user/sven/linux.git/kernel/cpu.c, branch v4.19.207

cpu/hotplug: Cure the cpusets trainwreck

2021-07-20T14:16:04Z

commit b22afcdf04c96ca58327784e280e10288cfd3303 upstream. Alexey and Joshua tried to solve a cpusets related hotplug problem which is user space visible and results in unexpected behaviour for some time after a CPU has been plugged in and the corresponding uevent was delivered. cpusets delegate the hotplug work (rebuilding cpumasks etc.) to a workqueue. This is done because the cpusets code has already a lock nesting of cgroups_mutex -> cpu_hotplug_lock. A synchronous callback or waiting for the work to finish with cpu_hotplug_lock held can and will deadlock because that results in the reverse lock order. As a consequence the uevent can be delivered before cpusets have consistent state which means that a user space invocation of sched_setaffinity() to move a task to the plugged CPU fails up to the point where the scheduled work has been processed. The same is true for CPU unplug, but that does not create user observable failure (yet). It's still inconsistent to claim that an operation is finished before it actually is and that's the real issue at hand. uevents just make it reliably observable. Obviously the problem should be fixed in cpusets/cgroups, but untangling that is pretty much impossible because according to the changelog of the commit which introduced this 8 years ago: 3a5a6d0c2b03("cpuset: don't nest cgroup_mutex inside get_online_cpus()") the lock order cgroups_mutex -> cpu_hotplug_lock is a design decision and the whole code is built around that. So bite the bullet and invoke the relevant cpuset function, which waits for the work to finish, in _cpu_up/down() after dropping cpu_hotplug_lock and only when tasks are not frozen by suspend/hibernate because that would obviously wait forever. Waiting there with cpu_add_remove_lock, which is protecting the present and possible CPU maps, held is not a problem at all because neither work queues nor cpusets/cgroups have any lockchains related to that lock. Waiting in the hotplug machinery is not problematic either because there are already state callbacks which wait for hardware queues to drain. It makes the operations slightly slower, but hotplug is slow anyway. This ensures that state is consistent before returning from a hotplug up/down operation. It's still inconsistent during the operation, but that's a different story. Add a large comment which explains why this is done and why this is not a dump ground for the hack of the day to work around half thought out locking schemes. Document also the implications vs. hotplug operations and serialization or the lack of it. Thanks to Alexy and Joshua for analyzing why this temporary sched_setaffinity() failure happened. Fixes: 3a5a6d0c2b03("cpuset: don't nest cgroup_mutex inside get_online_cpus()") Reported-by: Alexey Klimov Reported-by: Joshua Baker Signed-off-by: Thomas Gleixner Tested-by: Alexey Klimov Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87tuowcnv3.ffs@nanos.tec.linutronix.de Signed-off-by: Greg Kroah-Hartman

kernel/cpu: add arch override for clear_tasks_mm_cpumask() mm handling

2020-12-30T10:25:45Z

[ Upstream commit 8ff00399b153440c1c83e20c43020385b416415b ] powerpc/64s keeps a counter in the mm which counts bits set in mm_cpumask as well as other things. This means it can't use generic code to clear bits out of the mask and doesn't adjust the arch specific counter. Add an arch override that allows powerpc/64s to use clear_tasks_mm_cpumask(). Signed-off-by: Nicholas Piggin Reviewed-by: Aneesh Kumar K.V Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201126102530.691335-4-npiggin@gmail.com Signed-off-by: Sasha Levin

