user/sven/linux.git/kernel/rcu, branch v6.6.17

rcu: Defer RCU kthreads wakeup when CPU is dying

2024-02-01T00:19:03Z

[ Upstream commit e787644caf7628ad3269c1fbd321c3255cf51710 ] When the CPU goes idle for the last time during the CPU down hotplug process, RCU reports a final quiescent state for the current CPU. If this quiescent state propagates up to the top, some tasks may then be woken up to complete the grace period: the main grace period kthread and/or the expedited main workqueue (or kworker). If those kthreads have a SCHED_FIFO policy, the wake up can indirectly arm the RT bandwith timer to the local offline CPU. Since this happens after hrtimers have been migrated at CPUHP_AP_HRTIMERS_DYING stage, the timer gets ignored. Therefore if the RCU kthreads are waiting for RT bandwidth to be available, they may never be actually scheduled. This triggers TREE03 rcutorture hangs: rcu: INFO: rcu_preempt self-detected stall on CPU rcu: 4-...!: (1 GPs behind) idle=9874/1/0x4000000000000000 softirq=0/0 fqs=20 rcuc=21071 jiffies(starved) rcu: (t=21035 jiffies g=938281 q=40787 ncpus=6) rcu: rcu_preempt kthread starved for 20964 jiffies! g938281 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x0 ->cpu=0 rcu: Unless rcu_preempt kthread gets sufficient CPU time, OOM is now expected behavior. rcu: RCU grace-period kthread stack dump: task:rcu_preempt state:R running task stack:14896 pid:14 tgid:14 ppid:2 flags:0x00004000 Call Trace: __schedule+0x2eb/0xa80 schedule+0x1f/0x90 schedule_timeout+0x163/0x270 ? __pfx_process_timeout+0x10/0x10 rcu_gp_fqs_loop+0x37c/0x5b0 ? __pfx_rcu_gp_kthread+0x10/0x10 rcu_gp_kthread+0x17c/0x200 kthread+0xde/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2b/0x40 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 The situation can't be solved with just unpinning the timer. The hrtimer infrastructure and the nohz heuristics involved in finding the best remote target for an unpinned timer would then also need to handle enqueues from an offline CPU in the most horrendous way. So fix this on the RCU side instead and defer the wake up to an online CPU if it's too late for the local one. Reported-by: Paul E. McKenney Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier") Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay (AMD) Signed-off-by: Sasha Levin

rcu/tasks-trace: Handle new PF_IDLE semantics

2024-01-10T16:16:56Z

[ Upstream commit a80712b9cc7e57830260ec5e1feb9cdb59e1da2f ] The commit: cff9b2332ab7 ("kernel/sched: Modify initial boot task idle setup") has changed the semantics of what is to be considered an idle task in such a way that the idle task of an offline CPU may not carry the PF_IDLE flag anymore. However RCU-tasks-trace tests the opposite assertion, still assuming that idle tasks carry the PF_IDLE flag during their whole lifecycle. Remove this assumption to avoid spurious warnings but keep the initial test verifying that the idle task is the current task on any offline CPU. Reported-by: Naresh Kamboju Fixes: cff9b2332ab7 ("kernel/sched: Modify initial boot task idle setup") Suggested-by: Joel Fernandes Suggested-by: "Paul E. McKenney" Acked-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Sasha Levin

