[PATCH AUTOSEL 6.12 1/5] can: statistics: use atomic access in hot path

[PATCH AUTOSEL 6.12 1/5] can: statistics: use atomic access in hot path

[Sasha Levin]

From: Oliver Hartkopp <socketcan@hartkopp.net>

[ Upstream commit 80b5f90158d1364cbd80ad82852a757fc0692bf2 ]

In can_send() and can_receive() CAN messages and CAN filter matches are
counted to be visible in the CAN procfs files.

KCSAN detected a data race within can_send() when two CAN frames have
been generated by a timer event writing to the same CAN netdevice at the
same time. Use atomic operations to access the statistics in the hot path
to fix the KCSAN complaint.

Reported-by: syzbot+78ce4489b812515d5e4d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/67cd717d.050a0220.e1a89.0006.GAE@google.com
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250310143353.3242-1-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/can/af_can.c | 12 ++++++------
 net/can/af_can.h | 12 ++++++------
 net/can/proc.c   | 46 +++++++++++++++++++++++++++-------------------
 3 files changed, 39 insertions(+), 31 deletions(-)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index 01f3fbb3b67dc..65230e81fa08c 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -287,8 +287,8 @@ int can_send(struct sk_buff *skb, int loop)
 		netif_rx(newskb);
 
 	/* update statistics */
-	pkg_stats->tx_frames++;
-	pkg_stats->tx_frames_delta++;
+	atomic_long_inc(&pkg_stats->tx_frames);
+	atomic_long_inc(&pkg_stats->tx_frames_delta);
 
 	return 0;
 
@@ -647,8 +647,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	int matches;
 
 	/* update statistics */
-	pkg_stats->rx_frames++;
-	pkg_stats->rx_frames_delta++;
+	atomic_long_inc(&pkg_stats->rx_frames);
+	atomic_long_inc(&pkg_stats->rx_frames_delta);
 
 	/* create non-zero unique skb identifier together with *skb */
 	while (!(can_skb_prv(skb)->skbcnt))
@@ -669,8 +669,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	consume_skb(skb);
 
 	if (matches > 0) {
-		pkg_stats->matches++;
-		pkg_stats->matches_delta++;
+		atomic_long_inc(&pkg_stats->matches);
+		atomic_long_inc(&pkg_stats->matches_delta);
 	}
 }
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index 7c2d9161e2245..22f3352c77fec 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -66,9 +66,9 @@ struct receiver {
 struct can_pkg_stats {
 	unsigned long jiffies_init;
 
-	unsigned long rx_frames;
-	unsigned long tx_frames;
-	unsigned long matches;
+	atomic_long_t rx_frames;
+	atomic_long_t tx_frames;
+	atomic_long_t matches;
 
 	unsigned long total_rx_rate;
 	unsigned long total_tx_rate;
@@ -82,9 +82,9 @@ struct can_pkg_stats {
 	unsigned long max_tx_rate;
 	unsigned long max_rx_match_ratio;
 
-	unsigned long rx_frames_delta;
-	unsigned long tx_frames_delta;
-	unsigned long matches_delta;
+	atomic_long_t rx_frames_delta;
+	atomic_long_t tx_frames_delta;
+	atomic_long_t matches_delta;
 };
 
 /* persistent statistics */
diff --git a/net/can/proc.c b/net/can/proc.c
index bbce97825f13f..25fdf060e30d0 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -118,6 +118,13 @@ void can_stat_update(struct timer_list *t)
 	struct can_pkg_stats *pkg_stats = net->can.pkg_stats;
 	unsigned long j = jiffies; /* snapshot */
 
+	long rx_frames = atomic_long_read(&pkg_stats->rx_frames);
+	long tx_frames = atomic_long_read(&pkg_stats->tx_frames);
+	long matches = atomic_long_read(&pkg_stats->matches);
+	long rx_frames_delta = atomic_long_read(&pkg_stats->rx_frames_delta);
+	long tx_frames_delta = atomic_long_read(&pkg_stats->tx_frames_delta);
+	long matches_delta = atomic_long_read(&pkg_stats->matches_delta);
+
 	/* restart counting in timer context on user request */
 	if (user_reset)
 		can_init_stats(net);
@@ -127,35 +134,33 @@ void can_stat_update(struct timer_list *t)
 		can_init_stats(net);
 
 	/* prevent overflow in calc_rate() */
-	if (pkg_stats->rx_frames > (ULONG_MAX / HZ))
+	if (rx_frames > (LONG_MAX / HZ))
 		can_init_stats(net);
 
