	.map_update_elem = sock_map_update_elem,
 	.map_delete_elem = sock_map_delete_elem,
-	.map_release = sock_map_release,
+	.map_release_uref = sock_map_release,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4ca46df19c9a..ebfe9f29dae8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -257,8 +257,8 @@ static void bpf_map_free_deferred(struct work_struct *work)
 static void bpf_map_put_uref(struct bpf_map *map)
 {
 	if (atomic_dec_and_test(&map->usercnt)) {
-		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-			bpf_fd_array_map_clear(map);
+		if (map->ops->map_release_uref)
+			map->ops->map_release_uref(map);
 	}
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ce6848e46e94..1725b902983f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -491,7 +491,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 	if (!uprobe)
 		return NULL;
 
-	uprobe->inode = igrab(inode);
+	uprobe->inode = inode;
 	uprobe->offset = offset;
 	init_rwsem(&uprobe->register_rwsem);
 	init_rwsem(&uprobe->consumer_rwsem);
@@ -502,7 +502,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 	if (cur_uprobe) {
 		kfree(uprobe);
 		uprobe = cur_uprobe;
-		iput(inode);
 	}
 
 	return uprobe;
@@ -701,7 +700,6 @@ static void delete_uprobe(struct uprobe *uprobe)
 	rb_erase(&uprobe->rb_node, &uprobes_tree);
 	spin_unlock(&uprobes_treelock);
 	RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
-	iput(uprobe->inode);
 	put_uprobe(uprobe);
 }
 
@@ -873,7 +871,8 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u
  * tuple).  Creation refcount stops uprobe_unregister from freeing the
  * @uprobe even before the register operation is complete. Creation
  * refcount is released when the last @uc for the @uprobe
- * unregisters.
+ * unregisters. Caller of uprobe_register() is required to keep @inode
+ * (and the containing mount) referenced.
  *
  * Return errno if it cannot successully install probes
  * else return 0 (success)
diff --git a/kernel/module.c b/kernel/module.c
index a6e43a5806a1..ce8066b88178 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1472,7 +1472,8 @@ static ssize_t module_sect_show(struct module_attribute *mattr,
 {
 	struct module_sect_attr *sattr =
 		container_of(mattr, struct module_sect_attr, mattr);
-	return sprintf(buf, "0x%pK\n", (void *)sattr->address);
+	return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
+		       (void *)sattr->address : NULL);
 }
 
 static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index e8c0dab4fd65..07148b497451 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -704,24 +704,6 @@ static const struct bin_table bin_net_netfilter_table[] = {
 	{}
 };
 
-static const struct bin_table bin_net_irda_table[] = {
-	{ CTL_INT,	NET_IRDA_DISCOVERY,		"discovery" },
-	{ CTL_STR,	NET_IRDA_DEVNAME,		"devname" },
-	{ CTL_INT,	NET_IRDA_DEBUG,			"debug" },
-	{ CTL_INT,	NET_IRDA_FAST_POLL,		"fast_poll_increase" },
-	{ CTL_INT,	NET_IRDA_DISCOVERY_SLOTS,	"discovery_slots" },
-	{ CTL_INT,	NET_IRDA_DISCOVERY_TIMEOUT,	"discovery_timeout" },
-	{ CTL_INT,	NET_IRDA_SLOT_TIMEOUT,		"slot_timeout" },
-	{ CTL_INT,	NET_IRDA_MAX_BAUD_RATE,		"max_baud_rate" },
-	{ CTL_INT,	NET_IRDA_MIN_TX_TURN_TIME,	"min_tx_turn_time" },
-	{ CTL_INT,	NET_IRDA_MAX_TX_DATA_SIZE,	"max_tx_data_size" },
-	{ CTL_INT,	NET_IRDA_MAX_TX_WINDOW,		"max_tx_window" },
-	{ CTL_INT,	NET_IRDA_MAX_NOREPLY_TIME,	"max_noreply_time" },
-	{ CTL_INT,	NET_IRDA_WARN_NOREPLY_TIME,	"warn_noreply_time" },
-	{ CTL_INT,	NET_IRDA_LAP_KEEPALIVE_TIME,	"lap_keepalive_time" },
-	{}
-};
-
 static const struct bin_table bin_net_table[] = {
 	{ CTL_DIR,	NET_CORE,		"core",		bin_net_core_table },
 	/* NET_ETHER not used */
@@ -743,7 +725,7 @@ static const struct bin_table bin_net_table[] = {
 	{ CTL_DIR,	NET_LLC,		"llc",		bin_net_llc_table },
 	{ CTL_DIR,	NET_NETFILTER,		"netfilter",	bin_net_netfilter_table },
 	/* NET_DCCP "dccp" no longer used */
-	{ CTL_DIR,	NET_IRDA,		"irda",		bin_net_irda_table },
+	/* NET_IRDA "irda" no longer used */
 	{ CTL_INT,	2089,			"nf_conntrack_max" },
 	{}
 };
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index eda1210ce50f..14e858753d76 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -91,6 +91,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get_real,
 		},
 		{
+			.index = HRTIMER_BASE_BOOTTIME,
+			.clockid = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+		},
+		{
 			.index = HRTIMER_BASE_TAI,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
@@ -106,6 +111,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get_real,
 		},
 		{
+			.index = HRTIMER_BASE_BOOTTIME_SOFT,
+			.clockid = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+		},
+		{
 			.index = HRTIMER_BASE_TAI_SOFT,
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
@@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
-	[CLOCK_BOOTTIME]	= HRTIMER_BASE_MONOTONIC,
+	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
 	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
 };
 
