From a13007160f1b9ec7c67e28ec9254f197c5c08d7d Mon Sep 17 00:00:00 2001 From: Amos Kong Date: Fri, 9 Mar 2012 12:17:32 +0800 Subject: KVM: resize kvm_io_range array dynamically This patch makes the kvm_io_range array can be resized dynamically. Signed-off-by: Amos Kong Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 665a260c7e09..ba9fb4a9762d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -68,10 +68,11 @@ struct kvm_io_range { struct kvm_io_device *dev; }; +#define NR_IOBUS_DEVS 300 + struct kvm_io_bus { int dev_count; -#define NR_IOBUS_DEVS 300 - struct kvm_io_range range[NR_IOBUS_DEVS]; + struct kvm_io_range range[]; }; enum kvm_bus { -- cgit From 786a9f888bfbe70a36d0592b26037ca1e8c8da7f Mon Sep 17 00:00:00 2001 From: Amos Kong Date: Fri, 9 Mar 2012 12:17:40 +0800 Subject: KVM: set upper bounds for iobus dev to limit userspace kvm_io_bus devices are used for ioevent, pit, pic, ioapic, coalesced_mmio. Currently Qemu only emulates one PCI bus, it contains 32 slots, one slot contains 8 functions, maximum of supported PCI devices: 1 * 32 * 8 = 256. One virtio-blk takes one iobus device, one virtio-net(vhost=on) takes two iobus devices. The maximum of coalesced mmio zone is 100, each zone has an iobus devices. So 300 io_bus devices are not enough. Set an upper bounds for kvm_io_range to limit userspace. 1000 is a very large limit and not bloat the typical user. Signed-off-by: Amos Kong Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ba9fb4a9762d..3a2cea616283 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -68,7 +68,7 @@ struct kvm_io_range { struct kvm_io_device *dev; }; -#define NR_IOBUS_DEVS 300 +#define NR_IOBUS_DEVS 1000 struct kvm_io_bus { int dev_count; -- cgit From b6d33834bd4e8bdf4a199812e31b3e36da53c794 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Thu, 8 Mar 2012 16:44:24 -0500 Subject: KVM: Factor out kvm_vcpu_kick to arch-generic code The kvm_vcpu_kick function performs roughly the same funcitonality on most all architectures, so we shouldn't have separate copies. PowerPC keeps a pointer to interchanging waitqueues on the vcpu_arch structure and to accomodate this special need a __KVM_HAVE_ARCH_VCPU_GET_WQ define and accompanying function kvm_arch_vcpu_wq have been defined. For all other architectures this is a generic inline that just returns &vcpu->wq; Acked-by: Scott Wood Signed-off-by: Christoffer Dall Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm_host.h | 1 + arch/ia64/kvm/kvm-ia64.c | 20 +++++--------------- arch/powerpc/include/asm/kvm_host.h | 6 ++++++ arch/powerpc/kvm/powerpc.c | 21 ++++++--------------- arch/s390/kvm/kvm-s390.c | 8 ++++++++ arch/x86/kvm/x86.c | 16 ++-------------- include/linux/kvm_host.h | 9 +++++++++ virt/kvm/kvm_main.c | 22 ++++++++++++++++++++++ 8 files changed, 59 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index e35b3a84a40b..c4b4bac3d09e 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -365,6 +365,7 @@ struct thash_cb { }; struct kvm_vcpu_stat { + u32 halt_wakeup; }; struct kvm_vcpu_arch { diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index f5104b7c52cd..9d80ff8d9eff 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1872,21 +1872,6 @@ void kvm_arch_hardware_unsetup(void) { } -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) -{ - int me; - int cpu = vcpu->cpu; - - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); - - me = get_cpu(); - if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu)) - if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests)) - smp_send_reschedule(cpu); - put_cpu(); -} - int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) { return __apic_accept_irq(vcpu, irq->vector); @@ -1956,6 +1941,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) (kvm_highest_pending_irq(vcpu) != -1); } +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + return (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests)); +} + int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 52eb9c1f4fe0..889383735e73 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -498,4 +498,10 @@ struct kvm_vcpu_arch { #define KVM_MMIO_REG_QPR 0x0040 #define KVM_MMIO_REG_FQPR 0x0060 +#define __KVM_HAVE_ARCH_VCPU_GET_WQ 1 +static inline wait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.wqp; +} + #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 00d7e345b3fe..b5e9046462fd 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -43,6 +43,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) v->requests; } +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + return 1; +} + int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) { int nr = kvmppc_get_gpr(vcpu, 11); @@ -588,21 +593,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) return r; } -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) -{ - int me; - int cpu = vcpu->cpu; - - me = get_cpu(); - if (waitqueue_active(vcpu->arch.wqp)) { - wake_up_interruptible(vcpu->arch.wqp); - vcpu->stat.halt_wakeup++; - } else if (cpu != me && cpu != -1) { - smp_send_reschedule(vcpu->cpu); - } - put_cpu(); -} - int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { if (irq->irq == KVM_INTERRUPT_UNSET) { @@ -611,6 +601,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) } kvmppc_core_queue_external(vcpu, irq); + kvm_vcpu_kick(vcpu); return 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 217ce44395a4..d30c8350b949 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -423,6 +423,14 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) return 0; } +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + /* kvm common code