kernel.git/kernel/fork.c, branch linux-5.12.y

sched: Stop PF_NO_SETAFFINITY from being inherited by various init system threads

2021-07-14T15:00:32Z

commit a8ea6fc9b089156d9230bfeef964dd9be101a4a9 upstream. Commit: 00b89fe0197f ("sched: Make the idle task quack like a per-CPU kthread") ... added PF_KTHREAD | PF_NO_SETAFFINITY to the idle kernel threads. Unfortunately these properties are inherited to the init/0 children through kernel_thread() calls: init/1 and kthreadd. There are several side effects to that: 1) kthreadd affinity can not be reset anymore from userspace. Also PF_NO_SETAFFINITY propagates to all kthreadd children, including the unbound kthreads Therefore it's not possible anymore to overwrite the affinity of any of them. Here is an example of warning reported by rcutorture: WARNING: CPU: 0 PID: 116 at kernel/rcu/tree_nocb.h:1306 rcu_bind_current_to_nocb+0x31/0x40 Call Trace: rcu_torture_fwd_prog+0x62/0x730 kthread+0x122/0x140 ret_from_fork+0x22/0x30 2) init/1 does an exec() in the end which clears both PF_KTHREAD and PF_NO_SETAFFINITY so we are fine once kernel_init() escapes to userspace. But until then, no initcall or init code can successfully call sched_setaffinity() to init/1. Also PF_KTHREAD looks legit on init/1 before it calls exec() but we better be careful with unknown introduced side effects. One way to solve the PF_NO_SETAFFINITY issue is to not inherit this flag on copy_process() at all. The cases where it matters are: * fork_idle(): explicitly set the flag already. * fork() syscalls: userspace tasks that shouldn't be concerned by that. * create_io_thread(): the callers explicitly attribute the flag to the newly created tasks. * kernel_thread(): - Fix the issues on init/1 and kthreadd - Fix the issues on kthreadd children. - Usermode helper created by an unbound workqueue. This shouldn't matter. In the worst case it gives more control to userspace on setting affinity to these short living tasks although this can be tuned with inherited unbound workqueues affinity already. Fixes: 00b89fe0197f ("sched: Make the idle task quack like a per-CPU kthread") Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar Tested-by: Paul E. McKenney Link: https://lore.kernel.org/r/20210525235849.441842-1-frederic@kernel.org Signed-off-by: Greg Kroah-Hartman

sched/core: Initialize the idle task with preemption disabled

2021-07-14T14:59:16Z

[ Upstream commit f1a0a376ca0c4ef1fc3d24e3e502acbb5b795674 ] As pointed out by commit de9b8f5dcbd9 ("sched: Fix crash trying to dequeue/enqueue the idle thread") init_idle() can and will be invoked more than once on the same idle task. At boot time, it is invoked for the boot CPU thread by sched_init(). Then smp_init() creates the threads for all the secondary CPUs and invokes init_idle() on them. As the hotplug machinery brings the secondaries to life, it will issue calls to idle_thread_get(), which itself invokes init_idle() yet again. In this case it's invoked twice more per secondary: at _cpu_up(), and at bringup_cpu(). Given smp_init() already initializes the idle tasks for all *possible* CPUs, no further initialization should be required. Now, removing init_idle() from idle_thread_get() exposes some interesting expectations with regards to the idle task's preempt_count: the secondary startup always issues a preempt_disable(), requiring some reset of the preempt count to 0 between hot-unplug and hotplug, which is currently served by idle_thread_get() -> idle_init(). Given the idle task is supposed to have preemption disabled once and never see it re-enabled, it seems that what we actually want is to initialize its preempt_count to PREEMPT_DISABLED and leave it there. Do that, and remove init_idle() from idle_thread_get(). Secondary startups were patched via coccinelle: @begone@ @@ -preempt_disable(); ... cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20210512094636.2958515-1-valentin.schneider@arm.com Signed-off-by: Sasha Levin