@@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_
 static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 {
 	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
 	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
 
 	ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
-						   offs_real, offs_tai);
+					    offs_real, offs_boot, offs_tai);
 
 	base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
+	base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
 	base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
 
 	return now;
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index e0dbae98db9d..69a937c3cd81 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 	case CLOCK_BOOTTIME:
 		get_monotonic_boottime64(tp);
 		break;
-	case CLOCK_MONOTONIC_ACTIVE:
-		ktime_get_active_ts64(tp);
 	default:
 		return -EINVAL;
 	}
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index b6899b5060bd..10b7186d0638 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
 	return 0;
 }
 
-static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
 {
-	timekeeping_clocktai64(tp);
+	get_monotonic_boottime64(tp);
 	return 0;
 }
 
-static int posix_get_monotonic_active(clockid_t which_clock,
-				      struct timespec64 *tp)
+static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
 {
-	ktime_get_active_ts64(tp);
+	timekeeping_clocktai64(tp);
 	return 0;
 }
 
@@ -1317,9 +1316,19 @@ static const struct k_clock clock_tai = {
 	.timer_arm		= common_hrtimer_arm,
 };
 
-static const struct k_clock clock_monotonic_active = {
+static const struct k_clock clock_boottime = {
 	.clock_getres		= posix_get_hrtimer_res,
-	.clock_get		= posix_get_monotonic_active,
+	.clock_get		= posix_get_boottime,
+	.nsleep			= common_nsleep,
+	.timer_create		= common_timer_create,
+	.timer_set		= common_timer_set,
+	.timer_get		= common_timer_get,
+	.timer_del		= common_timer_del,
+	.timer_rearm		= common_hrtimer_rearm,
+	.timer_forward		= common_hrtimer_forward,
+	.timer_remaining	= common_hrtimer_remaining,
+	.timer_try_to_cancel	= common_hrtimer_try_to_cancel,
+	.timer_arm		= common_hrtimer_arm,
 };
 
 static const struct k_clock * const posix_clocks[] = {
@@ -1330,11 +1339,10 @@ static const struct k_clock * const posix_clocks[] = {
 	[CLOCK_MONOTONIC_RAW]		= &clock_monotonic_raw,
 	[CLOCK_REALTIME_COARSE]		= &clock_realtime_coarse,
 	[CLOCK_MONOTONIC_COARSE]	= &clock_monotonic_coarse,
-	[CLOCK_BOOTTIME]		= &clock_monotonic,
+	[CLOCK_BOOTTIME]		= &clock_boottime,
 	[CLOCK_REALTIME_ALARM]		= &alarm_clock,
 	[CLOCK_BOOTTIME_ALARM]		= &alarm_clock,
 	[CLOCK_TAI]			= &clock_tai,
-	[CLOCK_MONOTONIC_ACTIVE]	= &clock_monotonic_active,
 };
 
 static const struct k_clock *clockid_to_kclock(const clockid_t id)
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 099572ca4a8f..49edc1c4f3e6 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -419,19 +419,6 @@ void tick_suspend_local(void)
 	clockevents_shutdown(td->evtdev);
 }
 