rcu/tasks: Handle new PF_IDLE semantics

2024-01-10T16:16:56Z

[ Upstream commit 9715ed501b585d47444865071674c961c0cc0020 ] The commit: cff9b2332ab7 ("kernel/sched: Modify initial boot task idle setup") has changed the semantics of what is to be considered an idle task in such a way that CPU boot code preceding the actual idle loop is excluded from it. This has however introduced new potential RCU-tasks stalls when either: 1) Grace period is started before init/0 had a chance to set PF_IDLE, keeping it stuck in the holdout list until idle ever schedules. 2) Grace period is started when some possible CPUs have never been online, keeping their idle tasks stuck in the holdout list until the CPU ever boots up. 3) Similar to 1) but with secondary CPUs: Grace period is started concurrently with secondary CPU booting, putting its idle task in the holdout list because PF_IDLE isn't yet observed on it. It stays then stuck in the holdout list until that CPU ever schedules. The effect is mitigated here by the hotplug AP thread that must run to bring the CPU up. Fix this with handling the new semantics of PF_IDLE, keeping in mind that it may or may not be set on an idle task. Take advantage of that to strengthen the coverage of an RCU-tasks quiescent state within an idle task, excluding the CPU boot code from it. Only the code running within the idle loop is now a quiescent state, along with offline CPUs. Fixes: cff9b2332ab7 ("kernel/sched: Modify initial boot task idle setup") Suggested-by: Joel Fernandes Suggested-by: "Paul E. McKenney" Acked-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Sasha Levin

rcu: Introduce rcu_cpu_online()

2024-01-10T16:16:56Z

[ Upstream commit 2be4686d866ad5896f2bb94d82fe892197aea9c7 ] Export the RCU point of view as to when a CPU is considered offline (ie: when does RCU consider that a CPU is sufficiently down in the hotplug process to not feature any possible read side). This will be used by RCU-tasks whose vision of an offline CPU should reasonably match the one of RCU core. Fixes: cff9b2332ab7 ("kernel/sched: Modify initial boot task idle setup") Acked-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Sasha Levin

rcu: Break rcu_node_0 --> &rq->__lock order

2024-01-10T16:16:56Z

[ Upstream commit 85d68222ddc5f4522e456d97d201166acb50f716 ] Commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()") added a kfree() call to free any user provided affinity mask, if present. It was changed later to use kfree_rcu() in commit 9a5418bc48ba ("sched/core: Use kfree_rcu() in do_set_cpus_allowed()") to avoid a circular locking dependency problem. It turns out that even kfree_rcu() isn't safe for avoiding circular locking problem. As reported by kernel test robot, the following circular locking dependency now exists: &rdp->nocb_lock --> rcu_node_0 --> &rq->__lock Solve this by breaking the rcu_node_0 --> &rq->__lock chain by moving the resched_cpu() out from under rcu_node lock. [peterz: heavily borrowed from Waiman's Changelog] [paulmck: applied Z qiang feedback] Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()") Reported-by: kernel test robot Acked-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/oe-lkp/202310302207.a25f1a30-oliver.sang@intel.com Signed-off-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Sasha Levin

rcu: kmemleak: Ignore kmemleak false positives when RCU-freeing objects

2023-11-28T17:20:02Z

commit 5f98fd034ca6fd1ab8c91a3488968a0e9caaabf6 upstream. Since the actual slab freeing is deferred when calling kvfree_rcu(), so is the kmemleak_free() callback informing kmemleak of the object deletion. From the perspective of the kvfree_rcu() caller, the object is freed and it may remove any references to it. Since kmemleak does not scan RCU internal data storing the pointer, it will report such objects as leaks during the grace period. Tell kmemleak to ignore such objects on the kvfree_call_rcu() path. Note that the tiny RCU implementation does not have such issue since the objects can be tracked from the rcu_ctrlblk structure. Signed-off-by: Catalin Marinas Reported-by: Christoph Paasch Closes: https://lore.kernel.org/all/F903A825-F05F-4B77-A2B5-7356282FBA2C@apple.com/ Cc: Tested-by: Christoph Paasch Reviewed-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Frederic Weisbecker Signed-off-by: Greg Kroah-Hartman

