From: Pan Bian bianpan2016@163.com

commit cf3c46631e1637582f517a574c77cd6c05793817 upstream.

Put the device node dn before return error code on failure path.

Fixes: 461cd1b03e32 ("net: dsa: bcm_sf2: Register our slave MDIO bus") Signed-off-by: Pan Bian bianpan2016@163.com Link: https://lore.kernel.org/r/20210121123343.26330-1-bianpan2016@163.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/bcm_sf2.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -540,15 +540,19 @@ static int bcm_sf2_mdio_register(struct /* Find our integrated MDIO bus node */ dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio"); priv->master_mii_bus = of_mdio_find_bus(dn); - if (!priv->master_mii_bus) + if (!priv->master_mii_bus) { + of_node_put(dn); return -EPROBE_DEFER; + }

get_device(&priv->master_mii_bus->dev); priv->master_mii_dn = dn;

priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev); - if (!priv->slave_mii_bus) + if (!priv->slave_mii_bus) { + of_node_put(dn); return -ENOMEM; + }

priv->slave_mii_bus->priv = priv; priv->slave_mii_bus->name = "sf2 slave mii";

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

commit 81b704d3e4674e09781d331df73d76675d5ad8cb upstream.

Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time.

Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already.

For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone.

While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here.

[This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.]

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman stephen.berman@gmx.net Diagnosed-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Tested-by: Stephen Berman stephen.berman@gmx.net Cc: All applicable stable@vger.kernel.org [bigeasy: Backported to v5.4.y] Signed-off-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/acpi/thermal.c | 55 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 17 deletions(-)

--- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -188,6 +188,8 @@ struct acpi_thermal { int tz_enabled; int kelvin_offset; struct work_struct thermal_check_work; + struct mutex thermal_check_lock; + refcount_t thermal_check_count; };

/* -------------------------------------------------------------------------- @@ -513,17 +515,6 @@ static int acpi_thermal_get_trip_points( return 0; }

-static void acpi_thermal_check(void *data) -{ - struct acpi_thermal *tz = data; - - if (!tz->tz_enabled) - return; - - thermal_zone_device_update(tz->thermal_zone, - THERMAL_EVENT_UNSPECIFIED); -} - /* sys I/F for generic thermal sysfs support */

static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp) @@ -557,6 +548,8 @@ static int thermal_get_mode(struct therm return 0; }

+static void acpi_thermal_check_fn(struct work_struct *work); + static int thermal_set_mode(struct thermal_zone_device *thermal, enum thermal_device_mode mode) { @@ -582,7 +575,7 @@ static int thermal_set_mode(struct therm ACPI_DEBUG_PRINT((ACPI_DB_INFO, "%s kernel ACPI thermal control\n", tz->tz_enabled ? "Enable" : "Disable")); - acpi_thermal_check(tz); + acpi_thermal_check_fn(&tz->thermal_check_work); } return 0; } @@ -951,6 +944,12 @@ static void acpi_thermal_unregister_ther Driver Interface -------------------------------------------------------------------------- */

+static void acpi_queue_thermal_check(struct acpi_thermal *tz) +{ + if (!work_pending(&tz->thermal_check_work)) + queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); +} + static void acpi_thermal_notify(struct acpi_device *device, u32 event) { struct acpi_thermal *tz = acpi_driver_data(device); @@ -961,17 +960,17 @@ static void acpi_thermal_notify(struct a

switch (event) { case ACPI_THERMAL_NOTIFY_TEMPERATURE: - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); break; case ACPI_THERMAL_NOTIFY_THRESHOLDS: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_THRESHOLDS); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; case ACPI_THERMAL_NOTIFY_DEVICES: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_DEVICES); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; @@ -1071,7 +1070,27 @@ static void acpi_thermal_check_fn(struct { struct acpi_thermal *tz = container_of(work, struct acpi_thermal, thermal_check_work); - acpi_thermal_check(tz); + + if (!tz->tz_enabled) + return; + /* + * In general, it is not sufficient to check the pending bit, because + * subsequent instances of this function may be queued after one of them + * has started running (e.g. if _TMP sleeps). Avoid bailing out if just + * one of them is running, though, because it may have done the actual + * check some time ago, so allow at least one of them to block on the + * mutex while another one is running the update. + */ + if (!refcount_dec_not_one(&tz->thermal_check_count)) + return; + + mutex_lock(&tz->thermal_check_lock); + + thermal_zone_device_update(tz->thermal_zone, THERMAL_EVENT_UNSPECIFIED); + + refcount_inc(&tz->thermal_check_count); + + mutex_unlock(&tz->thermal_check_lock); }

static int acpi_thermal_add(struct acpi_device *device) @@ -1103,6 +1122,8 @@ static int acpi_thermal_add(struct acpi_ if (result) goto free_memory;