-static void tick_forward_next_period(void)
-{
-	ktime_t delta, now = ktime_get();
-	u64 n;
-
-	delta = ktime_sub(now, tick_next_period);
-	n = ktime_divns(delta, tick_period);
-	tick_next_period += n * tick_period;
-	if (tick_next_period < now)
-		tick_next_period += tick_period;
-	tick_sched_forward_next_period();
-}
-
 /**
  * tick_resume_local - Resume the local tick device
  *
@@ -444,8 +431,6 @@ void tick_resume_local(void)
 	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	bool broadcast = tick_resume_check_broadcast();
 
-	tick_forward_next_period();
-
 	clockevents_tick_resume(td->evtdev);
 	if (!broadcast) {
 		if (td->mode == TICKDEV_MODE_PERIODIC)
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 21efab7485ca..e277284c2831 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
 #endif /* !(BROADCAST && ONESHOT) */
 
-#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
-extern void tick_sched_forward_next_period(void);
-#else
-static inline void tick_sched_forward_next_period(void) { }
-#endif
-
 /* NO_HZ_FULL internal */
 #ifdef CONFIG_NO_HZ_FULL
 extern void tick_nohz_init(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 646645e981f9..da9455a6b42b 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -52,15 +52,6 @@ struct tick_sched *tick_get_tick_sched(int cpu)
 static ktime_t last_jiffies_update;
 
 /*
- * Called after resume. Make sure that jiffies are not fast forwarded due to
- * clock monotonic being forwarded by the suspended time.
- */
-void tick_sched_forward_next_period(void)
-{
-	last_jiffies_update = tick_next_period;
-}
-
-/*
  * Must be called with interrupts disabled !
  */
 static void tick_do_update_jiffies64(ktime_t now)
@@ -804,12 +795,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 		return;
 	}
 
-	hrtimer_set_expires(&ts->sched_timer, tick);
-
-	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
-		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
-	else
+	if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+		hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+	} else {
+		hrtimer_set_expires(&ts->sched_timer, tick);
 		tick_program_event(tick, 1);
+	}
 }
 
 static void tick_nohz_retain_tick(struct tick_sched *ts)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index dcf7f20fcd12..49cbceef5deb 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
 
 static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 {
-	/* Update both bases so mono and raw stay coupled. */
-	tk->tkr_mono.base += delta;
-	tk->tkr_raw.base += delta;
-
-	/* Accumulate time spent in suspend */
-	tk->time_suspended += delta;
+	tk->offs_boot = ktime_add(tk->offs_boot, delta);
 }
 
 /*
@@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
 
+/**
+ * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
+ *
+ * To keep it NMI safe since we're accessing from tracing, we're not using a
+ * separate timekeeper with updates to monotonic clock and boot offset
+ * protected with seqlocks. This has the following minor side effects:
+ *
+ * (1) Its possible that a timestamp be taken after the boot offset is updated
+ * but before the timekeeper is updated. If this happens, the new boot offset
+ * is added to the old timekeeping making the clock appear to update slightly
+ * earlier:
+ *    CPU 0                                        CPU 1
+ *    timekeeping_inject_sleeptime64()
+ *    __timekeeping_inject_sleeptime(tk, delta);
+ *                                                 timestamp();
+ *    timekeeping_update(tk, TK_CLEAR_NTP...);
+ *
+ * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
+ * partially updated.  Since the tk->offs_boot update is a rare event, this
+ * should be a rare occurrence which postprocessing should be able to handle.
+ */
+u64 notrace ktime_get_boot_fast_ns(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
+}
+EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
+
+
 /*
  * See comment for __ktime_get_fast_ns() vs. timestamp ordering
  */
@@ -764,6 +789,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
 
 static ktime_t *offsets[TK_OFFS_MAX] = {
 	[TK_OFFS_REAL]	= &tk_core.timekeeper.offs_real,
+	[TK_OFFS_BOOT]	= &tk_core.timekeeper.offs_boot,
 	[TK_OFFS_TAI]	= &tk_core.timekeeper.offs_tai,
 };
 
@@ -861,39 +887,6 @@ void ktime_get_ts64(struct timespec64 *ts)
 EXPORT_SYMBOL_GPL(ktime_get_ts64);
 
