/* * VFIO generic eventfd code for IRQFD support. * Derived from drivers/vfio/pci/vfio_pci_intrs.c * * Copyright (C) 2012 Red Hat, Inc. All rights reserved. * Author: Alex Williamson * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include #include #include #include #include #define DRIVER_VERSION "0.1" #define DRIVER_AUTHOR "Alex Williamson " #define DRIVER_DESC "IRQFD support for VFIO bus drivers" static struct workqueue_struct *vfio_irqfd_cleanup_wq; static DEFINE_SPINLOCK(virqfd_lock); static int __init vfio_virqfd_init(void) { vfio_irqfd_cleanup_wq = create_singlethread_workqueue("vfio-irqfd-cleanup"); if (!vfio_irqfd_cleanup_wq) return -ENOMEM; return 0; } static void __exit vfio_virqfd_exit(void) { destroy_workqueue(vfio_irqfd_cleanup_wq); } static void virqfd_deactivate(struct virqfd *virqfd) { queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown); } static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) { struct virqfd *virqfd = container_of(wait, struct virqfd, wait); unsigned long flags = (unsigned long)key; if (flags & POLLIN) { /* An event has been signaled, call function */ if ((!virqfd->handler || virqfd->handler(virqfd->opaque, virqfd->data)) && virqfd->thread) schedule_work(&virqfd->inject); } if (flags & POLLHUP) { unsigned long flags; spin_lock_irqsave(&virqfd_lock, flags); /* * The eventfd is closing, if the virqfd has not yet been * queued for release, as determined by testing whether the * virqfd pointer to it is still valid, queue it now. As * with kvm irqfds, we know we won't race against the virqfd * going away because we hold the lock to get here. */ if (*(virqfd->pvirqfd) == virqfd) { *(virqfd->pvirqfd) = NULL; virqfd_deactivate(virqfd); } spin_unlock_irqrestore(&virqfd_lock, flags); } return 0; } static void virqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh, poll_table *pt) { struct virqfd *virqfd = container_of(pt, struct virqfd, pt); add_wait_queue(wqh, &virqfd->wait); } static void virqfd_shutdown(struct work_struct *work) { struct virqfd *virqfd = container_of(work, struct virqfd, shutdown); u64 cnt; eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt); flush_work(&virqfd->inject); eventfd_ctx_put(virqfd->eventfd); kfree(virqfd); } static void virqfd_inject(struct work_struct *work) { struct virqfd *virqfd = container_of(work, struct virqfd, inject); if (virqfd->thread) virqfd->thread(virqfd->opaque, virqfd->data); } int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), void *data, struct virqfd **pvirqfd, int fd) { struct fd irqfd; struct eventfd_ctx *ctx; struct virqfd *virqfd; int ret = 0; unsigned int events; virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL); if (!virqfd) return -ENOMEM; virqfd->pvirqfd = pvirqfd; virqfd->opaque = opaque; virqfd->handler = handler; virqfd->thread = thread; virqfd->data = data; INIT_WORK(&virqfd->shutdown, virqfd_shutdown); INIT_WORK(&virqfd->inject, virqfd_inject); irqfd = fdget(fd); if (!irqfd.file) { ret = -EBADF; goto err_fd; } ctx = eventfd_ctx_fileget(irqfd.file); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); goto err_ctx; } virqfd->eventfd = ctx; /* * virqfds can be released by closing the eventfd or directly * through ioctl. These are both done through a workqueue, so * we update the pointer to the virqfd under lock to avoid * pushing multiple jobs to release the same virqfd. */ spin_lock_irq(&virqfd_lock); if (*pvirqfd) { spin_unlock_irq(&virqfd_lock); ret = -EBUSY; goto err_busy; } *pvirqfd = virqfd; spin_unlock_irq(&virqfd_lock); /* * Install our own custom wake-up handling so we are notified via * a callback whenever someone signals the underlying eventfd. */ init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup); init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc); events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt); /* * Check if there was an event already pending on the eventfd * before we registered and trigger it as if we didn't miss it. */ if (events & POLLIN) { if ((!handler || handler(opaque, data)) && thread) schedule_work(&virqfd->inject); } /* * Do not drop the file until the irqfd is fully initialized, * otherwise we might race against the POLLHUP. */ fdput(irqfd); return 0; err_busy: eventfd_ctx_put(ctx); err_ctx: fdput(irqfd); err_fd: kfree(virqfd); return ret; } EXPORT_SYMBOL_GPL(vfio_virqfd_enable); void vfio_virqfd_disable(struct virqfd **pvirqfd) { unsigned long flags; spin_lock_irqsave(&virqfd_lock, flags); if (*pvirqfd) { virqfd_deactivate(*pvirqfd); *pvirqfd = NULL; } spin_unlock_irqrestore(&virqfd_lock, flags); /* * Block until we know all outstanding shutdown jobs have completed. * Even if we don't queue the job, flush the wq to be sure it's * been released. */ flush_workqueue(vfio_irqfd_cleanup_wq); } EXPORT_SYMBOL_GPL(vfio_virqfd_disable); module_init(vfio_virqfd_init); module_exit(vfio_virqfd_exit); MODULE_VERSION(DRIVER_VERSION); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); /td> tree098a7c0ca4fceb8a65cb1f693c9d71990388933d /include/scsi/scsi_ioctl.h parenta0615a16f7d0ceb5804d295203c302d496d8ee91 (diff)
powerpc/mm: Fix spurrious segfaults on radix with autonuma
When autonuma (Automatic NUMA balancing) marks a PTE inaccessible it clears all the protection bits but leave the PTE valid. With the Radix MMU, an attempt at executing from such a PTE will take a fault with bit 35 of SRR1 set "SRR1_ISI_N_OR_G". It is thus incorrect to treat all such faults as errors. We should pass them to handle_mm_fault() for autonuma to deal with. The case of pages that are really not executable is handled by the existing test for VM_EXEC further down. That leaves us with catching the kernel attempts at executing user pages. We can catch that earlier, even before we do find_vma. It is never valid on powerpc for the kernel to take an exec fault to begin with. So fold that test with the existing test for the kernel faulting on kernel addresses to bail out early. Fixes: 1d18ad026844 ("powerpc/mm: Detect instruction fetch denied and report") Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Balbir Singh <bsingharora@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'include/scsi/scsi_ioctl.h')