+ refcount_set(&tz->thermal_check_count, 3); + mutex_init(&tz->thermal_check_lock); INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);

pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device), @@ -1168,7 +1189,7 @@ static int acpi_thermal_resume(struct de tz->state.active |= tz->trips.active[i].flags.enabled; }

- queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); + acpi_queue_thermal_check(tz);

return AE_OK; }

From: Eric Dumazet edumazet@google.com

commit dd5e073381f2ada3630f36be42833c6e9c78b75e upstream

syzbot report reminded us that very big ewma_log were supported in the past, even if they made litle sense.

tc qdisc replace dev xxx root est 1sec 131072sec ...

While fixing the bug, also add boundary checks for ewma_log, in line with range supported by iproute2.

UBSAN: shift-out-of-bounds in net/core/gen_estimator.c:83:38 shift exponent -1 is negative CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.10.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:395 est_timer.cold+0xbb/0x12d net/core/gen_estimator.c:83 call_timer_fn+0x1a5/0x710 kernel/time/timer.c:1417 expire_timers kernel/time/timer.c:1462 [inline] __run_timers.part.0+0x692/0xa80 kernel/time/timer.c:1731 __run_timers kernel/time/timer.c:1712 [inline] run_timer_softirq+0xb3/0x1d0 kernel/time/timer.c:1744 __do_softirq+0x2bc/0xa77 kernel/softirq.c:343 asm_call_irq_on_stack+0xf/0x20 </IRQ> __run_on_irqstack arch/x86/include/asm/irq_stack.h:26 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:77 [inline] do_softirq_own_stack+0xaa/0xd0 arch/x86/kernel/irq_64.c:77 invoke_softirq kernel/softirq.c:226 [inline] __irq_exit_rcu+0x17f/0x200 kernel/softirq.c:420 irq_exit_rcu+0x5/0x20 kernel/softirq.c:432 sysvec_apic_timer_interrupt+0x4d/0x100 arch/x86/kernel/apic/apic.c:1096 asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:628 RIP: 0010:native_save_fl arch/x86/include/asm/irqflags.h:29 [inline] RIP: 0010:arch_local_save_flags arch/x86/include/asm/irqflags.h:79 [inline] RIP: 0010:arch_irqs_disabled arch/x86/include/asm/irqflags.h:169 [inline] RIP: 0010:acpi_safe_halt drivers/acpi/processor_idle.c:111 [inline] RIP: 0010:acpi_idle_do_entry+0x1c9/0x250 drivers/acpi/processor_idle.c:516

Fixes: 1c0d32fde5bd ("net_sched: gen_estimator: complete rewrite of rate estimators") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Link: https://lore.kernel.org/r/20210114181929.1717985-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org [sudip: adjust context] Signed-off-by: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/gen_estimator.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

--- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -84,11 +84,11 @@ static void est_timer(unsigned long arg) u64 rate, brate;

est_fetch_counters(est, &b); - brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log); - brate -= (est->avbps >> est->ewma_log); + brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); + brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log);

- rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log); - rate -= (est->avpps >> est->ewma_log); + rate = (u64)(b.packets - est->last_packets) << (10 - est->intvl_log); + rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log);

write_seqcount_begin(&est->seq); est->avbps += brate; @@ -147,6 +147,9 @@ int gen_new_estimator(struct gnet_stats_ if (parm->interval < -2 || parm->interval > 3) return -EINVAL;

+ if (parm->ewma_log == 0 || parm->ewma_log >= 31) + return -EINVAL; + est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS;

From: "Rafael J. Wysocki" rafael.j.wysocki@intel.com

commit 3d1cf435e201d1fd63e4346b141881aed086effd upstream

If the device passed as the target (second argument) to device_is_dependent() is not completely registered (that is, it has been initialized, but not added yet), but the parent pointer of it is set, it may be missing from the list of the parent's children and device_for_each_child() called by device_is_dependent() cannot be relied on to catch that dependency.

For this reason, modify device_is_dependent() to check the ancestors of the target device by following its parent pointer in addition to the device_for_each_child() walk.