sched/core: Fix illegal RCU from offline CPUs

2020-06-22T07:05:14Z

[ Upstream commit bf2c59fce4074e55d622089b34be3a6bc95484fb ] In the CPU-offline process, it calls mmdrop() after idle entry and the subsequent call to cpuhp_report_idle_dead(). Once execution passes the call to rcu_report_dead(), RCU is ignoring the CPU, which results in lockdep complaining when mmdrop() uses RCU from either memcg or debugobjects below. Fix it by cleaning up the active_mm state from BP instead. Every arch which has CONFIG_HOTPLUG_CPU should have already called idle_task_exit() from AP. The only exception is parisc because it switches them to &init_mm unconditionally (see smp_boot_one_cpu() and smp_cpu_init()), but the patch will still work there because it calls mmgrab(&init_mm) in smp_cpu_init() and then should call mmdrop(&init_mm) in finish_cpu(). WARNING: suspicious RCU usage ----------------------------- kernel/workqueue.c:710 RCU or wq_pool_mutex should be held! other info that might help us debug this: RCU used illegally from offline CPU! Call Trace: dump_stack+0xf4/0x164 (unreliable) lockdep_rcu_suspicious+0x140/0x164 get_work_pool+0x110/0x150 __queue_work+0x1bc/0xca0 queue_work_on+0x114/0x120 css_release+0x9c/0xc0 percpu_ref_put_many+0x204/0x230 free_pcp_prepare+0x264/0x570 free_unref_page+0x38/0xf0 __mmdrop+0x21c/0x2c0 idle_task_exit+0x170/0x1b0 pnv_smp_cpu_kill_self+0x38/0x2e0 cpu_die+0x48/0x64 arch_cpu_idle_dead+0x30/0x50 do_idle+0x2f4/0x470 cpu_startup_entry+0x38/0x40 start_secondary+0x7a8/0xa80 start_secondary_resume+0x10/0x14 Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Qian Cai Signed-off-by: Peter Zijlstra (Intel) Acked-by: Michael Ellerman (powerpc) Link: https://lkml.kernel.org/r/20200401214033.8448-1-cai@lca.pw Signed-off-by: Sasha Levin

x86/speculation: Remove redundant arch_smt_update() invocation

2020-04-17T08:48:50Z

commit 34d66caf251df91ff27b24a3a786810d29989eca upstream. With commit a74cfffb03b7 ("x86/speculation: Rework SMT state change"), arch_smt_update() is invoked from each individual CPU hotplug function. Therefore the extra arch_smt_update() call in the sysfs SMT control is redundant. Fixes: a74cfffb03b7 ("x86/speculation: Rework SMT state change") Signed-off-by: Zhenzhong Duan Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Cc: Cc: Cc: Link: https://lkml.kernel.org/r/e2e064f2-e8ef-42ca-bf4f-76b612964752@default Cc: Guenter Roeck Signed-off-by: Greg Kroah-Hartman

cpu/hotplug, stop_machine: Fix stop_machine vs hotplug order

2020-02-24T07:34:35Z

[ Upstream commit 45178ac0cea853fe0e405bf11e101bdebea57b15 ] Paul reported a very sporadic, rcutorture induced, workqueue failure. When the planets align, the workqueue rescuer's self-migrate fails and then triggers a WARN for running a work on the wrong CPU. Tejun then figured that set_cpus_allowed_ptr()'s stop_one_cpu() call could be ignored! When stopper->enabled is false, stop_machine will insta complete the work, without actually doing the work. Worse, it will not WARN about this (we really should fix this). It turns out there is a small window where a freshly online'ed CPU is marked 'online' but doesn't yet have the stopper task running: BP AP bringup_cpu() __cpu_up(cpu, idle) --> start_secondary() ... cpu_startup_entry() bringup_wait_for_ap() wait_for_ap_thread() <-- cpuhp_online_idle() while (1) do_idle() ... available to run kthreads ... stop_machine_unpark() stopper->enable = true; Close this by moving the stop_machine_unpark() into cpuhp_online_idle(), such that the stopper thread is ready before we start the idle loop and schedule. Reported-by: "Paul E. McKenney" Debugged-by: Tejun Heo Signed-off-by: Peter Zijlstra (Intel) Tested-by: "Paul E. McKenney" Signed-off-by: Sasha Levin

cpu/SMT: State SMT is disabled even with nosmt and without "=force"

