July 2023 - Linux-stable-mirror

[PATCH v2] powerpc/bpf: populate extable entries only during the last pass

by Hari Bathini

Since commit 85e031154c7c ("powerpc/bpf: Perform complete extra passes to update addresses"), two additional passes are performed to avoid space and CPU time wastage on powerpc. But these extra passes led to WARN_ON_ONCE() hits in bpf_add_extable_entry() as extable entries are populated again, during the extra pass, without resetting the index. Fix it by resetting entry index before repopulating extable entries, if and when there is an additional pass. Fixes: 85e031154c7c ("powerpc/bpf: Perform complete extra passes to update addresses") Cc: stable(a)vger.kernel.org Signed-off-by: Hari Bathini <hbathini(a)linux.ibm.com> --- arch/powerpc/net/bpf_jit_comp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index e93aefcfb83f..37043dfc1add 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_hdr = jit_data->header; proglen = jit_data->proglen; extra_pass = true; + /* During extra pass, ensure index is reset before repopulating extable entries */ + cgctx.exentry_idx = 0; goto skip_init_ctx; } -- 2.40.0

1 year, 9 months

3
2
0 0

[PATCH net 1/3] wireguard: queueing: use saner cpu selection wrapping

by Jason A. Donenfeld

Using `% nr_cpumask_bits` is slow and complicated, and not totally robust toward dynamic changes to CPU topologies. Rather than storing the next CPU in the round-robin, just store the last one, and also return that value. This simplifies the loop drastically into a much more common pattern. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable(a)vger.kernel.org Reported-by: Linus Torvalds <torvalds(a)linux-foundation.org> Tested-by: Manuel Leiner <manuel.leiner(a)gmx.de> Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> --- drivers/net/wireguard/queueing.c | 1 + drivers/net/wireguard/queueing.h | 25 +++++++++++-------------- drivers/net/wireguard/receive.c | 2 +- drivers/net/wireguard/send.c | 2 +- 4 files changed, 14 insertions(+), 16 deletions(-) diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 8084e7408c0a..26d235d15235 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -28,6 +28,7 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, int ret; memset(queue, 0, sizeof(*queue)); + queue->last_cpu = -1; ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); if (ret) return ret; diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index 125284b346a7..1ea4f874e367 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -117,20 +117,17 @@ static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) return cpu; } -/* This function is racy, in the sense that next is unlocked, so it could return - * the same CPU twice. A race-free version of this would be to instead store an - * atomic sequence number, do an increment-and-return, and then iterate through - * every possible CPU until we get to that index -- choose_cpu. However that's - * a bit slower, and it doesn't seem like this potential race actually - * introduces any performance loss, so we live with it. +/* This function is racy, in the sense that it's called while last_cpu is + * unlocked, so it could return the same CPU twice. Adding locking or using + * atomic sequence numbers is slower though, and the consequences of racing are + * harmless, so live with it. */ -static inline int wg_cpumask_next_online(int *next) +static inline int wg_cpumask_next_online(int *last_cpu) { - int cpu = *next; - - while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask))) - cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; - *next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; + int cpu = cpumask_next(*last_cpu, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_first(cpu_online_mask); + *last_cpu = cpu; return cpu; } @@ -159,7 +156,7 @@ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) static inline int wg_queue_enqueue_per_device_and_peer( struct crypt_queue *device_queue, struct prev_queue *peer_queue, - struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu) + struct sk_buff *skb, struct workqueue_struct *wq) { int cpu; @@ -173,7 +170,7 @@ static inline int wg_queue_enqueue_per_device_and_peer( /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ - cpu = wg_cpumask_next_online(next_cpu); + cpu = wg_cpumask_next_online(&device_queue->last_cpu); if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb))) return -EPIPE; queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 7135d51d2d87..0b3f0c843550 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -524,7 +524,7 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb, - wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu); + wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD); if (likely(!ret || ret == -EPIPE)) { diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 5368f7c35b4b..95c853b59e1d 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -318,7 +318,7 @@ static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, - wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu); + wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: -- 2.41.0