rcu/tree: Defer setting of jiffies during stall reset

2023-11-28T17:20:02Z

commit b96e7a5fa0ba9cda32888e04f8f4bac42d49a7f8 upstream. There are instances where rcu_cpu_stall_reset() is called when jiffies did not get a chance to update for a long time. Before jiffies is updated, the CPU stall detector can go off triggering false-positives where a just-started grace period appears to be ages old. In the past, we disabled stall detection in rcu_cpu_stall_reset() however this got changed [1]. This is resulting in false-positives in KGDB usecase [2]. Fix this by deferring the update of jiffies to the third run of the FQS loop. This is more robust, as, even if rcu_cpu_stall_reset() is called just before jiffies is read, we would end up pushing out the jiffies read by 3 more FQS loops. Meanwhile the CPU stall detection will be delayed and we will not get any false positives. [1] https://lore.kernel.org/all/20210521155624.174524-2-senozhatsky@chromium.org/ [2] https://lore.kernel.org/all/20230814020045.51950-2-chenhuacai@loongson.cn/ Tested with rcutorture.cpu_stall option as well to verify stall behavior with/without patch. Tested-by: Huacai Chen Reported-by: Binbin Zhou Closes: https://lore.kernel.org/all/20230814020045.51950-2-chenhuacai@loongson.cn/ Suggested-by: Paul McKenney Cc: Sergey Senozhatsky Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: a80be428fbc1 ("rcu: Do not disable GP stall detection in rcu_cpu_stall_reset()") Signed-off-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Greg Kroah-Hartman

srcu: Only accelerate on enqueue time

2023-11-28T17:19:36Z

[ Upstream commit 8a77f38bcd28d3c22ab7dd8eff3f299d43c00411 ] Acceleration in SRCU happens on enqueue time for each new callback. This operation is expected not to fail and therefore any similar attempt from other places shouldn't find any remaining callbacks to accelerate. Moreover accelerations performed beyond enqueue time are error prone because rcu_seq_snap() then may return the snapshot for a new grace period that is not going to be started. Remove these dangerous and needless accelerations and introduce instead assertions reporting leaking unaccelerated callbacks beyond enqueue time. Co-developed-by: Yong He Signed-off-by: Yong He Co-developed-by: Joel Fernandes (Google) Signed-off-by: Joel Fernandes (Google) Co-developed-by: Neeraj upadhyay Signed-off-by: Neeraj upadhyay Reviewed-by: Like Xu Signed-off-by: Frederic Weisbecker Signed-off-by: Sasha Levin

srcu: Fix srcu_struct node grpmask overflow on 64-bit systems

2023-11-28T17:19:36Z

[ Upstream commit d8d5b7bf6f2105883bbd91bbd4d5b67e4e3dff71 ] The value of a bitwise expression 1 << (cpu - sdp->mynode->grplo) is subject to overflow due to a failure to cast operands to a larger data type before performing the bitwise operation. The maximum result of this subtraction is defined by the RCU_FANOUT_LEAF Kconfig option, which on 64-bit systems defaults to 16 (resulting in a maximum shift of 15), but which can be set up as high as 64 (resulting in a maximum shift of 63). A value of 31 can result in sign extension, resulting in 0xffffffff80000000 instead of the desired 0x80000000. A value of 32 or greater triggers undefined behavior per the C standard. This bug has not been known to cause issues because almost all kernels take the default CONFIG_RCU_FANOUT_LEAF=16. Furthermore, as long as a given compiler gives a deterministic non-zero result for 1<=32, the code correctly invokes all SRCU callbacks, albeit wasting CPU time along the way. This commit therefore substitutes the correct 1UL for the buggy 1. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Denis Arefev Reviewed-by: Mathieu Desnoyers Reviewed-by: Joel Fernandes (Google) Cc: David Laight Signed-off-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Sasha Levin