refers to this, but never calls it */ + BUG(); + return 0; +} + + static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) { kvm_s390_vcpu_initial_reset(vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4044ce0bf7c1..511031dcb9cc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6403,21 +6403,9 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) kvm_cpu_has_interrupt(vcpu)); } -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { - int me; - int cpu = vcpu->cpu; - - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); - ++vcpu->stat.halt_wakeup; - } - - me = get_cpu(); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE) - smp_send_reschedule(cpu); - put_cpu(); + return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3a2cea616283..5b624e1ff814 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -439,6 +439,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_kick(struct kvm_vcpu *vcpu); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); void kvm_resched(struct kvm_vcpu *vcpu); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); @@ -507,6 +508,7 @@ int kvm_arch_hardware_setup(void); void kvm_arch_hardware_unsetup(void); void kvm_arch_check_processor_compat(void *rtn); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); void kvm_free_physmem(struct kvm *kvm); @@ -522,6 +524,13 @@ static inline void kvm_arch_free_vm(struct kvm *kvm) } #endif +#ifndef __KVM_HAVE_ARCH_VCPU_GET_WQ +static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +{ + return &vcpu->wq; +} +#endif + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_free_all_assigned_devices(struct kvm *kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a9565e240636..7149a2e65524 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1514,6 +1514,28 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) finish_wait(&vcpu->wq, &wait); } +/* + * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. + */ +void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +{ + int me; + int cpu = vcpu->cpu; + wait_queue_head_t *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); + if (waitqueue_active(wqp)) { + wake_up_interruptible(wqp); + ++vcpu->stat.halt_wakeup; + } + + me = get_cpu(); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) + if (kvm_arch_vcpu_should_kick(vcpu)) + smp_send_reschedule(cpu); + put_cpu(); +} + void kvm_resched(struct kvm_vcpu *vcpu) { if (!need_resched()) -- cgit From 2246f8b56315befa30f3d3d2800e0734c774f70e Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 13 Mar 2012 22:35:01 +0100 Subject: KVM: PPC: Rework wqp conditional code On PowerPC, we sometimes use a waitqueue per core, not per thread, so we can't always use the vcpu internal waitqueue. This code has been generalized by Christoffer Dall recently, but unfortunately broke compilation for PowerPC. At the time the helper function is defined, struct kvm_vcpu is not declared yet, so we can't dereference it. This patch moves all logic into the generic inline function, at which time we have all information necessary. Signed-off-by: Alexander Graf Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/powerpc/include/asm/kvm_host.h | 6 +----- include/linux/kvm_host.h | 6 ++++-- 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 889383735e73..20ab5b2dbd0f 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -498,10 +498,6 @@ struct kvm_vcpu_arch { #define KVM_MMIO_REG_QPR 0x0040 #define KVM_MMIO_REG_FQPR 0x0060 -#define __KVM_HAVE_ARCH_VCPU_GET_WQ 1 -static inline wait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.wqp; -} +#define __KVM_HAVE_ARCH_WQP #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5b624e1ff814..5184817e714a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -524,12 +524,14 @@ static inline void kvm_arch_free_vm(struct kvm *kvm) } #endif -#ifndef __KVM_HAVE_ARCH_VCPU_GET_WQ static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) { +#ifdef __KVM_HAVE_ARCH_WQP + return vcpu->arch.wqp; +#else return &vcpu->wq; -} #endif +} int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); -- cgit From 1c0b28c2a46d98cd258d96b8c222144b22876c46 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Sat, 10 Mar 2012 14:37:27 -0500 Subject: KVM: x86: Add ioctl for KVM_KVMCLOCK_CTRL Now that we have a flag that will tell the guest it was suspended, create an interface for that communication using a KVM ioctl. Signed-off-by: Eric B Munson Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- Documentation/virtual/kvm/api.txt | 20 ++++++++++++++++++++ Documentation/virtual/kvm/msr.txt | 4 ++++ arch/x86/kvm/x86.c | 22 ++++++++++++++++++++++ include/linux/kvm.h | 3 +++ 4 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 6386f8c0482e..81ff39f6248d 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1669,6 +1669,26 @@ at the memory location pointed to by "addr". The list of registers accessible using this interface is identical to the list in 4.64. +4.70 KVM_KVMCLOCK_CTRL + +Capability: KVM_CAP_KVMCLOCK_CTRL +Architectures: Any that implement pvclocks (currently x86 only) +Type: vcpu ioctl +Parameters: None +Returns: 0 on success, -1 on error + +This signals to the host kernel that the specified guest is being paused by +userspace. The host will set a flag in the pvclock structure that is checked +from the soft lockup watchdog. The flag is part of the pvclock structure that +is shared between guest and host, specifically the second bit of the flags +field of the pvclock_vcpu_time_info structure. It will be set exclusively by +the host and read/cleared exclusively by the guest. The guest operation of +checking