1 year, 9 months

2
1
0 0

[PATCH net 2/3] wireguard: netlink: send staged packets when setting initial private key

by Jason A. Donenfeld

Packets bound for peers can queue up prior to the device private key being set. For example, if persistent keepalive is set, a packet is queued up to be sent as soon as the device comes up. However, if the private key hasn't been set yet, the handshake message never sends, and no timer is armed to retry, since that would be pointless. But, if a user later sets a private key, the expectation is that those queued packets, such as a persistent keepalive, are actually sent. So adjust the configuration logic to account for this edge case, and add a test case to make sure this works. Maxim noticed this with a wg-quick(8) config to the tune of: [Interface] PostUp = wg set %i private-key somefile [Peer] PublicKey = ... Endpoint = ... PersistentKeepalive = 25 Here, the private key gets set after the device comes up using a PostUp script, triggering the bug. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable(a)vger.kernel.org Reported-by: Maxim Cournoyer <maxim.cournoyer(a)gmail.com> Tested-by: Maxim Cournoyer <maxim.cournoyer(a)gmail.com> Link: https://lore.kernel.org/wireguard/87fs7xtqrv.fsf@gmail.com/ Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> --- drivers/net/wireguard/netlink.c | 14 ++++++---- tools/testing/selftests/wireguard/netns.sh | 30 +++++++++++++++++++--- 2 files changed, 35 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 43c8c84e7ea8..6d1bd9f52d02 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -546,6 +546,7 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]); u8 public_key[NOISE_PUBLIC_KEY_LEN]; struct wg_peer *peer, *temp; + bool send_staged_packets; if (!crypto_memneq(wg->static_identity.static_private, private_key, NOISE_PUBLIC_KEY_LEN)) @@ -564,14 +565,17 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) } down_write(&wg->static_identity.lock); - wg_noise_set_static_identity_private_key(&wg->static_identity, - private_key); - list_for_each_entry_safe(peer, temp, &wg->peer_list, - peer_list) { + send_staged_packets = !wg->static_identity.has_identity && netif_running(wg->dev); + wg_noise_set_static_identity_private_key(&wg->static_identity, private_key); + send_staged_packets = send_staged_packets && wg->static_identity.has_identity; + + wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); + list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) { wg_noise_precompute_static_static(peer); wg_noise_expire_current_peer_keypairs(peer); + if (send_staged_packets) + wg_packet_send_staged_packets(peer); } - wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); up_write(&wg->static_identity.lock); } skip_set_private_key: diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 69c7796c7ca9..405ff262ca93 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -514,10 +514,32 @@ n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' n1 ping -W 1 -c 1 192.168.241.2 [[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]] -ip1 link del veth1 -ip1 link del veth3 -ip1 link del wg0 -ip2 link del wg0 +ip1 link del dev veth3 +ip1 link del dev wg0 +ip2 link del dev wg0 + +# Make sure persistent keep alives are sent when an adapter comes up +ip1 link add dev wg0 type wireguard +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1 +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +ip1 link set dev wg0 up +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -gt 0 ]] +ip1 link del dev wg0 +# This should also happen even if the private key is set later +ip1 link add dev wg0 type wireguard +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1 +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +ip1 link set dev wg0 up +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +n1 wg set wg0 private-key <(echo "$key1") +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -gt 0 ]] +ip1 link del dev veth1 +ip1 link del dev wg0 # We test that Netlink/IPC is working properly by doing things that usually cause split responses ip0 link add dev wg0 type wireguard -- 2.41.0

1 year, 9 months

1
0
0 0

[PATCH AUTOSEL 5.4] rcu: Mark rcu_cpu_kthread() accesses to ->rcu_cpu_has_work

by Sasha Levin

From: "Paul E. McKenney" <paulmck(a)kernel.org> [ Upstream commit a24c1aab652ebacf9ea62470a166514174c96fe1 ] The rcu_data structure's ->rcu_cpu_has_work field can be modified by any CPU attempting to wake up the rcuc kthread. Therefore, this commit marks accesses to this field from the rcu_cpu_kthread() function. This data race was reported by KCSAN. Not appropriate for backporting due to failure being unlikely. Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/rcu/tree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 615283404d9dc..98d64f107fbb7 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2457,12 +2457,12 @@ static void rcu_cpu_kthread(unsigned int cpu) *statusp = RCU_KTHREAD_RUNNING; local_irq_disable(); work = *workp; - *workp = 0; + WRITE_ONCE(*workp, 0); local_irq_enable(); if (work) rcu_core(); local_bh_enable(); - if (*workp == 0) { + if (!READ_ONCE(*workp)) { trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); *statusp = RCU_KTHREAD_WAITING; return; -- 2.39.2