 	/* prevent overflow in calc_rate() */
-	if (pkg_stats->tx_frames > (ULONG_MAX / HZ))
+	if (tx_frames > (LONG_MAX / HZ))
 		can_init_stats(net);
 
 	/* matches overflow - very improbable */
-	if (pkg_stats->matches > (ULONG_MAX / 100))
+	if (matches > (LONG_MAX / 100))
 		can_init_stats(net);
 
 	/* calc total values */
-	if (pkg_stats->rx_frames)
-		pkg_stats->total_rx_match_ratio = (pkg_stats->matches * 100) /
-			pkg_stats->rx_frames;
+	if (rx_frames)
+		pkg_stats->total_rx_match_ratio = (matches * 100) / rx_frames;
 
 	pkg_stats->total_tx_rate = calc_rate(pkg_stats->jiffies_init, j,
-					    pkg_stats->tx_frames);
+					    tx_frames);
 	pkg_stats->total_rx_rate = calc_rate(pkg_stats->jiffies_init, j,
-					    pkg_stats->rx_frames);
+					    rx_frames);
 
 	/* calc current values */
-	if (pkg_stats->rx_frames_delta)
+	if (rx_frames_delta)
 		pkg_stats->current_rx_match_ratio =
-			(pkg_stats->matches_delta * 100) /
-			pkg_stats->rx_frames_delta;
+			(matches_delta * 100) /	rx_frames_delta;
 
-	pkg_stats->current_tx_rate = calc_rate(0, HZ, pkg_stats->tx_frames_delta);
-	pkg_stats->current_rx_rate = calc_rate(0, HZ, pkg_stats->rx_frames_delta);
+	pkg_stats->current_tx_rate = calc_rate(0, HZ, tx_frames_delta);
+	pkg_stats->current_rx_rate = calc_rate(0, HZ, rx_frames_delta);
 
 	/* check / update maximum values */
 	if (pkg_stats->max_tx_rate < pkg_stats->current_tx_rate)
@@ -168,9 +173,9 @@ void can_stat_update(struct timer_list *t)
 		pkg_stats->max_rx_match_ratio = pkg_stats->current_rx_match_ratio;
 
 	/* clear values for 'current rate' calculation */
-	pkg_stats->tx_frames_delta = 0;
-	pkg_stats->rx_frames_delta = 0;
-	pkg_stats->matches_delta   = 0;
+	atomic_long_set(&pkg_stats->tx_frames_delta, 0);
+	atomic_long_set(&pkg_stats->rx_frames_delta, 0);
+	atomic_long_set(&pkg_stats->matches_delta, 0);
 
 	/* restart timer (one second) */
 	mod_timer(&net->can.stattimer, round_jiffies(jiffies + HZ));
@@ -214,9 +219,12 @@ static int can_stats_proc_show(struct seq_file *m, void *v)
 	struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats;
 
 	seq_putc(m, '\n');
-	seq_printf(m, " %8ld transmitted frames (TXF)\n", pkg_stats->tx_frames);
-	seq_printf(m, " %8ld received frames (RXF)\n", pkg_stats->rx_frames);
-	seq_printf(m, " %8ld matched frames (RXMF)\n", pkg_stats->matches);
+	seq_printf(m, " %8ld transmitted frames (TXF)\n",
+		   atomic_long_read(&pkg_stats->tx_frames));
+	seq_printf(m, " %8ld received frames (RXF)\n",
+		   atomic_long_read(&pkg_stats->rx_frames));
+	seq_printf(m, " %8ld matched frames (RXMF)\n",
+		   atomic_long_read(&pkg_stats->matches));
 
 	seq_putc(m, '\n');
 
-- 
2.39.5

[PATCH AUTOSEL 6.12 2/5] memory: omap-gpmc: drop no compatible check

[Sasha Levin]

From: Roger Quadros <rogerq@kernel.org>

[ Upstream commit edcccc6892f65eff5fd3027a13976131dc7fd733 ]

We are no longer depending on legacy device trees so
drop the no compatible check for NAND and OneNAND
nodes.

