From f5c9803173848864d0c56108b9e102db0bf601de Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Thu, 25 Feb 2010 11:33:19 +0900 Subject: KVM: update gfn_to_hva() to use gfn_to_hva_memslot() Marcelo introduced gfn_to_hva_memslot() when he implemented gfn_to_pfn_memslot(). Let's use this for gfn_to_hva() too. Note: also remove parentheses next to return as checkpatch said to do. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c82ae2492634..5bac6eb0f0a9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -914,6 +914,11 @@ int memslot_id(struct kvm *kvm, gfn_t gfn) return memslot - slots->memslots; } +static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; +} + unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *slot; @@ -922,7 +927,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) slot = gfn_to_memslot_unaliased(kvm, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return bad_hva(); - return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); + return gfn_to_hva_memslot(slot, gfn); } EXPORT_SYMBOL_GPL(gfn_to_hva); @@ -972,11 +977,6 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_pfn); -static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) -{ - return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); -} - pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn) { -- cgit v1.2.3 From 2ed152afc7ed61830b848b32936e1541a1a57799 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 10 Mar 2010 19:00:43 +0800 Subject: KVM: cleanup kvm trace This patch does: - no need call tracepoint_synchronize_unregister() when kvm module is unloaded since ftrace can handle it - cleanup ftrace's macro Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 1 - 1 file changed, 1 deletion(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5bac6eb0f0a9..b152b23cd095 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2279,7 +2279,6 @@ EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { - tracepoint_synchronize_unregister(); kvm_exit_debug(); misc_deregister(&kvm_dev); kmem_cache_destroy(kvm_vcpu_cache); -- cgit v1.2.3 From a87fa35514bcf17aeca97245574e3f735cec9074 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 12 Mar 2010 12:59:06 +0800 Subject: KVM: fix the errno of ioctl KVM_[UN]REGISTER_COALESCED_MMIO failure This patch change the errno of ioctl KVM_[UN]REGISTER_COALESCED_MMIO from -EINVAL to -ENXIO if no coalesced mmio dev exists. Signed-off-by: Wei Yongjun Signed-off-by: Marcelo Tosatti --- virt/kvm/coalesced_mmio.c | 4 ++-- virt/kvm/kvm_main.c | 2 -- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'virt') diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 36e258029649..b66001f8754c 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -139,7 +139,7 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev; if (dev == NULL) - return -EINVAL; + return -ENXIO; mutex_lock(&kvm->slots_lock); if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) { @@ -162,7 +162,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *z; if (dev == NULL) - return -EINVAL; + return -ENXIO; mutex_lock(&kvm->slots_lock); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b152b23cd095..0db6dfcc8420 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1609,7 +1609,6 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; - r = -ENXIO; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); if (r) goto out; @@ -1621,7 +1620,6 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; - r = -ENXIO; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); if (r) goto out; -- cgit v1.2.3 From d57e2c0740bbdd768dcbafe58cf62174f31d7c2d Mon Sep 17 00:00:00 2001 From: jing zhang Date: Sat, 13 Mar 2010 15:00:45 +0800 Subject: KVM: fix assigned_device_enable_host_msix error handling Free IRQ's and disable MSIX upon failure. Cc: Avi Kivity Signed-off-by: Jing Zhang Signed-off-by: Marcelo Tosatti --- virt/kvm/assigned-dev.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'virt') diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index 02ff2b19dbe2..4d10b1e047f4 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -316,12 +316,16 @@ static int assigned_device_enable_host_msix(struct kvm *kvm, kvm_assigned_dev_intr, 0, "kvm_assigned_msix_device", (void *)dev); - /* FIXME: free requested_irq's on failure */ if (r) - return r; + goto err; } return 0; +err: + for (i -= 1; i >= 0; i--) + free_irq(dev->host_msix_entries[i].vector, (void *)dev); + pci_disable_msix(dev->dev); + return r; } #endif -- cgit v1.2.3 From 6ce5a090a9a0ea4266a2cad058c69e2f27201e11 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Mon, 15 Mar 2010 22:13:30 +0900 Subject: KVM: coalesced_mmio: fix kvm_coalesced_mmio_init()'s error handling kvm_coalesced_mmio_init() keeps to hold the addresses of a coalesced mmio ring page and dev even after it has freed them. Also, if this function fails, though it might be rare, it seems to be suggesting the system's serious state: so we'd better stop the works following the kvm_creat_vm(). This patch clears these problems. We move the coalesced mmio's initialization out of kvm_create_vm(). This seems to be natural because it includes a registration which can be done only when vm is successfully created. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- virt/kvm/coalesced_mmio.c | 2 ++ virt/kvm/kvm_main.c | 12 ++++++++---- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'virt') diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index b66001f8754c..53850177163f 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -120,8 +120,10 @@ int kvm_coalesced_mmio_init(struct kvm *kvm) return ret; out_free_dev: + kvm->coalesced_mmio_dev = NULL; kfree(dev); out_free_page: + kvm->coalesced_mmio_ring = NULL; __free_page(page); out_err: return ret; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0db6dfcc8420..55a5d4804499 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -422,9 +422,6 @@ static struct kvm *kvm_create_vm(void) spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); spin_unlock(&kvm_lock); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - kvm_coalesced_mmio_init(kvm); -#endif out: return kvm; @@ -1753,12 +1750,19 @@ static struct file_operations kvm_vm_fops = { static int kvm_dev_ioctl_create_vm(void) { - int fd; + int fd, r; struct kvm *kvm; kvm = kvm_create_vm(); if (IS_ERR(kvm)) return PTR_ERR(kvm); +#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET + r = kvm_coalesced_mmio_init(kvm); + if (r < 0) { + kvm_put_kvm(kvm); + return r; + } +#endif fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (fd < 0) kvm_put_kvm(kvm); -- cgit v1.2.3 From 660c22c425cbe14badfb3b0a0206862577701ab7 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 13 Apr 2010 22:47:24 +0900 Subject: KVM: limit the number of pages per memory slot This patch limits the number of pages per memory slot to make us free from extra care about type issues. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- virt/kvm/kvm_main.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 55a5d4804499..d6351a34b297 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -557,6 +557,10 @@ int __kvm_set_memory_region(struct kvm *kvm, base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; + r = -EINVAL; + if (npages > KVM_MEM_MAX_NR_PAGES) + goto out; + if (!npages) mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; @@ -1187,13 +1191,10 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) memslot = gfn_to_memslot_unaliased(kvm, gfn); if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; - unsigned long *p = memslot->dirty_bitmap + - rel_gfn / BITS_PER_LONG; - int offset = rel_gfn % BITS_PER_LONG; /* avoid RMW */ - if (!generic_test_le_bit(offset, p)) - generic___set_le_bit(offset, p); + if (!generic_test_le_bit(rel_gfn, memslot->dirty_bitmap)) + generic___set_le_bit(rel_gfn, memslot->dirty_bitmap); } } -- cgit v1.2.3 From 90d83dc3d49f5101addae962ccc1b4aff66b68d8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Mon, 19 Apr 2010 17:41:23 +0800 Subject: KVM: use the correct RCU API for PROVE_RCU=y The RCU/SRCU API have already changed for proving RCU usage. I got the following dmesg when PROVE_RCU=y because we used incorrect API. This patch coverts rcu_deference() to srcu_dereference() or family API. =================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- arch/x86/kvm/mmu.c:3020 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 2 locks held by qemu-system-x86/8550: #0: (&kvm->slots_lock){+.+.+.}, at: [] kvm_set_memory_region+0x29/0x50 [kvm] #1: (&(&kvm->mmu_lock)->rlock){+.+...}, at: [] kvm_arch_commit_memory_region+0xa6/0xe2 [kvm] stack backtrace: Pid: 8550, comm: qemu-system-x86 Not tainted 2.6.34-rc4-tip-01028-g939eab1 #27 Call Trace: [] lockdep_rcu_dereference+0xaa/0xb3 [] kvm_mmu_calculate_mmu_pages+0x44/0x7d [kvm] [] kvm_arch_commit_memory_region+0xb7/0xe2 [kvm] [] __kvm_set_memory_region+0x636/0x6e2 [kvm] [] kvm_set_memory_region+0x37/0x50 [kvm] [] vmx_set_tss_addr+0x46/0x5a [kvm_intel] [] kvm_arch_vm_ioctl+0x17a/0xcf8 [kvm] [] ? unlock_page+0x27/0x2c [] ? __do_fault+0x3a9/0x3e1 [] kvm_vm_ioctl+0x364/0x38d [kvm] [] ? up_read+0x23/0x3d [] vfs_ioctl+0x32/0xa6 [] do_vfs_ioctl+0x495/0x4db [] ? fget_light+0xc2/0x241 [] ? do_sys_open+0x104/0x116 [] ? retint_swapgs+0xe/0x13 [] sys_ioctl+0x47/0x6a [] system_call_fastpath+0x16/0x1b Signed-off-by: Lai Jiangshan Signed-off-by: Avi Kivity --- virt/kvm/iommu.c | 4 ++-- virt/kvm/kvm_main.c | 13 ++++++++----- 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'virt') diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 80fd3ad3b2de..37ca71ebdba8 