1 year, 9 months

1
0
0 0

[PATCH AUTOSEL 5.15] rcu: Mark rcu_cpu_kthread() accesses to ->rcu_cpu_has_work

by Sasha Levin

From: "Paul E. McKenney" <paulmck(a)kernel.org> [ Upstream commit a24c1aab652ebacf9ea62470a166514174c96fe1 ] The rcu_data structure's ->rcu_cpu_has_work field can be modified by any CPU attempting to wake up the rcuc kthread. Therefore, this commit marks accesses to this field from the rcu_cpu_kthread() function. This data race was reported by KCSAN. Not appropriate for backporting due to failure being unlikely. Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/rcu/tree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index df016f6d0662c..48f3e90c5de53 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2826,12 +2826,12 @@ static void rcu_cpu_kthread(unsigned int cpu) *statusp = RCU_KTHREAD_RUNNING; local_irq_disable(); work = *workp; - *workp = 0; + WRITE_ONCE(*workp, 0); local_irq_enable(); if (work) rcu_core(); local_bh_enable(); - if (*workp == 0) { + if (!READ_ONCE(*workp)) { trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); *statusp = RCU_KTHREAD_WAITING; return; -- 2.39.2

1 year, 9 months

1
0
0 0

[PATCH AUTOSEL 6.1 1/3] rcu-tasks: Avoid pr_info() with spin lock in cblist_init_generic()

by Sasha Levin

From: Shigeru Yoshida <syoshida(a)redhat.com> [ Upstream commit 5fc8cbe4cf0fd34ded8045c385790c3bf04f6785 ] pr_info() is called with rtp->cbs_gbl_lock spin lock locked. Because pr_info() calls printk() that might sleep, this will result in BUG like below: [ 0.206455] cblist_init_generic: Setting adjustable number of callback queues. [ 0.206463] [ 0.206464] ============================= [ 0.206464] [ BUG: Invalid wait context ] [ 0.206465] 5.19.0-00428-g9de1f9c8ca51 #5 Not tainted [ 0.206466] ----------------------------- [ 0.206466] swapper/0/1 is trying to lock: [ 0.206467] ffffffffa0167a58 (&port_lock_key){....}-{3:3}, at: serial8250_console_write+0x327/0x4a0 [ 0.206473] other info that might help us debug this: [ 0.206473] context-{5:5} [ 0.206474] 3 locks held by swapper/0/1: [ 0.206474] #0: ffffffff9eb597e0 (rcu_tasks.cbs_gbl_lock){....}-{2:2}, at: cblist_init_generic.constprop.0+0x14/0x1f0 [ 0.206478] #1: ffffffff9eb579c0 (console_lock){+.+.}-{0:0}, at: _printk+0x63/0x7e [ 0.206482] #2: ffffffff9ea77780 (console_owner){....}-{0:0}, at: console_emit_next_record.constprop.0+0x111/0x330 [ 0.206485] stack backtrace: [ 0.206486] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.19.0-00428-g9de1f9c8ca51 #5 [ 0.206488] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.fc36 04/01/2014 [ 0.206489] Call Trace: [ 0.206490] <TASK> [ 0.206491] dump_stack_lvl+0x6a/0x9f [ 0.206493] __lock_acquire.cold+0x2d7/0x2fe [ 0.206496] ? stack_trace_save+0x46/0x70 [ 0.206497] lock_acquire+0xd1/0x2f0 [ 0.206499] ? serial8250_console_write+0x327/0x4a0 [ 0.206500] ? __lock_acquire+0x5c7/0x2720 [ 0.206502] _raw_spin_lock_irqsave+0x3d/0x90 [ 0.206504] ? serial8250_console_write+0x327/0x4a0 [ 0.206506] serial8250_console_write+0x327/0x4a0 [ 0.206508] console_emit_next_record.constprop.0+0x180/0x330 [ 0.206511] console_unlock+0xf7/0x1f0 [ 0.206512] vprintk_emit+0xf7/0x330 [ 0.206514] _printk+0x63/0x7e [ 0.206516] cblist_init_generic.constprop.0.cold+0x24/0x32 [ 0.206518] rcu_init_tasks_generic+0x5/0xd9 [ 0.206522] kernel_init_freeable+0x15b/0x2a2 [ 0.206523] ? rest_init+0x160/0x160 [ 0.206526] kernel_init+0x11/0x120 [ 0.206527] ret_from_fork+0x1f/0x30 [ 0.206530] </TASK> [ 0.207018] cblist_init_generic: Setting shift to 1 and lim to 1. This patch moves pr_info() so that it is called without rtp->cbs_gbl_lock locked. Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Tested-by: "Zhang, Qiang1" <qiang1.zhang(a)intel.com> Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/rcu/tasks.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index c8409601fec38..74da2ecfbfa65 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -233,7 +233,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp) if (rcu_task_enqueue_lim < 0) { rcu_task_enqueue_lim = 1; rcu_task_cb_adjust = true; - pr_info("%s: Setting adjustable number of callback queues.\n", __func__); } else if (rcu_task_enqueue_lim == 0) { rcu_task_enqueue_lim = 1; } @@ -264,6 +263,10 @@ static void cblist_init_generic(struct rcu_tasks *rtp) raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled. } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); + + if (rcu_task_cb_adjust) + pr_info("%s: Setting adjustable number of callback queues.\n", __func__); + pr_info("%s: Setting shift to %d and lim to %d.\n", __func__, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim)); } -- 2.39.2