and clearing the flag must an atomic operation so +load-link/store-conditional, or equivalent must be used. There are two cases +where the guest will clear the flag: when the soft lockup watchdog timer resets +itself or when a soft lockup is detected. This ioctl can be called any time +after pausing the vcpu, but before it is resumed. + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt index 50317809113d..96b41bd97523 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virtual/kvm/msr.txt @@ -108,6 +108,10 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 | | time measures taken across 0 | 24 | multiple cpus are guaranteed to | | be monotonic + ------------------------------------------------------------- + | | guest vcpu has been paused by + 1 | N/A | the host + | | See 4.70 in api.txt ------------------------------------------------------------- Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 511031dcb9cc..99b738028fc0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2147,6 +2147,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_ASYNC_PF: case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_PCI_2_3: + case KVM_CAP_KVMCLOCK_CTRL: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2597,6 +2598,23 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, return r; } +/* + * kvm_set_guest_paused() indicates to the guest kernel that it has been + * stopped by the hypervisor. This function will be called from the host only. + * EINVAL is returned when the host attempts to set the flag for a guest that + * does not support pv clocks. + */ +static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) +{ + struct pvclock_vcpu_time_info *src = &vcpu->arch.hv_clock; + if (!vcpu->arch.time_page) + return -EINVAL; + src->flags |= PVCLOCK_GUEST_STOPPED; + mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT); + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2873,6 +2891,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = vcpu->arch.virtual_tsc_khz; goto out; } + case KVM_KVMCLOCK_CTRL: { + r = kvm_set_guest_paused(vcpu); + goto out; + } default: r = -EINVAL; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 6c322a90b92f..7a9dd4b3dede 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -589,6 +589,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_S390_UCONTROL 73 #define KVM_CAP_SYNC_REGS 74 #define KVM_CAP_PCI_2_3 75 +#define KVM_CAP_KVMCLOCK_CTRL 76 #ifdef KVM_CAP_IRQ_ROUTING @@ -859,6 +860,8 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_ONE_REG */ #define KVM_GET_ONE_REG _IOW(KVMIO, 0xab, struct kvm_one_reg) #define KVM_SET_ONE_REG _IOW(KVMIO, 0xac, struct kvm_one_reg) +/* VM is being stopped by host */ +#define KVM_KVMCLOCK_CTRL _IO(KVMIO, 0xad) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -- cgit From 93474b25af1eabf5b14743793156e8d307bfcd6b Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Thu, 1 Mar 2012 19:34:45 +0900 Subject: KVM: Remove unused dirty_bitmap_head and nr_dirty_pages Now that we do neither double buffering nor heuristic selection of the write protection method these are not needed anymore. Note: some drivers have their own implementation of set_bit_le() and making it generic needs a bit of work; so we use test_and_set_bit_le() and will later replace it with generic set_bit_le(). Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 -- virt/kvm/kvm_main.c | 14 +++++--------- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5184817e714a..49c2f2fd281f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -179,8 +179,6 @@ struct kvm_memory_slot { unsigned long flags; unsigned long *rmap; unsigned long *dirty_bitmap; - unsigned long *dirty_bitmap_head; - unsigned long nr_dirty_pages; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; int user_alloc; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a612bc8c921c..6bd34a6ecca1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -522,12 +522,11 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) return; if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE) - vfree(memslot->dirty_bitmap_head); + vfree(memslot->dirty_bitmap); else - kfree(memslot->dirty_bitmap_head); + kfree(memslot->dirty_bitmap); memslot->dirty_bitmap = NULL; - memslot->dirty_bitmap_head = NULL; } /* @@ -611,8 +610,7 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) /* * Allocation size is twice as large as the actual dirty bitmap size. - * This makes it possible to do double buffering: see x86's - * kvm_vm_ioctl_get_dirty_log(). + * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed. */ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) { @@ -627,8 +625,6 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) if (!memslot->dirty_bitmap) return -ENOMEM; - memslot->dirty_bitmap_head = memslot->dirty_bitmap; - memslot->nr_dirty_pages = 0; #endif /* !CONFIG_S390 */ return 0; } @@ -1476,8 +1472,8 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; - if (!test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap)) - memslot->nr_dirty_pages++; + /* TODO: introduce set_bit_le() and use it */ + test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap); } } -- cgit From f78146b0f9230765c6315b2e14f56112513389ad Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 18 Apr 2012 19:22:47 +0300 Subject: KVM: Fix page-crossing MMIO MMIO that are split across a page boundary are currently broken - the code does not expect to be aborted by the exit to userspace for the first MMIO fragment. This patch fixes the problem by generalizing the current code for handling 16-byte MMIOs to handle a number of "fragments", and changes the MMIO code to create those fragments. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/ia64/include/asm/kvm_host.h | 2 + arch/ia64/kvm/kvm-ia64.c | 10 ++-- arch/x86/kvm/x86.c | 114 +++++++++++++++++++++++++++------------ include/linux/kvm_host.h | 31 +++++++++-- 4 files changed, 115 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index c4b4bac3d09e..6d6a5ac48d85 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -449,6 +449,8 @@ struct kvm_vcpu_arch { char log_buf[VMM_LOG_LEN]; union context host; union context guest; + + char mmio_data[8]; }; struct kvm_vm_stat { diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 9d80ff8d9eff..882ab21a8dcd 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -232,12 +232,12 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if ((p->addr & PAGE_MASK) == IOAPIC_DEFAULT_BASE_ADDRESS) goto mmio; vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = kvm_run->mmio.phys_addr = p->addr; - vcpu->mmio_size = kvm_run->mmio.len = p->size; + vcpu->mmio_fragments[0].gpa = kvm_run->mmio.phys_addr = p->addr; + vcpu->mmio_fragments[0].len = kvm_run->mmio.len = p->size; vcpu->mmio_is_write = kvm_run->mmio.is_write = !p->dir; if (vcpu->mmio_is_write) - memcpy(vcpu->mmio_data, &p->data, p->size); + memcpy(vcpu->arch.mmio_data, &p->data, p->size); memcpy(kvm_run->mmio.data, &p->data, p->size); kvm_run->exit_reason = KVM_EXIT_MMIO; return 0; @@ -719,7 +719,7 @@ static void kvm_set_mmio_data(struct kvm_vcpu *vcpu) struct kvm_mmio_req *p = kvm_get_vcpu_ioreq(vcpu); if (!vcpu->mmio_is_write) - memcpy(&p->data, vcpu->mmio_data, 8); + memcpy(&p->data, vcpu->arch.mmio_data, 8); p->state = STATE_IORESP_READY; } @@ -739,7 +739,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } if (vcpu->mmio_needed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); + memcpy(vcpu->arch.mmio_data, kvm_run->mmio.data, 8); kvm_set_mmio_data(vcpu); vcpu->mmio_read_completed = 1; vcpu->mmio_needed = 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0d9a57875f0b..4de705cdcafd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3718,9 +3718,8 @@ struct read_write_emulator_ops { static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) { if (vcpu->mmio_read_completed) { - memcpy(val, vcpu->mmio_data, bytes); trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, - vcpu->mmio_phys_addr, *(u64 *)val); + vcpu->mmio_fragments[0].gpa, *(u64 *)val); vcpu->mmio_read_completed = 0; return 1; } @@ -3756,8 +3755,9 @@ static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { - memcpy(vcpu->mmio_data, val, bytes); - memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0]; + + memcpy(vcpu->run->mmio.data, frag->data, frag->len); return X86EMUL_CONTINUE; } @@ -3784,10 +3784,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, gpa_t gpa; int handled, ret; bool write = ops->write; - - if (ops->read_write_prepare && - ops->read_write_prepare(vcpu, val, bytes)) - return X86EMUL_CONTINUE; + struct kvm_mmio_fragment *frag; ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); @@ -3813,15 +3810,19 @@ mmio: bytes -= handled; val += handled; - vcpu->mmio_needed = 1; - vcpu->run->exit_reason = KVM_EXIT_MMIO; - vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->run->mmio.len = min(vcpu->mmio_size, 8); - vcpu->run->mmio.is_write = vcpu->mmio_is_write = write; - vcpu->mmio_index = 0; + while (bytes) { + unsigned now = min(bytes, 8U); - return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); + frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++]; + frag->gpa = gpa; + frag->data = val; + frag->len = now; + + gpa += now; + val += now; + bytes -= now; + } + return X86EMUL_CONTINUE; } int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, @@ -3830,10 +3831,18 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, struct read_write_emulator_ops *ops) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + gpa_t gpa; + int rc; + + if (ops->read_write_prepare && + ops->read_write_prepare(vcpu, val, bytes)) + return X86EMUL_CONTINUE; + + vcpu->mmio_nr_fragments = 0; /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { - int rc, now; + int now; now = -addr & ~PAGE_MASK; rc = emulator_read_write_onepage(addr, val, now, exception, @@ -3846,8 +3855,25 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, bytes -= now; } - return emulator_read_write_onepage(addr, val, bytes, exception, - vcpu, ops); + rc = emulator_read_write_onepage(addr, val, bytes, exception, + vcpu, ops); + if (rc != X86EMUL_CONTINUE) + return rc; + + if (!vcpu->mmio_nr_fragments) + return rc; + + gpa = vcpu->mmio_fragments[0].gpa; + + vcpu->mmio_needed = 1; + vcpu->mmio_cur_fragment = 0; + + vcpu->run->mmio.len = vcpu->mmio_fragments[0].len; + vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write; + vcpu->run->exit_reason = KVM_EXIT_MMIO; + vcpu->run->mmio.phys_addr = gpa; + + return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); } static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, @@ -5446,33 +5472,55 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) return r; } +/* + * Implements the following, as a state machine: + * + * read: + * for each fragment + * write gpa, len + * exit + * copy data + * execute insn + * + * write: + * for each fragment + * write gpa, len + * copy data + * exit + */ static int complete_mmio(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; + struct kvm_mmio_fragment *frag; int r; if (!