Add a reference to ucounts for each cred

2021-07-14T14:59:14Z

[ Upstream commit 905ae01c4ae2ae3df05bb141801b1db4b7d83c61 ] For RLIMIT_NPROC and some other rlimits the user_struct that holds the global limit is kept alive for the lifetime of a process by keeping it in struct cred. Adding a pointer to ucounts in the struct cred will allow to track RLIMIT_NPROC not only for user in the system, but for user in the user_namespace. Updating ucounts may require memory allocation which may fail. So, we cannot change cred.ucounts in the commit_creds() because this function cannot fail and it should always return 0. For this reason, we modify cred.ucounts before calling the commit_creds(). Changelog v6: * Fix null-ptr-deref in is_ucounts_overlimit() detected by trinity. This error was caused by the fact that cred_alloc_blank() left the ucounts pointer empty. Reported-by: kernel test robot Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/b37aaef28d8b9b0d757e07ba6dd27281bbe39259.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman Signed-off-by: Sasha Levin

Merge tag 'io_uring-5.12-2021-03-27' of git://git.kernel.dk/linux-block

2021-03-28T18:42:05Z

Pull io_uring fixes from Jens Axboe: - Use thread info versions of flag testing, as discussed last week. - The series enabling PF_IO_WORKER to just take signals, instead of needing to special case that they do not in a bunch of places. Ends up being pretty trivial to do, and then we can revert all the special casing we're currently doing. - Kill dead pointer assignment - Fix hashed part of async work queue trace - Fix sign extension issue for IORING_OP_PROVIDE_BUFFERS - Fix a link completion ordering regression in this merge window - Cancellation fixes * tag 'io_uring-5.12-2021-03-27' of git://git.kernel.dk/linux-block: io_uring: remove unsued assignment to pointer io io_uring: don't cancel extra on files match io_uring: don't cancel-track common timeouts io_uring: do post-completion chore on t-out cancel io_uring: fix timeout cancel return code Revert "signal: don't allow STOP on PF_IO_WORKER threads" Revert "kernel: freezer should treat PF_IO_WORKER like PF_KTHREAD for freezing" Revert "kernel: treat PF_IO_WORKER like PF_KTHREAD for ptrace/signals" Revert "signal: don't allow sending any signals to PF_IO_WORKER threads" kernel: stop masking signals in create_io_thread() io_uring: handle signals for IO threads like a normal thread kernel: don't call do_exit() for PF_IO_WORKER threads io_uring: maintain CQE order of a failed link io-wq: fix race around pending work on teardown io_uring: do ctx sqd ejection in a clear context io_uring: fix provide_buffers sign extension io_uring: don't skip file_end_write() on reissue io_uring: correct io_queue_async_work() traces io_uring: don't use {test,clear}_tsk_thread_flag() for current

kernel: stop masking signals in create_io_thread()

2021-03-27T20:09:10Z

This is racy - move the blocking into when the task is created and we're marking it as PF_IO_WORKER anyway. The IO threads are now prepared to handle signals like SIGSTOP as well, so clear that from the mask to allow proper stopping of IO threads. Acked-by: "Eric W. Biederman" Reported-by: Oleg Nesterov Signed-off-by: Jens Axboe

Merge tag 'io_uring-5.12-2021-03-19' of git://git.kernel.dk/linux-block

2021-03-20T00:01:09Z

Pull io_uring fixes from Jens Axboe: "Quieter week this time, which was both expected and desired. About half of the below is fixes for this release, the other half are just fixes in general. In detail: - Fix the freezing of IO threads, by making the freezer not send them fake signals. Make them freezable by default. - Like we did for personalities, move the buffer IDR to xarray. Kills some code and avoids a use-after-free on teardown. - SQPOLL cleanups and fixes (Pavel) - Fix linked timeout race (Pavel) - Fix potential completion post use-after-free (Pavel) - Cleanup and move internal structures outside of general kernel view (Stefan) - Use MSG_SIGNAL for send/recv from io_uring (Stefan)" * tag 'io_uring-5.12-2021-03-19' of git://git.kernel.dk/linux-block: io_uring: don't leak creds on SQO attach error io_uring: use typesafe pointers in io_uring_task io_uring: remove structures from include/linux/io_uring.h io_uring: imply MSG_NOSIGNAL for send[msg]()/recv[msg]() calls io_uring: fix sqpoll cancellation via task_work io_uring: add generic callback_head helpers io_uring: fix concurrent parking io_uring: halt SQO submission on ctx exit io_uring: replace sqd rw_semaphore with mutex io_uring: fix complete_post use ctx after free io_uring: fix ->flags races by linked timeouts io_uring: convert io_buffer_idr to XArray io_uring: allow IO worker threads to be frozen kernel: freezer should treat PF_IO_WORKER like PF_KTHREAD for freezing