1 year, 9 months

1
2
0 0

[PATCH AUTOSEL 6.3 1/3] rcu-tasks: Avoid pr_info() with spin lock in cblist_init_generic()

by Sasha Levin

From: Shigeru Yoshida <syoshida(a)redhat.com> [ Upstream commit 5fc8cbe4cf0fd34ded8045c385790c3bf04f6785 ] pr_info() is called with rtp->cbs_gbl_lock spin lock locked. Because pr_info() calls printk() that might sleep, this will result in BUG like below: [ 0.206455] cblist_init_generic: Setting adjustable number of callback queues. [ 0.206463] [ 0.206464] ============================= [ 0.206464] [ BUG: Invalid wait context ] [ 0.206465] 5.19.0-00428-g9de1f9c8ca51 #5 Not tainted [ 0.206466] ----------------------------- [ 0.206466] swapper/0/1 is trying to lock: [ 0.206467] ffffffffa0167a58 (&port_lock_key){....}-{3:3}, at: serial8250_console_write+0x327/0x4a0 [ 0.206473] other info that might help us debug this: [ 0.206473] context-{5:5} [ 0.206474] 3 locks held by swapper/0/1: [ 0.206474] #0: ffffffff9eb597e0 (rcu_tasks.cbs_gbl_lock){....}-{2:2}, at: cblist_init_generic.constprop.0+0x14/0x1f0 [ 0.206478] #1: ffffffff9eb579c0 (console_lock){+.+.}-{0:0}, at: _printk+0x63/0x7e [ 0.206482] #2: ffffffff9ea77780 (console_owner){....}-{0:0}, at: console_emit_next_record.constprop.0+0x111/0x330 [ 0.206485] stack backtrace: [ 0.206486] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.19.0-00428-g9de1f9c8ca51 #5 [ 0.206488] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.fc36 04/01/2014 [ 0.206489] Call Trace: [ 0.206490] <TASK> [ 0.206491] dump_stack_lvl+0x6a/0x9f [ 0.206493] __lock_acquire.cold+0x2d7/0x2fe [ 0.206496] ? stack_trace_save+0x46/0x70 [ 0.206497] lock_acquire+0xd1/0x2f0 [ 0.206499] ? serial8250_console_write+0x327/0x4a0 [ 0.206500] ? __lock_acquire+0x5c7/0x2720 [ 0.206502] _raw_spin_lock_irqsave+0x3d/0x90 [ 0.206504] ? serial8250_console_write+0x327/0x4a0 [ 0.206506] serial8250_console_write+0x327/0x4a0 [ 0.206508] console_emit_next_record.constprop.0+0x180/0x330 [ 0.206511] console_unlock+0xf7/0x1f0 [ 0.206512] vprintk_emit+0xf7/0x330 [ 0.206514] _printk+0x63/0x7e [ 0.206516] cblist_init_generic.constprop.0.cold+0x24/0x32 [ 0.206518] rcu_init_tasks_generic+0x5/0xd9 [ 0.206522] kernel_init_freeable+0x15b/0x2a2 [ 0.206523] ? rest_init+0x160/0x160 [ 0.206526] kernel_init+0x11/0x120 [ 0.206527] ret_from_fork+0x1f/0x30 [ 0.206530] </TASK> [ 0.207018] cblist_init_generic: Setting shift to 1 and lim to 1. This patch moves pr_info() so that it is called without rtp->cbs_gbl_lock locked. Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Tested-by: "Zhang, Qiang1" <qiang1.zhang(a)intel.com> Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/rcu/tasks.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index bfb5e1549f2b2..e5cadc3d515af 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -233,7 +233,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp) if (rcu_task_enqueue_lim < 0) { rcu_task_enqueue_lim = 1; rcu_task_cb_adjust = true; - pr_info("%s: Setting adjustable number of callback queues.\n", __func__); } else if (rcu_task_enqueue_lim == 0) { rcu_task_enqueue_lim = 1; } @@ -264,6 +263,10 @@ static void cblist_init_generic(struct rcu_tasks *rtp) raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled. } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); + + if (rcu_task_cb_adjust) + pr_info("%s: Setting adjustable number of callback queues.\n", __func__); + pr_info("%s: Setting shift to %d and lim to %d.\n", __func__, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim)); } -- 2.39.2