(vcpu->arch.pio.count || vcpu->mmio_needed)) return 1; if (vcpu->mmio_needed) { - vcpu->mmio_needed = 0; + /* Complete previous fragment */ + frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++]; if (!vcpu->mmio_is_write) - memcpy(vcpu->mmio_data + vcpu->mmio_index, - run->mmio.data, 8); - vcpu->mmio_index += 8; - if (vcpu->mmio_index < vcpu->mmio_size) { - run->exit_reason = KVM_EXIT_MMIO; - run->mmio.phys_addr = vcpu->mmio_phys_addr + vcpu->mmio_index; - memcpy(run->mmio.data, vcpu->mmio_data + vcpu->mmio_index, 8); - run->mmio.len = min(vcpu->mmio_size - vcpu->mmio_index, 8); - run->mmio.is_write = vcpu->mmio_is_write; - vcpu->mmio_needed = 1; - return 0; + memcpy(frag->data, run->mmio.data, frag->len); + if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) { + vcpu->mmio_needed = 0; + if (vcpu->mmio_is_write) + return 1; + vcpu->mmio_read_completed = 1; + goto done; } + /* Initiate next fragment */ + ++frag; + run->exit_reason = KVM_EXIT_MMIO; + run->mmio.phys_addr = frag->gpa; if (vcpu->mmio_is_write) - return 1; - vcpu->mmio_read_completed = 1; + memcpy(run->mmio.data, frag->data, frag->len); + run->mmio.len = frag->len; + run->mmio.is_write = vcpu->mmio_is_write; + return 0; + } +done: vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a2d00b1bbf54..186ffab0b9f0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -34,6 +34,20 @@ #define KVM_MMIO_SIZE 8 #endif +/* + * If we support unaligned MMIO, at most one fragment will be split into two: + */ +#ifdef KVM_UNALIGNED_MMIO +# define KVM_EXTRA_MMIO_FRAGMENTS 1 +#else +# define KVM_EXTRA_MMIO_FRAGMENTS 0 +#endif + +#define KVM_USER_MMIO_SIZE 8 + +#define KVM_MAX_MMIO_FRAGMENTS \ + (KVM_MMIO_SIZE / KVM_USER_MMIO_SIZE + KVM_EXTRA_MMIO_FRAGMENTS) + /* * vcpu->requests bit members */ @@ -117,6 +131,16 @@ enum { EXITING_GUEST_MODE }; +/* + * Sometimes a large or cross-page mmio needs to be broken up into separate + * exits for userspace servicing. + */ +struct kvm_mmio_fragment { + gpa_t gpa; + void *data; + unsigned len; +}; + struct kvm_vcpu { struct kvm *kvm; #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -144,10 +168,9 @@ struct kvm_vcpu { int mmio_needed; int mmio_read_completed; int mmio_is_write; - int mmio_size; - int mmio_index; - unsigned char mmio_data[KVM_MMIO_SIZE]; - gpa_t mmio_phys_addr; + int mmio_cur_fragment; + int mmio_nr_fragments; + struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS]; #endif #ifdef CONFIG_KVM_ASYNC_PF -- cgit From 07975ad3b30579ca27d880491ad992326b930c63 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Thu, 29 Mar 2012 21:14:12 +0200 Subject: KVM: Introduce direct MSI message injection for in-kernel irqchips Currently, MSI messages can only be injected to in-kernel irqchips by defining a corresponding IRQ route for each message. This is not only unhandy if the MSI messages are generated "on the fly" by user space, IRQ routes are a limited resource that user space has to manage carefully. By providing a direct injection path, we can both avoid using up limited resources and simplify the necessary steps for user land. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- Documentation/virtual/kvm/api.txt | 21 +++++++++++++++++++++ arch/x86/kvm/Kconfig | 1 + include/linux/kvm.h | 11 +++++++++++ include/linux/kvm_host.h | 2 ++ virt/kvm/Kconfig | 3 +++ virt/kvm/irq_comm.c | 14 ++++++++++++++ virt/kvm/kvm_main.c | 14 ++++++++++++++ 7 files changed, 66 insertions(+) (limited to 'include/linux') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 81ff39f6248d..a1552210b16d 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1689,6 +1689,27 @@ where the guest will clear the flag: when the soft lockup watchdog timer resets itself or when a soft lockup is detected. This ioctl can be called any time after pausing the vcpu, but before it is resumed. +4.71 KVM_SIGNAL_MSI + +Capability: KVM_CAP_SIGNAL_MSI +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_msi (in) +Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error + +Directly inject a MSI message. Only valid with in-kernel irqchip that handles +MSI messages. + +struct kvm_msi { + __u32 address_lo; + __u32 address_hi; + __u32 data; + __u32 flags; + __u8 pad[16]; +}; + +No flags are defined so far. The corresponding field must be 0. + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 1a7fe868f375..a28f338843ea 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -36,6 +36,7 @@ config KVM select TASKSTATS select TASK_DELAY_ACCT select PERF_EVENTS + select HAVE_KVM_MSI ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 7a9dd4b3dede..225b452e1d1d 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -590,6 +590,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_SYNC_REGS 74 #define KVM_CAP_PCI_2_3 75 #define KVM_CAP_KVMCLOCK_CTRL 76 +#define KVM_CAP_SIGNAL_MSI 77 #ifdef KVM_CAP_IRQ_ROUTING @@ -715,6 +716,14 @@ struct kvm_one_reg { __u64 addr; }; +struct kvm_msi { + __u32 address_lo; + __u32 address_hi; + __u32 data; + __u32 flags; + __u8 pad[16]; +}; + /* * ioctls for VM fds */ @@ -789,6 +798,8 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_PCI_2_3 */ #define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \ struct kvm_assigned_pci_dev) +/* Available with KVM_CAP_SIGNAL_MSI */ +#define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi) /* * ioctls for vcpu fds diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 186ffab0b9f0..6f343307d72b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -802,6 +802,8 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned flags); void kvm_free_irq_routing(struct kvm *kvm); +int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); + #else static inline void kvm_free_irq_routing(struct kvm *kvm) {} diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index f63ccb0a5982..28694f4a9139 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -18,3 +18,6 @@ config KVM_MMIO config KVM_ASYNC_PF bool + +config HAVE_KVM_MSI + bool diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 9f614b4e365f..a6a0365475ed 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -138,6 +138,20 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq); } +int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) +{ + struct kvm_kernel_irq_routing_entry route; + + if (!irqchip_in_kernel(kvm) || msi->flags != 0) + return -EINVAL; + + route.msi.address_lo = msi->address_lo; + route.msi.address_hi = msi->address_hi; + route.msi.data = msi->data; + + return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1); +} + /* * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9eb7936e491d..1847c762d8d9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2059,6 +2059,17 @@ static long kvm_vm_ioctl(struct file *filp, kvm->bsp_vcpu_id = arg; mutex_unlock(&kvm->lock); break; +#endif +#ifdef CONFIG_HAVE_KVM_MSI + case KVM_SIGNAL_MSI: { + struct kvm_msi msi; + + r = -EFAULT; + if (copy_from_user(&msi, argp, sizeof msi)) + goto out; + r = kvm_send_userspace_msi(kvm, &msi); + break; + } #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); @@ -2188,6 +2199,9 @@ static long kvm_dev_ioctl_check_extension_generic(long arg) case KVM_CAP_SET_BOOT_CPU_ID: #endif case KVM_CAP_INTERNAL_ERROR_DATA: +#ifdef CONFIG_HAVE_KVM_MSI + case KVM_CAP_SIGNAL_MSI: +#endif return 1; #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQ_ROUTING: -- cgit From 41628d334361670d825fb03c04568f5ef9f084dc Mon Sep 17 00:00:00 2001 From: Konstantin Weitz Date: Wed, 25 Apr 2012 15:30:38 +0200 Subject: KVM: s390: Implement the directed yield (diag 9c) hypervisor call for KVM This patch implements the directed yield hypercall found on other System z hypervisors. It delegates execution time to the virtual cpu specified in the instruction's parameter. Useful to avoid long spinlock waits in the guest. Christian Borntraeger: moved common code in virt/kvm/ Signed-off-by: Konstantin Weitz Signed-off-by: Christian Borntraeger Signed-off-by: Marcelo Tosatti --- arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kvm/diag.c | 25 ++++++++++++++++++++++++ arch/s390/kvm/kvm-s390.c | 1 + include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 42 +++++++++++++++++++++++++--------------- 5 files changed, 54 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 7343872890a2..dd17537b9a9d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -148,6 +148,7 @@ struct kvm_vcpu_stat { u32 instruction_sigp_restart; u32 diagnose_10; u32 diagnose_44; + u32 diagnose_9c; }; struct kvm_s390_io_info { diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index a353f0ea45c2..2d2ae327b747 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -53,6 +53,29 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu) return 0; } +static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *tcpu; + int tid; + int i; + + tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; + vcpu->stat.diagnose_9c++; + VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid); + + if (tid == vcpu->vcpu_id) + return 0; + + kvm_for_each_vcpu(i, tcpu, kvm) + if (tcpu->vcpu_id == tid) { + kvm_vcpu_yield_to(tcpu); + break; + } + + return 0; +} + static int __diag_ipl_functions(struct kvm_vcpu *vcpu) { unsigned int reg = vcpu->arch.sie_block->ipa & 0xf; @@ -89,6 +112,8 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) return diag_release_pages(vcpu); case 0x44: return __diag_time_slice_end(vcpu); + case 0x9c: + return __diag_time_slice_end_directed(vcpu); case 0x308: return __diag_ipl_functions(vcpu); default: diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d30c8350b949..fd98914a36f1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -74,6 +74,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, { "diagnose_10", VCPU_STAT(diagnose_10) }, { "diagnose_44", VCPU_STAT(diagnose_44) }, + { "diagnose_9c", VCPU_STAT(diagnose_9c) }, { NULL } }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6f343307d72b..cae342d29d1b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -461,6 +461,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, void kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); +bool kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); void kvm_resched(struct kvm_vcpu *vcpu); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1847c762d8d9..7e140683ff14 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1543,6 +1543,31 @@ void kvm_resched(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_resched); +bool kvm_vcpu_yield_to(struct kvm_vcpu *target) +{ + struct pid *pid; + struct task_struct *task = NULL; + + rcu_read_lock(); + pid = rcu_dereference(target->pid); + if (pid) + task = get_pid_task(target->pid, PIDTYPE_PID); + rcu_read_unlock(); + if (!task) + return false; + if (task->flags & PF_VCPU) { + put_task_struct(task); + return false; + } + if (yield_to(task, 1)) { + put_task_struct(task); + return true; + } + put_task_struct(task); + return false; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); + void kvm_vcpu_on_spin(struct kvm_vcpu *me) { struct kvm *kvm = me->kvm; @@ -1561,8 +1586,6 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me) */ for (pass = 0; pass < 2 && !yielded; pass++) { kvm_for_each_vcpu(i, vcpu, kvm) { - struct task_struct *task = NULL; - struct pid *pid; if (!pass && i < last_boosted_vcpu) { i = last_boosted_vcpu; continue; @@ -1572,24 +1595,11 