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -78,7 +78,7 @@ static int kvm_iommu_map_memslots(struct kvm *kvm) int i, r = 0; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; i++) { r = kvm_iommu_map_pages(kvm, &slots->memslots[i]); @@ -217,7 +217,7 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm) int i; struct kvm_memslots *slots; - slots = rcu_dereference(kvm->memslots); + slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; i++) { kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d6351a34b297..4901ec5061ba 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -834,7 +834,7 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva); struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memslots *slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; ++i) { struct kvm_memory_slot *memslot = &slots->memslots[i]; @@ -856,7 +856,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memslots *slots = kvm_memslots(kvm); gfn = unalias_gfn_instantiation(kvm, gfn); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { @@ -900,7 +900,7 @@ out: int memslot_id(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = NULL; gfn = unalias_gfn(kvm, gfn); @@ -1994,7 +1994,9 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { int i; - struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); + struct kvm_io_bus *bus; + + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_write(bus->devs[i], addr, len, val)) return 0; @@ -2006,8 +2008,9 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { int i; - struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); + struct kvm_io_bus *bus; + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_read(bus->devs[i], addr, len, val)) return 0; -- cgit v1.2.3 From 66cbff59a16017234ea6c80ecddfc17b27a83504 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sat, 17 Apr 2010 17:00:19 +0800 Subject: KVM: do not call hardware_disable() on CPU_UP_CANCELED When CPU_UP_CANCELED, hardware_enable() has not been called at the CPU which is going up because raw_notifier_call_chain(CPU_ONLINE) has not been called for this cpu. Drop the handling for CPU_UP_CANCELED. Signed-off-by: Lai Jiangshan Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4901ec5061ba..6dc940455e8b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1931,11 +1931,6 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, cpu); hardware_disable(NULL); break; - case CPU_UP_CANCELED: - printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", - cpu); - smp_call_function_single(cpu, hardware_disable, NULL, 1); - break; case CPU_ONLINE: printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", cpu); -- cgit v1.2.3 From d14769377a247d4e7b570592a090474c8a059938 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Fri, 23 Apr 2010 17:48:35 +0900 Subject: KVM: Remove test-before-set optimization for dirty bits As Avi pointed out, testing bit part in mark_page_dirty() was important in the days of shadow paging, but currently EPT and NPT has already become common and the chance of faulting a page more that once per iteration is small. So let's remove the test bit to avoid extra access. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6dc940455e8b..9ab1a77941ef 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1192,9 +1192,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn) if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; - /* avoid RMW */ - if (!generic_test_le_bit(rel_gfn, memslot->dirty_bitmap)) - generic___set_le_bit(rel_gfn, memslot->dirty_bitmap); + generic___set_le_bit(rel_gfn, memslot->dirty_bitmap); } } -- cgit v1.2.3 From 0ee75bead83da4791e5cbf659806c54d8ee40f12 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 28 Apr 2010 15:39:01 +0300 Subject: KVM: Let vcpu structure alignment be determined at runtime vmx and svm vcpus have different contents and therefore may have different alignmment requirements. Let each specify its required alignment. Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'virt') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9ab1a77941ef..f032806a212f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2178,7 +2178,7 @@ static void kvm_sched_out(struct preempt_notifier *pn, kvm_arch_vcpu_put(vcpu); } -int kvm_init(void *opaque, unsigned int vcpu_size, +int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module) { int r; @@ -2228,8 +2228,9 @@ int kvm_init(void *opaque, unsigned int vcpu_size, goto out_free_4; /* A kmem cache lets us meet the alignment requirements of fx_save. */ - kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, - __alignof__(struct kvm_vcpu), + if (!vcpu_align) + vcpu_align = __alignof__(struct kvm_vcpu); + kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align, 0, NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; -- cgit v1.2.3