1 year, 9 months

1
2
0 0

[PATCH AUTOSEL 6.4 1/4] rcu-tasks: Avoid pr_info() with spin lock in cblist_init_generic()

by Sasha Levin

From: Shigeru Yoshida <syoshida(a)redhat.com> [ Upstream commit 5fc8cbe4cf0fd34ded8045c385790c3bf04f6785 ] pr_info() is called with rtp->cbs_gbl_lock spin lock locked. Because pr_info() calls printk() that might sleep, this will result in BUG like below: [ 0.206455] cblist_init_generic: Setting adjustable number of callback queues. [ 0.206463] [ 0.206464] ============================= [ 0.206464] [ BUG: Invalid wait context ] [ 0.206465] 5.19.0-00428-g9de1f9c8ca51 #5 Not tainted [ 0.206466] ----------------------------- [ 0.206466] swapper/0/1 is trying to lock: [ 0.206467] ffffffffa0167a58 (&port_lock_key){....}-{3:3}, at: serial8250_console_write+0x327/0x4a0 [ 0.206473] other info that might help us debug this: [ 0.206473] context-{5:5} [ 0.206474] 3 locks held by swapper/0/1: [ 0.206474] #0: ffffffff9eb597e0 (rcu_tasks.cbs_gbl_lock){....}-{2:2}, at: cblist_init_generic.constprop.0+0x14/0x1f0 [ 0.206478] #1: ffffffff9eb579c0 (console_lock){+.+.}-{0:0}, at: _printk+0x63/0x7e [ 0.206482] #2: ffffffff9ea77780 (console_owner){....}-{0:0}, at: console_emit_next_record.constprop.0+0x111/0x330 [ 0.206485] stack backtrace: [ 0.206486] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.19.0-00428-g9de1f9c8ca51 #5 [ 0.206488] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.fc36 04/01/2014 [ 0.206489] Call Trace: [ 0.206490] <TASK> [ 0.206491] dump_stack_lvl+0x6a/0x9f [ 0.206493] __lock_acquire.cold+0x2d7/0x2fe [ 0.206496] ? stack_trace_save+0x46/0x70 [ 0.206497] lock_acquire+0xd1/0x2f0 [ 0.206499] ? serial8250_console_write+0x327/0x4a0 [ 0.206500] ? __lock_acquire+0x5c7/0x2720 [ 0.206502] _raw_spin_lock_irqsave+0x3d/0x90 [ 0.206504] ? serial8250_console_write+0x327/0x4a0 [ 0.206506] serial8250_console_write+0x327/0x4a0 [ 0.206508] console_emit_next_record.constprop.0+0x180/0x330 [ 0.206511] console_unlock+0xf7/0x1f0 [ 0.206512] vprintk_emit+0xf7/0x330 [ 0.206514] _printk+0x63/0x7e [ 0.206516] cblist_init_generic.constprop.0.cold+0x24/0x32 [ 0.206518] rcu_init_tasks_generic+0x5/0xd9 [ 0.206522] kernel_init_freeable+0x15b/0x2a2 [ 0.206523] ? rest_init+0x160/0x160 [ 0.206526] kernel_init+0x11/0x120 [ 0.206527] ret_from_fork+0x1f/0x30 [ 0.206530] </TASK> [ 0.207018] cblist_init_generic: Setting shift to 1 and lim to 1. This patch moves pr_info() so that it is called without rtp->cbs_gbl_lock locked. Signed-off-by: Shigeru Yoshida <syoshida(a)redhat.com> Tested-by: "Zhang, Qiang1" <qiang1.zhang(a)intel.com> Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/rcu/tasks.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 5f4fc8184dd0b..65df1aaf0ce9b 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -241,7 +241,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp) if (rcu_task_enqueue_lim < 0) { rcu_task_enqueue_lim = 1; rcu_task_cb_adjust = true; - pr_info("%s: Setting adjustable number of callback queues.\n", __func__); } else if (rcu_task_enqueue_lim == 0) { rcu_task_enqueue_lim = 1; } @@ -272,6 +271,10 @@ static void cblist_init_generic(struct rcu_tasks *rtp) raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled. } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); + + if (rcu_task_cb_adjust) + pr_info("%s: Setting adjustable number of callback queues.\n", __func__); + pr_info("%s: Setting shift to %d and lim to %d.\n", __func__, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim)); } -- 2.39.2