 /**
- * ktime_get_active_ts64 - Get the active non-suspended monotonic clock
- * @ts:		pointer to timespec variable
- *
- * The function calculates the monotonic clock from the realtime clock and
- * the wall_to_monotonic offset, subtracts the accumulated suspend time and
- * stores the result in normalized timespec64 format in the variable
- * pointed to by @ts.
- */
-void ktime_get_active_ts64(struct timespec64 *ts)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-	struct timespec64 tomono, tsusp;
-	u64 nsec, nssusp;
-	unsigned int seq;
-
-	WARN_ON(timekeeping_suspended);
-
-	do {
-		seq = read_seqcount_begin(&tk_core.seq);
-		ts->tv_sec = tk->xtime_sec;
-		nsec = timekeeping_get_ns(&tk->tkr_mono);
-		tomono = tk->wall_to_monotonic;
-		nssusp = tk->time_suspended;
-	} while (read_seqcount_retry(&tk_core.seq, seq));
-
-	ts->tv_sec += tomono.tv_sec;
-	ts->tv_nsec = 0;
-	timespec64_add_ns(ts, nsec + tomono.tv_nsec);
-	tsusp = ns_to_timespec64(nssusp);
-	*ts = timespec64_sub(*ts, tsusp);
-}
-
-/**
  * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
  *
  * Returns the seconds portion of CLOCK_MONOTONIC with a single non
@@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 		return;
 	}
 	tk_xtime_add(tk, delta);
+	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
 	tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
 	tk_debug_account_sleep_time(delta);
 }
@@ -2125,7 +2119,7 @@ out:
 void getboottime64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended);
+	ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
 
 	*ts = ktime_to_timespec64(t);
 }
@@ -2188,6 +2182,7 @@ void do_timer(unsigned long ticks)
  * ktime_get_update_offsets_now - hrtimer helper
  * @cwsseq:	pointer to check and store the clock was set sequence number
  * @offs_real:	pointer to storage for monotonic -> realtime offset
+ * @offs_boot:	pointer to storage for monotonic -> boottime offset
  * @offs_tai:	pointer to storage for monotonic -> clock tai offset
  *
  * Returns current monotonic time and updates the offsets if the
@@ -2197,7 +2192,7 @@ void do_timer(unsigned long ticks)
  * Called from hrtimer_interrupt() or retrigger_next_event()
  */
 ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
-				     ktime_t *offs_tai)
+				     ktime_t *offs_boot, ktime_t *offs_tai)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned int seq;
@@ -2214,6 +2209,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 		if (*cwsseq != tk->clock_was_set_seq) {
 			*cwsseq = tk->clock_was_set_seq;
 			*offs_real = tk->offs_real;
+			*offs_boot = tk->offs_boot;
 			*offs_tai = tk->offs_tai;
 		}
 
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 79b67f5e0343..7a9b4eb7a1d5 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -6,6 +6,7 @@
  */
 extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
 					    ktime_t *offs_real,
+					    ktime_t *offs_boot,
 					    ktime_t *offs_tai);
 
 extern int timekeeping_valid_for_hres(void);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dfbcf9ee1447..414d7210b2ec 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1165,7 +1165,7 @@ static struct {
 	{ trace_clock,			"perf",		1 },
 	{ ktime_get_mono_fast_ns,	"mono",		1 },
 	{ ktime_get_raw_fast_ns,	"mono_raw",	1 },
-	{ ktime_get_mono_fast_ns,	"boot",		1 },
+	{ ktime_get_boot_fast_ns,	"boot",		1 },
 	ARCH_TRACE_CLOCKS
 };
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0d7b3ffbecc2..b9061ed59bbd 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2466,6 +2466,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 		else if (strcmp(modifier, "usecs") == 0)
 			*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
 		else {
+			hist_err("Invalid field modifier: ", modifier);
 			field = ERR_PTR(-EINVAL);
 			goto out;
 		}
@@ -2481,6 +2482,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 	else {
 		field = trace_find_event_field(file->event_call, field_name);
 		if (!field || !field->size) {
+			hist_err("Couldn't find field: ", field_name);
 			field = ERR_PTR(-EINVAL);
 			goto out;
 		}
@@ -4913,6 +4915,16 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 		seq_printf(m, "%s", field_name);
 	} else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
 		seq_puts(m, "common_timestamp");
+
+	if (hist_field->flags) {
+		if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) &&
+		    !(hist_field->flags & HIST_FIELD_FL_EXPR)) {
+			const char *flags = get_hist_field_flags(hist_field);
+
+			if (flags)
+				seq_printf(m, ".%s", flags);
+		}
+	}
 }
 
 static int event_hist_trigger_print(struct seq_file *m,
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 34fd0e0ec51d..ac892878dbe6 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -55,6 +55,7 @@ struct trace_uprobe {
 	struct list_head		list;
 	struct trace_uprobe_filter	filter;
 	struct uprobe_consumer		consumer;
+	struct path			path;
 	struct inode			*inode;
 	char				*filename;
 	unsigned long			offset;
@@ -289,7 +290,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
 	for (i = 0; i < tu->tp.nr_args; i++)
 		traceprobe_free_probe_arg(&tu->tp.args[i]);
 