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me) continue; if (waitqueue_active(&vcpu->wq)) continue; - rcu_read_lock(); - pid = rcu_dereference(vcpu->pid); - if (pid) - task = get_pid_task(vcpu->pid, PIDTYPE_PID); - rcu_read_unlock(); - if (!task) - continue; - if (task->flags & PF_VCPU) { - put_task_struct(task); - continue; - } - if (yield_to(task, 1)) { - put_task_struct(task); + if (kvm_vcpu_yield_to(vcpu)) { kvm->last_boosted_vcpu = i; yielded = 1; break; } - put_task_struct(task); } } } -- cgit From 5b74716ebab10e7bce960d148fe6d8f6920451e5 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 26 Apr 2012 19:43:42 +0000 Subject: kvm/powerpc: Add new ioctl to retreive server MMU infos This is necessary for qemu to be able to pass the right information to the guest, such as the supported page sizes and corresponding encodings in the SLB and hash table, which can vary depending on the processor type, the type of KVM used (PR vs HV) and the version of KVM Signed-off-by: Benjamin Herrenschmidt [agraf: fix compilation on hv, adjust for newer ioctl numbers] Signed-off-by: Alexander Graf --- Documentation/virtual/kvm/api.txt | 70 ++++++++++++++++++++++++++++++++++++++ arch/powerpc/include/asm/kvm_ppc.h | 2 ++ arch/powerpc/kernel/ppc_ksyms.c | 4 +++ arch/powerpc/kvm/book3s_hv.c | 32 +++++++++++++++++ arch/powerpc/kvm/book3s_pr.c | 25 ++++++++++++++ arch/powerpc/kvm/powerpc.c | 18 +++++++++- include/linux/kvm.h | 27 +++++++++++++++ 7 files changed, 177 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index eb62761b7683..930126698a0f 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1860,6 +1860,76 @@ See KVM_GET_PIT2 for details on struct kvm_pit_state2. This IOCTL replaces the obsolete KVM_SET_PIT. +4.74 KVM_PPC_GET_SMMU_INFO + +Capability: KVM_CAP_PPC_GET_SMMU_INFO +Architectures: powerpc +Type: vm ioctl +Parameters: None +Returns: 0 on success, -1 on error + +This populates and returns a structure describing the features of +the "Server" class MMU emulation supported by KVM. +This can in turn be used by userspace to generate the appropariate +device-tree properties for the guest operating system. + +The structure contains some global informations, followed by an +array of supported segment page sizes: + + struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u32 pad; + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; + }; + +The supported flags are: + + - KVM_PPC_PAGE_SIZES_REAL: + When that flag is set, guest page sizes must "fit" the backing + store page sizes. When not set, any page size in the list can + be used regardless of how they are backed by userspace. + + - KVM_PPC_1T_SEGMENTS + The emulated MMU supports 1T segments in addition to the + standard 256M ones. + +The "slb_size" field indicates how many SLB entries are supported + +The "sps" array contains 8 entries indicating the supported base +page sizes for a segment in increasing order. Each entry is defined +as follow: + + struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; + }; + +An entry with a "page_shift" of 0 is unused. Because the array is +organized in increasing order, a lookup can stop when encoutering +such an entry. + +The "slb_enc" field provides the encoding to use in the SLB for the +page size. The bits are in positions such as the value can directly +be OR'ed into the "vsid" argument of the slbmte instruction. + +The "enc" array is a list which for each of those segment base page +size provides the list of supported actual page sizes (which can be +only larger or equal to the base page size), along with the +corresponding encoding in the hash PTE. Similarily, the array is +8 entries sorted by increasing sizes and an entry with a "0" shift +is an empty entry and a terminator: + + struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ + }; + +The "pte_enc" field provides a value that can OR'ed into the hash +PTE's RPN field (ie, it needs to be shifted left by 12 to OR it +into the hash PTE second double word). + 5. The kvm_run structure ------------------------ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c1069f63dcaf..c87e3b503fdc 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -140,6 +140,8 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem); +extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, + struct kvm_ppc_smmu_info *info); extern int kvmppc_bookehv_init(void); extern void kvmppc_bookehv_exit(void); diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 786a2700ec2d..d1f2aafcbe8c 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -190,3 +190,7 @@ EXPORT_SYMBOL(__arch_hweight16); EXPORT_SYMBOL(__arch_hweight32); EXPORT_SYMBOL(__arch_hweight64); #endif + +#ifdef CONFIG_PPC_BOOK3S_64 +EXPORT_SYMBOL_GPL(mmu_psize_defs); +#endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 59c296743595..bb5a0f4b4bbb 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1175,6 +1175,38 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret) return fd; } +static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps, + int linux_psize) +{ + struct mmu_psize_def *def = &mmu_psize_defs[linux_psize]; + + if (!def->shift) + return; + (*sps)->page_shift = def->shift; + (*sps)->slb_enc = def->sllp; + (*sps)->enc[0].page_shift = def->shift; + (*sps)->enc[0].pte_enc = def->penc; + (*sps)++; +} + +int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info) +{ + struct kvm_ppc_one_seg_page_size *sps; + + info->flags = KVM_PPC_PAGE_SIZES_REAL; + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) + info->flags |= KVM_PPC_1T_SEGMENTS; + info->slb_size = mmu_slb_size; + + /* We only support these