Fixes: 9ed9895370ae ("driver core: Functional dependencies tracking support") Reported-by: Stephan Gerhold stephan@gerhold.net Tested-by: Stephan Gerhold stephan@gerhold.net Reviewed-by: Saravana Kannan saravanak@google.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Link: https://lore.kernel.org/r/17705994.d592GUb2YH@kreacher Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/base/core.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)

--- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -96,6 +96,16 @@ void device_links_read_unlock(int not_us } #endif /* !CONFIG_SRCU */

+static bool device_is_ancestor(struct device *dev, struct device *target) +{ + while (target->parent) { + target = target->parent; + if (dev == target) + return true; + } + return false; +} + /** * device_is_dependent - Check if one device depends on another one * @dev: Device to check dependencies for. @@ -109,7 +119,12 @@ static int device_is_dependent(struct de struct device_link *link; int ret;

- if (dev == target) + /* + * The "ancestors" check is needed to catch the case when the target + * device has not been completely initialized yet and it is still + * missing from the list of children of its parent device. + */ + if (dev == target || device_is_ancestor(dev, target)) return 1;

ret = device_for_each_child(dev, target, device_is_dependent);

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 66a425011c61e71560c234492d204e83cfb73d1d ]

When the compiler choses to not inline the trivial MSR helpers:

vmlinux.o: warning: objtool: __sev_es_nmi_complete()+0xce: call to __wrmsr.constprop.14() leaves .noinstr.text section

Reported-by: Randy Dunlap rdunlap@infradead.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Randy Dunlap rdunlap@infradead.org # build-tested Link: https://lore.kernel.org/r/X/bf3gV+BW7kGEsB@hirez.programming.kicks-ass.net Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/msr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 30df295f6d94c..18f9a9b7280bd 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -88,7 +88,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high);

@@ -100,7 +100,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); }

-static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n"

From: Javed Hasan jhasan@marvell.com

[ Upstream commit b2b0f16fa65e910a3ec8771206bb49ee87a54ac5 ]

A race condition exists between the response handler getting called because of exchange_mgr_reset() (which clears out all the active XIDs) and the response we get via an interrupt.

Sequence of events:

rport ba0200: Port timeout, state PLOGI rport ba0200: Port entered PLOGI state from PLOGI state xid 1052: Exchange timer armed : 20000 msecs  xid timer armed here rport ba0200: Received LOGO request while in state PLOGI rport ba0200: Delete port rport ba0200: work event 3 rport ba0200: lld callback ev 3 bnx2fc: rport_event_hdlr: event = 3, port_id = 0xba0200 bnx2fc: ba0200 - rport not created Yet!! /* Here we reset any outstanding exchanges before freeing rport using the exch_mgr_reset() */ xid 1052: Exchange timer canceled /* Here we got two responses for one xid */ xid 1052: invoking resp(), esb 20000000 state 3 xid 1052: invoking resp(), esb 20000000 state 3 xid 1052: fc_rport_plogi_resp() : ep->resp_active 2 xid 1052: fc_rport_plogi_resp() : ep->resp_active 2

Skip the response if the exchange is already completed.

Link: https://lore.kernel.org/r/20201215194731.2326-1-jhasan@marvell.com Signed-off-by: Javed Hasan jhasan@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/libfc/fc_exch.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 6ba257cbc6d94..384458d1f73c3 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -1631,8 +1631,13 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) rc = fc_exch_done_locked(ep); WARN_ON(fc_seq_exch(sp) != ep); spin_unlock_bh(&ep->ex_lock); - if (!rc) + if (!rc) { fc_exch_delete(ep); + } else { + FC_EXCH_DBG(ep, "ep is completed already," + "hence skip calling the resp\n"); + goto skip_resp; + } }

/* @@ -1651,6 +1656,7 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) if (!fc_invoke_resp(ep, sp, fp)) fc_frame_free(fp);

+skip_resp: fc_exch_release(ep); return; rel: @@ -1907,10 +1913,16 @@ static void fc_exch_reset(struct fc_exch *ep)

fc_exch_hold(ep);

- if (!rc) + if (!rc) { fc_exch_delete(ep); + } else { + FC_EXCH_DBG(ep, "ep is completed already," + "hence skip calling the resp\n"); + goto skip_resp; + }

fc_invoke_resp(ep, sp, ERR_PTR(-FC_EX_CLOSED)); +skip_resp: fc_seq_set_resp(sp, NULL, ep->arg); fc_exch_release(ep); }