-	iput(tu->inode);
+	path_put(&tu->path);
 	kfree(tu->tp.call.class->system);
 	kfree(tu->tp.call.name);
 	kfree(tu->filename);
@@ -363,7 +364,6 @@ end:
 static int create_trace_uprobe(int argc, char **argv)
 {
 	struct trace_uprobe *tu;
-	struct inode *inode;
 	char *arg, *event, *group, *filename;
 	char buf[MAX_EVENT_NAME_LEN];
 	struct path path;
@@ -371,7 +371,6 @@ static int create_trace_uprobe(int argc, char **argv)
 	bool is_delete, is_return;
 	int i, ret;
 
-	inode = NULL;
 	ret = 0;
 	is_delete = false;
 	is_return = false;
@@ -437,21 +436,16 @@ static int create_trace_uprobe(int argc, char **argv)
 	}
 	/* Find the last occurrence, in case the path contains ':' too. */
 	arg = strrchr(argv[1], ':');
-	if (!arg) {
-		ret = -EINVAL;
-		goto fail_address_parse;
-	}
+	if (!arg)
+		return -EINVAL;
 
 	*arg++ = '\0';
 	filename = argv[1];
 	ret = kern_path(filename, LOOKUP_FOLLOW, &path);
 	if (ret)
-		goto fail_address_parse;
-
-	inode = igrab(d_real_inode(path.dentry));
-	path_put(&path);
+		return ret;
 
-	if (!inode || !S_ISREG(inode->i_mode)) {
+	if (!d_is_reg(path.dentry)) {
 		ret = -EINVAL;
 		goto fail_address_parse;
 	}
@@ -490,7 +484,7 @@ static int create_trace_uprobe(int argc, char **argv)
 		goto fail_address_parse;
 	}
 	tu->offset = offset;
-	tu->inode = inode;
+	tu->path = path;
 	tu->filename = kstrdup(filename, GFP_KERNEL);
 
 	if (!tu->filename) {
@@ -558,7 +552,7 @@ error:
 	return ret;
 
 fail_address_parse:
-	iput(inode);
+	path_put(&path);
 
 	pr_info("Failed to parse address or file.\n");
 
@@ -922,6 +916,7 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
 		goto err_flags;
 
 	tu->consumer.filter = filter;
+	tu->inode = d_real_inode(tu->path.dentry);
 	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
 	if (ret)
 		goto err_buffer;
@@ -967,6 +962,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
+	tu->inode = NULL;
 	tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;
 
 	uprobe_buffer_disable();
@@ -1337,7 +1333,6 @@ struct trace_event_call *
 create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 {
 	struct trace_uprobe *tu;
-	struct inode *inode;
 	struct path path;
 	int ret;
 
@@ -1345,11 +1340,8 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 	if (ret)
 		return ERR_PTR(ret);
 
-	inode = igrab(d_inode(path.dentry));
-	path_put(&path);
-
-	if (!inode || !S_ISREG(inode->i_mode)) {
-		iput(inode);
+	if (!d_is_reg(path.dentry)) {
+		path_put(&path);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1364,11 +1356,12 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 	if (IS_ERR(tu)) {
 		pr_info("Failed to allocate trace_uprobe.(%d)\n",
 			(int)PTR_ERR(tu));
+		path_put(&path);
 		return ERR_CAST(tu);
 	}
 
 	tu->offset = offs;
-	tu->inode = inode;
+	tu->path = path;
 	tu->filename = kstrdup(name, GFP_KERNEL);
 	init_trace_event_call(tu, &tu->tp.call);
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 671b13457387..1e37da2e0c25 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -207,7 +207,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 			lockdep_is_held(&tracepoints_mutex));
 	old = func_add(&tp_funcs, func, prio);
 	if (IS_ERR(old)) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
 		return PTR_ERR(old);
 	}
 
@@ -239,7 +239,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 			lockdep_is_held(&tracepoints_mutex));
 	old = func_remove(&tp_funcs, func);
 	if (IS_ERR(old)) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
 		return PTR_ERR(old);
 	}
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-16 22:29:20 +0000