1 year, 9 months

1
3
0 0

[PATCH AUTOSEL 5.4] arm64: mm: fix VA-range sanity check

by Sasha Levin

From: Mark Rutland <mark.rutland(a)arm.com> [ Upstream commit ab9b4008092c86dc12497af155a0901cc1156999 ] Both create_mapping_noalloc() and update_mapping_prot() sanity-check their 'virt' parameter, but the check itself doesn't make much sense. The condition used today appears to be a historical accident. The sanity-check condition: if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } ... can only be true for the KASAN shadow region or the module region, and there's no reason to exclude these specifically for creating and updateing mappings. When arm64 support was first upstreamed in commit: c1cc1552616d0f35 ("arm64: MMU initialisation") ... the condition was: if (virt < VMALLOC_START) { [ ... warning here ... ] return; } At the time, VMALLOC_START was the lowest kernel address, and this was checking whether 'virt' would be translated via TTBR1. Subsequently in commit: 14c127c957c1c607 ("arm64: mm: Flip kernel VA space") ... the condition was changed to: if ((virt >= VA_START) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } This appear to have been a thinko. The commit moved the linear map to the bottom of the kernel address space, with VMALLOC_START being at the halfway point. The old condition would warn for changes to the linear map below this, and at the time VA_START was the end of the linear map. Subsequently we cleaned up the naming of VA_START in commit: 77ad4ce69321abbe ("arm64: memory: rename VA_START to PAGE_END") ... keeping the erroneous condition as: if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } Correct the condition to check against the start of the TTBR1 address space, which is currently PAGE_OFFSET. This simplifies the logic, and more clearly matches the "outside kernel range" message in the warning. Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Cc: Russell King <linux(a)armlinux.org.uk> Cc: Steve Capper <steve.capper(a)arm.com> Cc: Will Deacon <will(a)kernel.org> Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> Link: https://lore.kernel.org/r/20230615102628.1052103-1-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- arch/arm64/mm/mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 5cf575f23af28..8e934bb44f12e 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -399,7 +399,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift) static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { + if (virt < PAGE_OFFSET) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; @@ -426,7 +426,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, static void update_mapping_prot(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { + if (virt < PAGE_OFFSET) { pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; -- 2.39.2

1 year, 9 months

1
0
0 0

[PATCH AUTOSEL 5.10 1/5] ACPI: button: Add lid disable DMI quirk for Nextbook Ares 8A

by Sasha Levin

From: Hans de Goede <hdegoede(a)redhat.com> [ Upstream commit 4fd5556608bfa9c2bf276fc115ef04288331aded ] The LID0 device on the Nextbook Ares 8A tablet always reports lid closed causing userspace to suspend the device as soon as booting is complete. Add a DMI quirk to disable the broken lid functionality. Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/acpi/button.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 0d93a5ef4d071..4861aad1a9e93 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -82,6 +82,15 @@ static const struct dmi_system_id dmi_lid_quirks[] = { }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED, }, + { + /* Nextbook Ares 8A tablet, _LID device always reports lid closed */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "CherryTrail"), + DMI_MATCH(DMI_BIOS_VERSION, "M882"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED, + }, { /* * Medion Akoya E2215T, notification of the LID device only -- 2.39.2

1 year, 9 months

1
4
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2023