Suggested-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250114-omap-gpmc-drop-no-compatible-check-v1-1-262c8d549732@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/memory/omap-gpmc.c | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index c8a0d82f9c27d..719225c09a4d6 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -2245,26 +2245,6 @@ static int gpmc_probe_generic_child(struct platform_device *pdev,
 		goto err;
 	}
 
-	if (of_node_name_eq(child, "nand")) {
-		/* Warn about older DT blobs with no compatible property */
-		if (!of_property_read_bool(child, "compatible")) {
-			dev_warn(&pdev->dev,
-				 "Incompatible NAND node: missing compatible");
-			ret = -EINVAL;
-			goto err;
-		}
-	}
-
-	if (of_node_name_eq(child, "onenand")) {
-		/* Warn about older DT blobs with no compatible property */
-		if (!of_property_read_bool(child, "compatible")) {
-			dev_warn(&pdev->dev,
-				 "Incompatible OneNAND node: missing compatible");
-			ret = -EINVAL;
-			goto err;
-		}
-	}
-
 	if (of_match_node(omap_nand_ids, child)) {
 		/* NAND specific setup */
 		val = 8;
-- 
2.39.5

[PATCH AUTOSEL 6.12 3/5] Revert "sched/core: Reduce cost of sched_move_task when config autogroup"

[Sasha Levin]

From: Dietmar Eggemann <dietmar.eggemann@arm.com>

[ Upstream commit 76f970ce51c80f625eb6ddbb24e9cb51b977b598 ]

This reverts commit eff6c8ce8d4d7faef75f66614dd20bb50595d261.

Hazem reported a 30% drop in UnixBench spawn test with commit
eff6c8ce8d4d ("sched/core: Reduce cost of sched_move_task when config
autogroup") on a m6g.xlarge AWS EC2 instance with 4 vCPUs and 16 GiB RAM
(aarch64) (single level MC sched domain):

  https://lkml.kernel.org/r/20250205151026.13061-1-hagarhem@amazon.com

There is an early bail from sched_move_task() if p->sched_task_group is
equal to p's 'cpu cgroup' (sched_get_task_group()). E.g. both are
pointing to taskgroup '/user.slice/user-1000.slice/session-1.scope'
(Ubuntu '22.04.5 LTS').

So in:

  do_exit()

    sched_autogroup_exit_task()

      sched_move_task()

        if sched_get_task_group(p) == p->sched_task_group
          return

        /* p is enqueued */
        dequeue_task()              \
        sched_change_group()        |
          task_change_group_fair()  |
            detach_task_cfs_rq()    |                              (1)
            set_task_rq()           |
            attach_task_cfs_rq()    |
        enqueue_task()              /

(1) isn't called for p anymore.

Turns out that the regression is related to sgs->group_util in
group_is_overloaded() and group_has_capacity(). If (1) isn't called for
all the 'spawn' tasks then sgs->group_util is ~900 and
sgs->group_capacity = 1024 (single CPU sched domain) and this leads to
group_is_overloaded() returning true (2) and group_has_capacity() false
(3) much more often compared to the case when (1) is called.

I.e. there are much more cases of 'group_is_overloaded' and
'group_fully_busy' in WF_FORK wakeup sched_balance_find_dst_cpu() which
then returns much more often a CPU != smp_processor_id() (5).

This isn't good for these extremely short running tasks (FORK + EXIT)
and also involves calling sched_balance_find_dst_group_cpu() unnecessary
(single CPU sched domain).

Instead if (1) is called for 'p->flags & PF_EXITING' then the path
(4),(6) is taken much more often.

  select_task_rq_fair(..., wake_flags = WF_FORK)

    cpu = smp_processor_id()

    new_cpu = sched_balance_find_dst_cpu(..., cpu, ...)

      group = sched_balance_find_dst_group(..., cpu)

        do {

          update_sg_wakeup_stats()

            sgs->group_type = group_classify()

              if group_is_overloaded()                             (2)
                return group_overloaded

              if !group_has_capacity()                             (3)
                return group_fully_busy

              return group_has_spare                               (4)

        } while group

        if local_sgs.group_type > idlest_sgs.group_type
          return idlest                                            (5)

        case group_has_spare:

          if local_sgs.idle_cpus >= idlest_sgs.idle_cpus
            return NULL                                            (6)

Unixbench Tests './Run -c 4 spawn' on:

(a) VM AWS instance (m7gd.16xlarge) with v6.13 ('maxcpus=4 nr_cpus=4')
    and Ubuntu 22.04.5 LTS (aarch64).

    Shell & test run in '/user.slice/user-1000.slice/session-1.scope'.

    w/o patch	w/ patch
    21005	27120

(b) i7-13700K with tip/sched/core ('nosmt maxcpus=8 nr_cpus=8') and
    Ubuntu 22.04.5 LTS (x86_64).

    Shell & test run in '/A'.

    w/o patch	w/ patch
    67675	88806

CONFIG_SCHED_AUTOGROUP=y & /sys/proc/kernel/sched_autogroup_enabled equal
0 or 1.