Merge branch 'akpm' (patches from Andrew)

2021-03-14T19:23:34Z

Merge misc fixes from Andrew Morton: "28 patches. Subsystems affected by this series: mm (memblock, pagealloc, hugetlb, highmem, kfence, oom-kill, madvise, kasan, userfaultfd, memcg, and zram), core-kernel, kconfig, fork, binfmt, MAINTAINERS, kbuild, and ia64" * emailed patches from Andrew Morton : (28 commits) zram: fix broken page writeback zram: fix return value on writeback_store mm/memcg: set memcg when splitting page mm/memcg: rename mem_cgroup_split_huge_fixup to split_page_memcg and add nr_pages argument ia64: fix ptrace(PTRACE_SYSCALL_INFO_EXIT) sign ia64: fix ia64_syscall_get_set_arguments() for break-based syscalls mm/userfaultfd: fix memory corruption due to writeprotect kasan: fix KASAN_STACK dependency for HW_TAGS kasan, mm: fix crash with HW_TAGS and DEBUG_PAGEALLOC mm/madvise: replace ptrace attach requirement for process_madvise include/linux/sched/mm.h: use rcu_dereference in in_vfork() kfence: fix reports if constant function prefixes exist kfence, slab: fix cache_alloc_debugcheck_after() for bulk allocations kfence: fix printk format for ptrdiff_t linux/compiler-clang.h: define HAVE_BUILTIN_BSWAP* MAINTAINERS: exclude uapi directories in API/ABI section binfmt_misc: fix possible deadlock in bm_register_write mm/highmem.c: fix zero_user_segments() with start > end hugetlb: do early cow when page pinned on src mm mm: use is_cow_mapping() across tree where proper ...

mm/fork: clear PASID for new mm

2021-03-13T19:27:30Z

When a new mm is created, its PASID should be cleared, i.e. the PASID is initialized to its init state 0 on both ARM and X86. This patch was part of the series introducing mm->pasid, but got lost along the way [1]. It still makes sense to have it, because each address space has a different PASID. And the IOMMU code in iommu_sva_alloc_pasid() expects the pasid field of a new mm struct to be cleared. [1] https://lore.kernel.org/linux-iommu/YDgh53AcQHT+T3L0@otcwcpicx3.sc.intel.com/ Link: https://lkml.kernel.org/r/20210302103837.2562625-1-jean-philippe@linaro.org Signed-off-by: Fenghua Yu Signed-off-by: Jean-Philippe Brucker Reviewed-by: Tony Luck Cc: Jacob Pan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

io_uring: allow IO worker threads to be frozen

2021-03-13T03:26:13Z

With the freezer using the proper signaling to notify us of when it's time to freeze a thread, we can re-enable normal freezer usage for the IO threads. Ensure that SQPOLL, io-wq, and the io-wq manager call try_to_freeze() appropriately, and remove the default setting of PF_NOFREEZE from create_io_thread(). Signed-off-by: Jens Axboe

kernel: make IO threads unfreezable by default

2021-03-10T14:28:43Z

The io-wq threads were already marked as no-freeze, but the manager was not. On resume, we perpetually have signal_pending() being true, and hence the manager will loop and spin 100% of the time. Just mark the tasks created by create_io_thread() as PF_NOFREEZE by default, and remove any knowledge of it in io-wq and io_uring. Reported-by: Kevin Locke Tested-by: Kevin Locke Signed-off-by: Jens Axboe