/* * KVM coalesced MMIO * * Copyright (c) 2008 Bull S.A.S. * Copyright 2009 Red Hat, Inc. and/or its affiliates. * * Author: Laurent Vivier * */ #include #include #include #include #include "coalesced_mmio.h" static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev) { return container_of(dev, struct kvm_coalesced_mmio_dev, dev); } static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, gpa_t addr, int len) { /* is it in a batchable area ? * (addr,len) is fully included in * (zone->addr, zone->size) */ if (len < 0) return 0; if (addr + len < addr) return 0; if (addr < dev->zone.addr) return 0; if (addr + len > dev->zone.addr + dev->zone.size) return 0; return 1; } static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev) { struct kvm_coalesced_mmio_ring *ring; unsigned avail; /* Are we able to batch it ? */ /* last is the first free entry * check if we don't meet the first used entry * there is always one unused entry in the buffer */ ring = dev->kvm->coalesced_mmio_ring; avail = (ring->first - ring->last - 1) % KVM_COALESCED_MMIO_MAX; if (avail == 0) { /* full */ return 0; } return 1; } static int coalesced_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring; if (!coalesced_mmio_in_range(dev, addr, len)) return -EOPNOTSUPP; spin_lock(&dev->kvm->ring_lock); if (!coalesced_mmio_has_room(dev)) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } /* copy data in first free entry of the ring */ ring->coalesced_mmio[ring->last].phys_addr = addr; ring->coalesced_mmio[ring->last].len = len; memcpy(ring->coalesced_mmio[ring->last].data, val, len); smp_wmb(); ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX; spin_unlock(&dev->kvm->ring_lock); return 0; } static void coalesced_mmio_destructor(struct kvm_io_device *this) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); list_del(&dev->list); kfree(dev); } static const struct kvm_io_device_ops coalesced_mmio_ops = { .write = coalesced_mmio_write, .destructor = coalesced_mmio_destructor, }; int kvm_coalesced_mmio_init(struct kvm *kvm) { struct page *page; int ret; ret = -ENOMEM; page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) goto out_err; ret = 0; kvm->coalesced_mmio_ring = page_address(page); /* * We're using this spinlock to sync access to the coalesced ring. * The list doesn't need it's own lock since device registration and * unregistration should only happen when kvm->slots_lock is held. */ spin_lock_init(&kvm->ring_lock); INIT_LIST_HEAD(&kvm->coalesced_zones); out_err: return ret; } void kvm_coalesced_mmio_free(struct kvm *kvm) { if (kvm->coalesced_mmio_ring) free_page((unsigned long)kvm->coalesced_mmio_ring); } int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { int ret; struct kvm_coalesced_mmio_dev *dev; dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL); if (!dev) return -ENOMEM; kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops); dev->kvm = kvm; dev->zone = *zone; mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, zone->addr, zone->size, &dev->dev); if (ret < 0) goto out_free_dev; list_add_tail(&dev->list, &kvm->coalesced_zones); mutex_unlock(&kvm->slots_lock); return 0; out_free_dev: mutex_unlock(&kvm->slots_lock); kfree(dev); return ret; } int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { struct kvm_coalesced_mmio_dev *dev, *tmp; mutex_lock(&kvm->slots_lock); list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) if (coalesced_mmio_in_range(dev, zone->addr, zone->size)) { kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dev->dev); kvm_iodevice_destructor(&dev->dev); } mutex_unlock(&kvm->slots_lock); return 0; } on value='0' selected='selected'>includemode:
authorDouglas Miller <dougmill@linux.vnet.ibm.com>2017-01-28 06:42:20 -0600
committerTejun Heo <tj@kernel.org>2017-01-28 07:49:42 -0500
commit966d2b04e070bc040319aaebfec09e0144dc3341 (patch)
tree4b96156e3d1dd4dfd6039b7c219c9dc4616da52d /drivers/usb/dwc2/platform.c
parent1b1bc42c1692e9b62756323c675a44cb1a1f9dbd (diff)
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines use an actual boolean internally instead of the atomic long result truncated to a int. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com> Reviewed-by: Jens Axboe <axboe@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints") Cc: stable@vger.kernel.org # v3.18+
Diffstat (limited to 'drivers/usb/dwc2/platform.c')