srcu: Fix callbacks acceleration mishandling

2023-11-20T10:58:53Z

[ Upstream commit 4a8e65b0c348e42107c64381e692e282900be361 ] SRCU callbacks acceleration might fail if the preceding callbacks advance also fails. This can happen when the following steps are met: 1) The RCU_WAIT_TAIL segment has callbacks (say for gp_num 8) and the RCU_NEXT_READY_TAIL also has callbacks (say for gp_num 12). 2) The grace period for RCU_WAIT_TAIL is observed as started but not yet completed so rcu_seq_current() returns 4 + SRCU_STATE_SCAN1 = 5. 3) This value is passed to rcu_segcblist_advance() which can't move any segment forward and fails. 4) srcu_gp_start_if_needed() still proceeds with callback acceleration. But then the call to rcu_seq_snap() observes the grace period for the RCU_WAIT_TAIL segment (gp_num 8) as completed and the subsequent one for the RCU_NEXT_READY_TAIL segment as started (ie: 8 + SRCU_STATE_SCAN1 = 9) so it returns a snapshot of the next grace period, which is 16. 5) The value of 16 is passed to rcu_segcblist_accelerate() but the freshly enqueued callback in RCU_NEXT_TAIL can't move to RCU_NEXT_READY_TAIL which already has callbacks for a previous grace period (gp_num = 12). So acceleration fails. 6) Note in all these steps, srcu_invoke_callbacks() hadn't had a chance to run srcu_invoke_callbacks(). Then some very bad outcome may happen if the following happens: 7) Some other CPU races and starts the grace period number 16 before the CPU handling previous steps had a chance. Therefore srcu_gp_start() isn't called on the latter sdp to fix the acceleration leak from previous steps with a new pair of call to advance/accelerate. 8) The grace period 16 completes and srcu_invoke_callbacks() is finally called. All the callbacks from previous grace periods (8 and 12) are correctly advanced and executed but callbacks in RCU_NEXT_READY_TAIL still remain. Then rcu_segcblist_accelerate() is called with a snaphot of 20. 9) Since nothing started the grace period number 20, callbacks stay unhandled. This has been reported in real load: [3144162.608392] INFO: task kworker/136:12:252684 blocked for more than 122 seconds. [3144162.615986] Tainted: G O K 5.4.203-1-tlinux4-0011.1 #1 [3144162.623053] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [3144162.631162] kworker/136:12 D 0 252684 2 0x90004000 [3144162.631189] Workqueue: kvm-irqfd-cleanup irqfd_shutdown [kvm] [3144162.631192] Call Trace: [3144162.631202] __schedule+0x2ee/0x660 [3144162.631206] schedule+0x33/0xa0 [3144162.631209] schedule_timeout+0x1c4/0x340 [3144162.631214] ? update_load_avg+0x82/0x660 [3144162.631217] ? raw_spin_rq_lock_nested+0x1f/0x30 [3144162.631218] wait_for_completion+0x119/0x180 [3144162.631220] ? wake_up_q+0x80/0x80 [3144162.631224] __synchronize_srcu.part.19+0x81/0xb0 [3144162.631226] ? __bpf_trace_rcu_utilization+0x10/0x10 [3144162.631227] synchronize_srcu+0x5f/0xc0 [3144162.631236] irqfd_shutdown+0x3c/0xb0 [kvm] [3144162.631239] ? __schedule+0x2f6/0x660 [3144162.631243] process_one_work+0x19a/0x3a0 [3144162.631244] worker_thread+0x37/0x3a0 [3144162.631247] kthread+0x117/0x140 [3144162.631247] ? process_one_work+0x3a0/0x3a0 [3144162.631248] ? __kthread_cancel_work+0x40/0x40 [3144162.631250] ret_from_fork+0x1f/0x30 Fix this with taking the snapshot for acceleration _before_ the read of the current grace period number. The only side effect of this solution is that callbacks advancing happen then _after_ the full barrier in rcu_seq_snap(). This is not a problem because that barrier only cares about: 1) Ordering accesses of the update side before call_srcu() so they don't bleed. 2) See all the accesses prior to the grace period of the current gp_num The only things callbacks advancing need to be ordered against are carried by snp locking. Reported-by: Yong He Co-developed-by:: Yong He Signed-off-by: Yong He Co-developed-by: Joel Fernandes (Google) Signed-off-by: Joel Fernandes (Google) Co-developed-by: Neeraj upadhyay Signed-off-by: Neeraj upadhyay Link: http://lore.kernel.org/CANZk6aR+CqZaqmMWrC2eRRPY12qAZnDZLwLnHZbNi=xXMB401g@mail.gmail.com Fixes: da915ad5cf25 ("srcu: Parallelize callback handling") Signed-off-by: Frederic Weisbecker Signed-off-by: Sasha Levin