From: Brian King brking@linux.vnet.ibm.com

[ Upstream commit 764907293edc1af7ac857389af9dc858944f53dc ]

While testing live partition mobility, we have observed occasional crashes of the Linux partition. What we've seen is that during the live migration, for specific configurations with large amounts of memory, slow network links, and workloads that are changing memory a lot, the partition can end up being suspended for 30 seconds or longer. This resulted in the following scenario:

CPU 0 CPU 1 ------------------------------- ---------------------------------- scsi_queue_rq migration_store -> blk_mq_start_request -> rtas_ibm_suspend_me -> blk_add_timer -> on_each_cpu(rtas_percpu_suspend_me _______________________________________V | V -> IPI from CPU 1 -> rtas_percpu_suspend_me -> __rtas_suspend_last_cpu

-- Linux partition suspended for > 30 seconds -- -> for_each_online_cpu(cpu) plpar_hcall_norets(H_PROD -> scsi_dispatch_cmd -> scsi_times_out -> scsi_abort_command -> queue_delayed_work -> ibmvfc_queuecommand_lck -> ibmvfc_send_event -> ibmvfc_send_crq - returns H_CLOSED <- returns SCSI_MLQUEUE_HOST_BUSY -> __blk_mq_requeue_request

-> scmd_eh_abort_handler -> scsi_try_to_abort_cmd - returns SUCCESS -> scsi_queue_insert

Normally, the SCMD_STATE_COMPLETE bit would protect against the command completion and the timeout, but that doesn't work here, since we don't check that at all in the SCSI_MLQUEUE_HOST_BUSY path.

In this case we end up calling scsi_queue_insert on a request that has already been queued, or possibly even freed, and we crash.

The patch below simply increases the default I/O timeout to avoid this race condition. This is also the timeout value that nearly all IBM SAN storage recommends setting as the default value.

Link: https://lore.kernel.org/r/1610463998-19791-1-git-send-email-brking@linux.vne... Signed-off-by: Brian King brking@linux.vnet.ibm.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/ibmvscsi/ibmvfc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index dbacd9830d3df..460014ded14de 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -2891,8 +2891,10 @@ static int ibmvfc_slave_configure(struct scsi_device *sdev) unsigned long flags = 0;

spin_lock_irqsave(shost->host_lock, flags); - if (sdev->type == TYPE_DISK) + if (sdev->type == TYPE_DISK) { sdev->allow_restart = 1; + blk_queue_rq_timeout(sdev->request_queue, 120 * HZ); + } spin_unlock_irqrestore(shost->host_lock, flags); return 0; }

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit ac687e6e8c26181a33270efd1a2e2241377924b0 ]

There is a need to distinguish geniune per-cpu kthreads from kthreads that happen to have a single CPU affinity.

Geniune per-cpu kthreads are kthreads that are CPU affine for correctness, these will obviously have PF_KTHREAD set, but must also have PF_NO_SETAFFINITY set, lest userspace modify their affinity and ruins things.

However, these two things are not sufficient, PF_NO_SETAFFINITY is also set on other tasks that have their affinities controlled through other means, like for instance workqueues.

Therefore another bit is needed; it turns out kthread_create_per_cpu() already has such a bit: KTHREAD_IS_PER_CPU, which is used to make kthread_park()/kthread_unpark() work correctly.

Expose this flag and remove the implicit setting of it from kthread_create_on_cpu(); the io_uring usage of it seems dubious at best.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Valentin Schneider valentin.schneider@arm.com Tested-by: Valentin Schneider valentin.schneider@arm.com Link: https://lkml.kernel.org/r/20210121103506.557620262@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/kthread.h | 3 +++ kernel/kthread.c | 27 ++++++++++++++++++++++++++- kernel/smpboot.c | 1 + 3 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 4e26609c77d41..eb305353f20fa 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -31,6 +31,9 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt);

+void kthread_set_per_cpu(struct task_struct *k, int cpu); +bool kthread_is_per_cpu(struct task_struct *k); + /** * kthread_run - create and wake a thread. * @threadfn: the function to run until signal_pending(current). diff --git a/kernel/kthread.c b/kernel/kthread.c index bd58765d75e76..fd6f9322312aa 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -433,11 +433,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; }

+void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *k) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 5043e7433f4b1..eeb7f8e9cce37 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -187,6 +187,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + kthread_set_per_cpu(tsk, cpu); /* * Park the thread so that it could start right on the CPU * when it is available.