Reported-by: Hazem Mohamed Abuelfotoh <abuehaze@amazon.com>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Hagar Hemdan <hagarhem@amazon.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250314151345.275739-1-dietmar.eggemann@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sched/core.c | 21 +++------------------
 1 file changed, 3 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1f817d0c5d2d0..e9bb1b4c58421 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8919,7 +8919,7 @@ void sched_release_group(struct task_group *tg)
 	spin_unlock_irqrestore(&task_group_lock, flags);
 }
 
-static struct task_group *sched_get_task_group(struct task_struct *tsk)
+static void sched_change_group(struct task_struct *tsk)
 {
 	struct task_group *tg;
 
@@ -8931,13 +8931,7 @@ static struct task_group *sched_get_task_group(struct task_struct *tsk)
 	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
 			  struct task_group, css);
 	tg = autogroup_task_group(tsk, tg);
-
-	return tg;
-}
-
-static void sched_change_group(struct task_struct *tsk, struct task_group *group)
-{
-	tsk->sched_task_group = group;
+	tsk->sched_task_group = tg;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_change_group)
@@ -8958,20 +8952,11 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 {
 	int queued, running, queue_flags =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
-	struct task_group *group;
 	struct rq *rq;
 
 	CLASS(task_rq_lock, rq_guard)(tsk);
 	rq = rq_guard.rq;
 
-	/*
-	 * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous
-	 * group changes.
-	 */
-	group = sched_get_task_group(tsk);
-	if (group == tsk->sched_task_group)
-		return;
-
 	update_rq_clock(rq);
 
 	running = task_current(rq, tsk);
@@ -8982,7 +8967,7 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 	if (running)
 		put_prev_task(rq, tsk);
 
-	sched_change_group(tsk, group);
+	sched_change_group(tsk);
 	if (!for_autogroup)
 		scx_cgroup_move_task(tsk);
 
-- 
2.39.5

[PATCH AUTOSEL 6.12 4/5] hwmon: (nct6775-core) Fix out of bounds access for NCT679{8,9}

[Sasha Levin]

From: Tasos Sahanidis <tasos@tasossah.com>

[ Upstream commit 815f80ad20b63830949a77c816e35395d5d55144 ]

pwm_num is set to 7 for these chips, but NCT6776_REG_PWM_MODE and
NCT6776_PWM_MODE_MASK only contain 6 values.

Fix this by adding another 0 to the end of each array.

Signed-off-by: Tasos Sahanidis <tasos@tasossah.com>
Link: https://lore.kernel.org/r/20250312030832.106475-1-tasos@tasossah.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/hwmon/nct6775-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c
index fa3351351825b..79bc67ffb9986 100644
--- a/drivers/hwmon/nct6775-core.c
+++ b/drivers/hwmon/nct6775-core.c
@@ -273,8 +273,8 @@ static const s8 NCT6776_BEEP_BITS[NUM_BEEP_BITS] = {
 static const u16 NCT6776_REG_TOLERANCE_H[] = {
 	0x10c, 0x20c, 0x30c, 0x80c, 0x90c, 0xa0c, 0xb0c };
 
-static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0 };
-static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0, 0 };
 
 static const u16 NCT6776_REG_FAN_MIN[] = {
 	0x63a, 0x63c, 0x63e, 0x640, 0x642, 0x64a, 0x64c };
-- 
2.39.5

[PATCH AUTOSEL 6.12 5/5] netfs: Fix netfs_unbuffered_read() to return ssize_t rather than int

[Sasha Levin]

From: David Howells <dhowells@redhat.com>

[ Upstream commit 07c574eb53d4cc9aa7b985bc8bfcb302e5dc4694 ]

Fix netfs_unbuffered_read() to return an ssize_t rather than an int as
netfs_wait_for_read() returns ssize_t and this gets implicitly truncated.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20250314164201.1993231-5-dhowells@redhat.com
Acked-by: "Paulo Alcantara (Red Hat)" <pc@manguebit.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Viacheslav Dubeyko <slava@dubeyko.com>
cc: Alex Markuze <amarkuze@redhat.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: ceph-devel@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/direct_read.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
index b1a66a6e6bc2d..917b7edc34ef5 100644
--- a/fs/netfs/direct_read.c
+++ b/fs/netfs/direct_read.c
@@ -108,9 +108,9 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
  * Perform a read to an application buffer, bypassing the pagecache and the
  * local disk cache.
  */
-static int netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync)
+static ssize_t netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync)
 {
-	int ret;
+	ssize_t ret;
 
 	_enter("R=%x %llx-%llx",
 	       rreq->debug_id, rreq->start, rreq->start + rreq->len - 1);
@@ -149,7 +149,7 @@ static int netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync)
 	}
 
 out:
-	_leave(" = %d", ret);
+	_leave(" = %zd", ret);
 	return ret;
 }
 
-- 
2.39.5