2019-11-24T07:20:18Z

[ Upstream commit d0e7d14455d41163126afecd0fcce935463cc512 ] When booting with "nosmt=force" a message is issued into dmesg to confirm that SMT has been force-disabled but such a message is not issued when only "nosmt" is on the kernel command line. Fix that. Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181004172227.10094-1-bp@alien8.de Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin

cpu/speculation: Uninline and export CPU mitigations helpers

2019-11-12T18:21:38Z

commit 731dc9df975a5da21237a18c3384f811a7a41cc6 upstream. A kernel module may need to check the value of the "mitigations=" kernel command line parameter as part of its setup when the module needs to perform software mitigations for a CPU flaw. Uninline and export the helper functions surrounding the cpu_mitigations enum to allow for their usage from a module. Lastly, privatize the enum and cpu_mitigations variable since the value of cpu_mitigations can be checked with the exported helper functions. Signed-off-by: Tyler Hicks Signed-off-by: Paolo Bonzini Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman

cpu/hotplug: Fix out-of-bounds read when setting fail state

2019-07-21T07:03:11Z

[ Upstream commit 33d4a5a7a5b4d02915d765064b2319e90a11cbde ] Setting invalid value to /sys/devices/system/cpu/cpuX/hotplug/fail can control `struct cpuhp_step *sp` address, results in the following global-out-of-bounds read. Reproducer: # echo -2 > /sys/devices/system/cpu/cpu0/hotplug/fail KASAN report: BUG: KASAN: global-out-of-bounds in write_cpuhp_fail+0x2cd/0x2e0 Read of size 8 at addr ffffffff89734438 by task bash/1941 CPU: 0 PID: 1941 Comm: bash Not tainted 5.2.0-rc6+ #31 Call Trace: write_cpuhp_fail+0x2cd/0x2e0 dev_attr_store+0x58/0x80 sysfs_kf_write+0x13d/0x1a0 kernfs_fop_write+0x2bc/0x460 vfs_write+0x1e1/0x560 ksys_write+0x126/0x250 do_syscall_64+0xc1/0x390 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f05e4f4c970 The buggy address belongs to the variable: cpu_hotplug_lock+0x98/0xa0 Memory state around the buggy address: ffffffff89734300: fa fa fa fa 00 00 00 00 00 00 00 00 00 00 00 00 ffffffff89734380: fa fa fa fa 00 00 00 00 00 00 00 00 00 00 00 00 >ffffffff89734400: 00 00 00 00 fa fa fa fa 00 00 00 00 fa fa fa fa ^ ffffffff89734480: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffff89734500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Add a sanity check for the value written from user space. Fixes: 1db49484f21ed ("smp/hotplug: Hotplug state fail injection") Signed-off-by: Eiichi Tsukata Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Link: https://lkml.kernel.org/r/20190627024732.31672-1-devel@etsukata.com Signed-off-by: Sasha Levin

cpu/speculation: Warn on unsupported mitigations= parameter

2019-07-03T11:14:46Z

commit 1bf72720281770162c87990697eae1ba2f1d917a upstream. Currently, if the user specifies an unsupported mitigation strategy on the kernel command line, it will be ignored silently. The code will fall back to the default strategy, possibly leaving the system more vulnerable than expected. This may happen due to e.g. a simple typo, or, for a stable kernel release, because not all mitigation strategies have been backported. Inform the user by printing a message. Fixes: 98af8452945c5565 ("cpu/speculation: Add 'mitigations=' cmdline option") Signed-off-by: Geert Uytterhoeven Signed-off-by: Thomas Gleixner Acked-by: Josh Poimboeuf Cc: Peter Zijlstra Cc: Jiri Kosina Cc: Greg Kroah-Hartman Cc: Ben Hutchings Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190516070935.22546-1-geert@linux-m68k.org Signed-off-by: Greg Kroah-Hartman

x86/power: Fix 'nosmt' vs hibernation triple fault during resume

2019-06-11T10:20:52Z

commit ec527c318036a65a083ef68d8ba95789d2212246 upstream. As explained in 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees. That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once. This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid. That results in triple fault shortly after cr3 is switched, and machine reboots. Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration. Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait. Cc: 4.19+ # v4.19+ Debugged-by: Thomas Gleixner Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina Acked-by: Pavel Machek Reviewed-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman