From f848a5a8dcb655553423f77cc98909a04e64173d Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 31 Mar 2014 21:50:38 +0300 Subject: KVM: support any-length wildcard ioeventfd It is sometimes benefitial to ignore IO size, and only match on address. In hindsight this would have been a better default than matching length when KVM_IOEVENTFD_FLAG_DATAMATCH is not set, In particular, this kind of access can be optimized on VMX: there no need to do page lookups. This can currently be done with many ioeventfds but in a suboptimal way. However we can't change kernel/userspace ABI without risk of breaking some applications. Use len = 0 to mean "ignore length for matching" in a more optimal way. Signed-off-by: Michael S. Tsirkin Signed-off-by: Marcelo Tosatti --- virt/kvm/eventfd.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'virt') diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 29c2a04e036e..2721996bb9c2 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -600,7 +600,15 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val) { u64 _val; - if (!(addr == p->addr && len == p->length)) + if (addr != p->addr) + /* address must be precise for a hit */ + return false; + + if (!p->length) + /* length = 0 means only look at the address, so always a hit */ + return true; + + if (len != p->length) /* address-range must be precise for a hit */ return false; @@ -671,9 +679,11 @@ ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p) list_for_each_entry(_p, &kvm->ioeventfds, list) if (_p->bus_idx == p->bus_idx && - _p->addr == p->addr && _p->length == p->length && - (_p->wildcard || p->wildcard || - _p->datamatch == p->datamatch)) + _p->addr == p->addr && + (!_p->length || !p->length || + (_p->length == p->length && + (_p->wildcard || p->wildcard || + _p->datamatch == p->datamatch)))) return true; return false; @@ -697,8 +707,9 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) int ret; bus_idx = ioeventfd_bus_from_flags(args->flags); - /* must be natural-word sized */ + /* must be natural-word sized, or 0 to ignore length */ switch (args->len) { + case 0: case 1: case 2: case 4: @@ -716,6 +727,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK) return -EINVAL; + /* ioeventfd with no length can't be combined with DATAMATCH */ + if (!args->len && + args->flags & (KVM_IOEVENTFD_FLAG_PIO | + KVM_IOEVENTFD_FLAG_DATAMATCH)) + return -EINVAL; + eventfd = eventfd_ctx_fdget(args->fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); -- cgit v1.2.3 From 68c3b4d1676d870f0453c31d5a52e7e65c7448ae Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 31 Mar 2014 21:50:44 +0300 Subject: KVM: VMX: speed up wildcard MMIO EVENTFD With KVM, MMIO is much slower than PIO, due to the need to do page walk and emulation. But with EPT, it does not have to be: we know the address from the VMCS so if the address is unique, we can look up the eventfd directly, bypassing emulation. Unfortunately, this only works if userspace does not need to match on access length and data. The implementation adds a separate FAST_MMIO bus internally. This serves two purposes: - minimize overhead for old userspace that does not use eventfd with lengtth = 0 - minimize disruption in other code (since we don't know the length, devices on the MMIO bus only get a valid address in write, this way we don't need to touch all devices to teach them to handle an invalid length) At the moment, this optimization only has effect for EPT on x86. It will be possible to speed up MMIO for NPT and MMU using the same idea in the future. With this patch applied, on VMX MMIO EVENTFD is essentially as fast as PIO. I was unable to detect any measureable slowdown to non-eventfd MMIO. Making MMIO faster is important for the upcoming virtio 1.0 which includes an MMIO signalling capability. The idea was suggested by Peter Anvin. Lots of thanks to Gleb for pre-review and suggestions. Signed-off-by: Michael S. Tsirkin Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/vmx.c | 4 ++++ include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 1 + virt/kvm/eventfd.c | 16 ++++++++++++++++ virt/kvm/kvm_main.c | 1 + 5 files changed, 23 insertions(+) (limited to 'virt') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1f68c5831924..eb3f2b1b764c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5528,6 +5528,10 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); + if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + skip_emulated_instruction(vcpu); + return 1; + } ret = handle_mmio_page_fault_common(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7d21cf9f4380..6c3c2eb96d06 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -163,6 +163,7 @@ enum kvm_bus { KVM_MMIO_BUS, KVM_PIO_BUS, KVM_VIRTIO_CCW_NOTIFY_BUS, + KVM_FAST_MMIO_BUS, KVM_NR_BUSES }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 39098a61f41c..d8a6ce4c2a83 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -515,6 +515,7 @@ enum { kvm_ioeventfd_flag_nr_pio, kvm_ioeventfd_flag_nr_deassign, kvm_ioeventfd_flag_nr_virtio_ccw_notify, + kvm_ioeventfd_flag_nr_fast_mmio, kvm_ioeventfd_flag_nr_max, }; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 2721996bb9c2..912ec5a95e2c 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -770,6 +770,16 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (ret < 0) goto unlock_fail; + /* When length is ignored, MMIO is also put on a separate bus, for + * faster lookups. + */ + if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) { + ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS, + p->addr, 0, &p->dev); + if (ret < 0) + goto register_fail; + } + kvm->buses[bus_idx]->ioeventfd_count++; list_add_tail(&p->list, &kvm->ioeventfds); @@ -777,6 +787,8 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) return 0; +register_fail: + kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); unlock_fail: mutex_unlock(&kvm->slots_lock); @@ -816,6 +828,10 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) continue; kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); + if (!p->length) { + kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS, + &p->dev); + } kvm->buses[bus_idx]->ioeventfd_count--; ioeventfd_release(p); ret = 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 56baae8c2f56..96456ac888ba 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2922,6 +2922,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range, return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_read - called under kvm->slots_lock */ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, -- cgit v1.2.3 From 15f36ebd34b5b296c274ef67024f14c2d394a507 Mon Sep 17 00:00:00 2001 From: "Jason J. Herne" Date: Thu, 2 Aug 2012 10:10:17 -0400 Subject: KVM: s390: Add proper dirty bitmap support to S390 kvm. Replace the kvm_s390_sync_dirty_log() stub with code to construct the KVM dirty_bitmap from S390 memory change bits. Also add code to properly clear the dirty_bitmap size when clearing the bitmap. Signed-off-by: Jason J. Herne CC: Dominik Dingel [Dominik Dingel: use gmap_test_and_clear_dirty, locking fixes] Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++- virt/kvm/kvm_main.c | 2 -- 2 files changed, 50 insertions(+), 3 deletions(-) (limited to 'virt') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b767ec97368a..346a3478dd00 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -11,6 +11,7 @@ * Christian Borntraeger * Heiko Carstens * Christian Ehrhardt + * Jason J. Herne */ #include @@ -179,6 +180,25 @@ int kvm_dev_ioctl_check_extension(long ext) return r; } +static void kvm_s390_sync_dirty_log(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + gfn_t cur_gfn, last_gfn; + unsigned long address; + struct gmap *gmap = kvm->arch.gmap; + + down_read(&gmap->mm->mmap_sem); + /* Loop over all guest pages */ + last_gfn = memslot->base_gfn + memslot->npages; + for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) { + address = gfn_to_hva_memslot(memslot, cur_gfn); + + if (gmap_test_and_clear_dirty(address, gmap)) + mark_page_dirty(kvm, cur_gfn); + } + up_read(&gmap->mm->mmap_sem); +} + /* Section: vm related */ /* * Get (and clear) the dirty memory log for a memory slot. @@ -186,7 +206,36 @@ int kvm_dev_ioctl_check_extension(long ext) int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - return 0; + int r; + unsigned long n; + struct kvm_memory_slot *memslot; + int is_dirty = 0; + + mutex_lock(&kvm->slots_lock); + + r = -EINVAL; + if (log->slot >= KVM_USER_MEM_SLOTS) + goto out; + + memslot = id_to_memslot(kvm->memslots, log->slot); + r = -ENOENT; + if (!memslot->dirty_bitmap) + goto out; + + kvm_s390_sync_dirty_log(kvm, memslot); + r = kvm_get_dirty_log(kvm, log, &is_dirty); + if (r) + goto out; + + /* Clear the dirty log */ + if (is_dirty) { + n = kvm_dirty_bitmap_bytes(memslot); + memset(memslot->dirty_bitmap, 0, n); + } + r = 0; +out: + mutex_unlock(&kvm->slots_lock); + return r; } static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 56baae8c2f56..7facdb1f1374 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -637,14 +637,12 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) */ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) { -#ifndef CONFIG_S390 unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes); if (!memslot->dirty_bitmap) return -ENOMEM; -#endif /* !CONFIG_S390 */ return 0; } -- cgit v1.2.3 From a086f6a1ebc9d8d2d028b99e779ce0dbd9691dea Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 17 Apr 2014 17:06:12 +0800 Subject: Revert "KVM: Simplify kvm->tlbs_dirty handling" This reverts commit 5befdc385ddb2d5ae8995ad89004529a3acf58fc. Since we will allow flush tlb out of mmu-lock in the later patch Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/paging_tmpl.h | 7 +++---- include/linux/kvm_host.h | 4 +--- virt/kvm/kvm_main.c | 5 ++++- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'virt') diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 123efd3ec29f..410776528265 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -913,8 +913,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't * used by guest then tlbs are not flushed, so guest is allowed to access the * freed pages. - * We set tlbs_dirty to let the notifier know this change and delay the flush - * until such a case actually happens. + * And we increase kvm->tlbs_dirty to delay tlbs flush in this case. */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -943,7 +942,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return -EINVAL; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - vcpu->kvm->tlbs_dirty = true; + vcpu->kvm->tlbs_dirty++; continue; } @@ -958,7 +957,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (gfn != sp->gfns[i]) { drop_spte(vcpu->kvm, &sp->spt[i]); - vcpu->kvm->tlbs_dirty = true; + vcpu->kvm->tlbs_dirty++; continue; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 32d263f683dc..820fc2e1d9df 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -411,9 +411,7 @@ struct kvm { unsigned long mmu_notifier_seq; long mmu_notifier_count; #endif - /* Protected by mmu_lock */ - bool tlbs_dirty; - + long tlbs_dirty; struct list_head devices; }; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ea46d64c8e75..fa70c6e642b4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -186,9 +186,12 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) void kvm_flush_remote_tlbs(struct kvm *kvm) { + long dirty_count = kvm->tlbs_dirty; + + smp_mb(); if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.remote_tlb_flush; - kvm->tlbs_dirty = false; + cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); -- cgit v1.2.3 From d72d946d0b649b79709b99b9d5cb7269fff8afaa Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 21 Apr 2014 15:25:58 +0200 Subject: KVM: async_pf: kill the unnecessary use_mm/unuse_mm async_pf_execute() async_pf_execute() has no reasons to adopt apf->mm, gup(current, mm) should work just fine even if current has another or NULL ->mm. Recently kvm_async_page_present_sync() was added insedie the "use_mm" section, but it seems that it doesn't need current->mm too. Signed-off-by: Oleg Nesterov Reviewed-by: Andrea Arcangeli Signed-off-by: Paolo Bonzini --- virt/kvm/async_pf.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'virt') diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 10df100c4514..0ced4f31bc65 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -80,12 +80,10 @@ static void async_pf_execute(struct work_struct *work) might_sleep(); - use_mm(mm); down_read(&mm->mmap_sem); get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL); up_read(&mm->mmap_sem); kvm_async_page_present_sync(vcpu, apf); - unuse_mm(mm); spin_lock(&vcpu->async_pf.lock); list_add_tail(&apf->link, &vcpu->async_pf.done); -- cgit v1.2.3 From e9545b9f8aeb63e05818e4b3250057260bc072aa Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 28 Apr 2014 17:03:00 +0200 Subject: KVM: async_pf: change async_pf_execute() to use get_user_pages(tsk => NULL) async_pf_execute() passes tsk == current to gup(), this is doesn't hurt but unnecessary and misleading. "tsk" is only used to account the number of faults and current is the random workqueue thread. Signed-off-by: Oleg Nesterov Suggested-by: Andrea Arcangeli Signed-off-by: Paolo Bonzini --- virt/kvm/async_pf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'virt') diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 0ced4f31bc65..62f4223f4c9e 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -81,7 +81,7 @@ static void async_pf_execute(struct work_struct *work) might_sleep(); down_read(&mm->mmap_sem); - get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL); + get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL); up_read(&mm->mmap_sem); kvm_async_page_present_sync(vcpu, apf); -- cgit v1.2.3 From 719d93cd5f5c5c8775b7a38192069e8e1d1ac46e Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 16 Jan 2014 13:44:20 +0100 Subject: kvm/irqchip: Speed up KVM_SET_GSI_ROUTING When starting lots of dataplane devices the bootup takes very long on Christian's s390 with irqfd patches. With larger setups he is even able to trigger some timeouts in some components. Turns out that the KVM_SET_GSI_ROUTING ioctl takes very long (strace claims up to 0.1 sec) when having multiple CPUs. This is caused by the synchronize_rcu and the HZ=100 of s390. By changing the code to use a private srcu we can speed things up. This patch reduces the boot time till mounting root from 8 to 2 seconds on my s390 guest with 100 disks. Uses of hlist_for_each_entry_rcu, hlist_add_head_rcu, hlist_del_init_rcu are fine because they do not have lockdep checks (hlist_for_each_entry_rcu uses rcu_dereference_raw rather than rcu_dereference, and write-sides do not do rcu lockdep at all). Note that we're hardly relying on the "sleepable" part of srcu. We just want SRCU's faster detection of grace periods. Testing was done by Andrew Theurer using netperf tests STREAM, MAERTS and RR. The difference between results "before" and "after" the patch has mean -0.2% and standard deviation 0.6%. Using a paired t-test on the data points says that there is a 2.5% probability that the patch is the cause of the performance difference (rather than a random fluctuation). (Restricting the t-test to RR, which is the most likely to be affected, changes the numbers to respectively -0.3% mean, 0.7% stdev, and 8% probability that the numbers actually say something about the patch. The probability increases mostly because there are fewer data points). Cc: Marcelo Tosatti Cc: Michael S. Tsirkin Tested-by: Christian Borntraeger # s390 Reviewed-by: Christian Borntraeger Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + virt/kvm/eventfd.c | 25 +++++++++++++++---------- virt/kvm/irq_comm.c | 17 +++++++++-------- virt/kvm/irqchip.c | 31 ++++++++++++++++--------------- virt/kvm/kvm_main.c | 16 ++++++++++------ 5 files changed, 51 insertions(+), 39 deletions(-) (limited to 'virt') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1e125b055327..970c68197c69 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -370,6 +370,7 @@ struct kvm { struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots *memslots; struct srcu_struct srcu; + struct srcu_struct irq_srcu; #ifdef CONFIG_KVM_APIC_ARCHITECTURE u32 bsp_vcpu_id; #endif diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 912ec5a95e2c..20c3af7692c5 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include "iodev.h" @@ -118,19 +119,22 @@ static void irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) { struct _irqfd_resampler *resampler; + struct kvm *kvm; struct _irqfd *irqfd; + int idx; resampler = container_of(kian, struct _irqfd_resampler, notifier); + kvm = resampler->kvm; - kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); - rcu_read_lock(); + idx = srcu_read_lock(&kvm->irq_srcu); list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link) eventfd_signal(irqfd->resamplefd, 1); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } static void @@ -142,7 +146,7 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd) mutex_lock(&kvm->irqfds.resampler_lock); list_del_rcu(&irqfd->resampler_link); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); if (list_empty(&resampler->list)) { list_del(&resampler->link); @@ -221,17 +225,18 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) unsigned long flags = (unsigned long)key; struct kvm_kernel_irq_routing_entry *irq; struct kvm *kvm = irqfd->kvm; + int idx; if (flags & POLLIN) { - rcu_read_lock(); - irq = rcu_dereference(irqfd->irq_entry); + idx = srcu_read_lock(&kvm->irq_srcu); + irq = srcu_dereference(irqfd->irq_entry, &kvm->irq_srcu); /* An event has been signaled, inject an interrupt */ if (irq) kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false); else schedule_work(&irqfd->inject); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } if (flags & POLLHUP) { @@ -363,7 +368,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); mutex_unlock(&kvm->irqfds.resampler_lock); } @@ -465,7 +470,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) * another thread calls kvm_irq_routing_update before * we flush workqueue below (we synchronize with * kvm_irq_routing_update using irqfds.lock). - * It is paired with synchronize_rcu done by caller + * It is paired with synchronize_srcu done by caller * of that function. */ rcu_assign_pointer(irqfd->irq_entry, NULL); @@ -524,7 +529,7 @@ kvm_irqfd_release(struct kvm *kvm) /* * Change irq_routing and irqfd. - * Caller must invoke synchronize_rcu afterwards. + * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards. */ void kvm_irq_routing_update(struct kvm *kvm, struct kvm_irq_routing_table *irq_rt) diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index e2e6b4473a96..ced4a542a031 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -163,6 +163,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) struct kvm_kernel_irq_routing_entry *e; int ret = -EINVAL; struct kvm_irq_routing_table *irq_rt; + int idx; trace_kvm_set_irq(irq, level, irq_source_id); @@ -174,8 +175,8 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) * Since there's no easy way to do this, we only support injecting MSI * which is limited to 1:1 GSI mapping. */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); if (irq < irq_rt->nr_rt_entries) hlist_for_each_entry(e, &irq_rt->map[irq], link) { if (likely(e->type == KVM_IRQ_ROUTING_MSI)) @@ -184,7 +185,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) ret = -EWOULDBLOCK; break; } - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); return ret; } @@ -253,22 +254,22 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, mutex_lock(&kvm->irq_lock); hlist_del_rcu(&kimn->link); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); } void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask) { struct kvm_irq_mask_notifier *kimn; - int gsi; + int idx, gsi; - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin]; if (gsi != -1) hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link) if (kimn->irq == gsi) kimn->func(kimn, mask); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 20dc9e4a8f6c..b43c275775cd 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -26,6 +26,7 @@ #include #include +#include #include #include #include "irq.h" @@ -33,19 +34,19 @@ bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; - int gsi; + int gsi, idx; - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin]; if (gsi != -1) hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) { - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); return true; } - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); return false; } @@ -54,18 +55,18 @@ EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; - int gsi; + int gsi, idx; trace_kvm_ack_irq(irqchip, pin); - rcu_read_lock(); - gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin]; if (gsi != -1) hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) kian->irq_acked(kian); - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); } void kvm_register_irq_ack_notifier(struct kvm *kvm, @@ -85,7 +86,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, mutex_lock(&kvm->irq_lock); hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu(&kvm->irq_srcu); #ifdef __KVM_HAVE_IOAPIC kvm_vcpu_request_scan_ioapic(kvm); #endif @@ -115,7 +116,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; - int ret = -1, i = 0; + int ret = -1, i = 0, idx; struct kvm_irq_routing_table *irq_rt; trace_kvm_set_irq(irq, level, irq_source_id); @@ -124,12 +125,12 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - rcu_read_lock(); - irq_rt = rcu_dereference(kvm->irq_routing); + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); if (irq < irq_rt->nr_rt_entries) hlist_for_each_entry(e, &irq_rt->map[irq], link) irq_set[i++] = *e; - rcu_read_unlock(); + srcu_read_unlock(&kvm->irq_srcu, idx); while(i--) { int r; @@ -226,7 +227,7 @@ int kvm_set_irq_routing(struct kvm *kvm, kvm_irq_routing_update(kvm, new); mutex_unlock(&kvm->irq_lock); - synchronize_rcu(); + synchronize_srcu_expedited(&kvm->irq_srcu); new = old; r = 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fa70c6e642b4..95b4c2b3906a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -457,11 +457,11 @@ static struct kvm *kvm_create_vm(unsigned long type) r = kvm_arch_init_vm(kvm, type); if (r) - goto out_err_nodisable; + goto out_err_no_disable; r = hardware_enable_all(); if (r) - goto out_err_nodisable; + goto out_err_no_disable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); @@ -473,10 +473,12 @@ static struct kvm *kvm_create_vm(unsigned long type) r = -ENOMEM; kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!kvm->memslots) - goto out_err_nosrcu; + goto out_err_no_srcu; kvm_init_memslots_id(kvm); if (init_srcu_struct(&kvm->srcu)) - goto out_err_nosrcu; + goto out_err_no_srcu; + if (init_srcu_struct(&kvm->irq_srcu)) + goto out_err_no_irq_srcu; for (i = 0; i < KVM_NR_BUSES; i++) { kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); @@ -505,10 +507,12 @@ static struct kvm *kvm_create_vm(unsigned long type) return kvm; out_err: + cleanup_srcu_struct(&kvm->irq_srcu); +out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); -out_err_nosrcu: +out_err_no_srcu: hardware_disable_all(); -out_err_nodisable: +out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); kfree(kvm->memslots); -- cgit v1.2.3 From 820b3fcdeb80d30410f4427d2cbf9161c35fdeef Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 3 Jun 2014 13:44:17 +0200 Subject: KVM: add missing cleanup_srcu_struct Reported-by: hrg Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 95b4c2b3906a..c86be0f983db 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -608,6 +608,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); kvm_free_physmem(kvm); + cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); hardware_disable_all(); -- cgit v1.2.3