sizes for now, and no muti-size segments */ + sps = &info->sps[0]; + kvmppc_add_seg_page_size(&sps, MMU_PAGE_4K); + kvmppc_add_seg_page_size(&sps, MMU_PAGE_64K); + kvmppc_add_seg_page_size(&sps, MMU_PAGE_16M); + + return 0; +} + /* * Get (and clear) the dirty memory log for a memory slot. */ diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 815ac5938a9e..a1baec340f7e 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1158,6 +1158,31 @@ out: return r; } +#ifdef CONFIG_PPC64 +int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info) +{ + /* No flags */ + info->flags = 0; + + /* SLB is always 64 entries */ + info->slb_size = 64; + + /* Standard 4k base page size segment */ + info->sps[0].page_shift = 12; + info->sps[0].slb_enc = 0; + info->sps[0].enc[0].page_shift = 12; + info->sps[0].enc[0].pte_enc = 0; + + /* Standard 16M large page size segment */ + info->sps[1].page_shift = 24; + info->sps[1].slb_enc = SLB_VSID_L; + info->sps[1].enc[0].page_shift = 24; + info->sps[1].enc[0].pte_enc = 0; + + return 0; +} +#endif /* CONFIG_PPC64 */ + int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem) { diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6ac31154d170..1493c8de947b 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -279,6 +279,11 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; +#ifdef CONFIG_PPC_BOOK3S_64 + case KVM_CAP_PPC_GET_SMMU_INFO: + r = 1; + break; +#endif default: r = 0; break; @@ -718,7 +723,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } #endif - default: r = -EINVAL; } @@ -800,6 +804,18 @@ long kvm_arch_vm_ioctl(struct file *filp, } #endif /* CONFIG_KVM_BOOK3S_64_HV */ +#ifdef CONFIG_PPC_BOOK3S_64 + case KVM_PPC_GET_SMMU_INFO: { + struct kvm *kvm = filp->private_data; + struct kvm_ppc_smmu_info info; + + memset(&info, 0, sizeof(info)); + r = kvm_vm_ioctl_get_smmu_info(kvm, &info); + if (r >= 0 && copy_to_user(argp, &info, sizeof(info))) + r = -EFAULT; + break; + } +#endif /* CONFIG_PPC_BOOK3S_64 */ default: r = -ENOTTY; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 225b452e1d1d..8d696cf6edcc 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -449,6 +449,30 @@ struct kvm_ppc_pvinfo { __u8 pad[108]; }; +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u32 pad; + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ @@ -591,6 +615,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_PCI_2_3 75 #define KVM_CAP_KVMCLOCK_CTRL 76 #define KVM_CAP_SIGNAL_MSI 77 +#define KVM_CAP_PPC_GET_SMMU_INFO 78 #ifdef KVM_CAP_IRQ_ROUTING @@ -800,6 +825,8 @@ struct kvm_s390_ucas_mapping { struct kvm_assigned_pci_dev) /* Available with KVM_CAP_SIGNAL_MSI */ #define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi) +/* Available with KVM_CAP_PPC_GET_SMMU_INFO */ +#define KVM_PPC_GET_SMMU_INFO _IOR(KVMIO, 0xa6, struct kvm_ppc_smmu_info) /* * ioctls for vcpu fds -- cgit From c142786c6291189b5c85f53d91743e1eefbd8fe0 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 14 May 2012 15:44:06 +0300 Subject: KVM: MMU: Don't use RCU for lockless shadow walking Using RCU for lockless shadow walking can increase the amount of memory in use by the system, since RCU grace periods are unpredictable. We also have an unconditional write to a shared variable (reader_counter), which isn't good for scaling. Replace that with a scheme similar to x86's get_user_pages_fast(): disable interrupts during lockless shadow walk to force the freer (kvm_mmu_commit_zap_page()) to wait for the TLB flush IPI to find the processor with interrupts enabled. We also add a new vcpu->mode, READING_SHADOW_PAGE_TABLES, to prevent kvm_flush_remote_tlbs() from avoiding the IPI. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_host.h | 4 --- arch/x86/kvm/mmu.c | 73 ++++++++++++++++------------------------- include/linux/kvm_host.h | 3 +- 3 files changed, 31 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 69e39bc7e36f..64c8989263f6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -240,8 +240,6 @@ struct kvm_mmu_page { #endif int write_flooding_count; - - struct rcu_head rcu; }; struct kvm_pio_request { @@ -540,8 +538,6 @@ struct kvm_arch { u64 hv_guest_os_id; u64 hv_hypercall; - atomic_t reader_counter; - #ifdef CONFIG_KVM_MMU_AUDIT int audit_point; #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 07424cf60434..72102e0ab7cb 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -551,19 +551,29 @@ static u64 mmu_spte_get_lockless(u64 *sptep) static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { - rcu_read_lock(); - atomic_inc(&vcpu->kvm->arch.reader_counter); - - /* Increase the counter before walking shadow page table */ - smp_mb__after_atomic_inc(); + /* + * Prevent page table teardown by making any free-er wait during + * kvm_flush_remote_tlbs() IPI to all active vcpus. + */ + local_irq_disable(); + vcpu->mode = READING_SHADOW_PAGE_TABLES; + /* + * Make sure a following spte read is not reordered ahead of the write + * to vcpu->mode. + */ + smp_mb(); } static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { - /* Decrease the counter after walking shadow page table finished */ - smp_mb__before_atomic_dec(); - atomic_dec(&vcpu->kvm->arch.reader_counter); - rcu_read_unlock(); + /* + * Make sure the write to vcpu->mode is not reordered in front of + * reads to sptes. If it does, kvm_commit_zap_page() can see us + * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. + */ + smp_mb(); + vcpu->mode = OUTSIDE_GUEST_MODE; + local_irq_enable(); } static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, @@ -1989,30 +1999,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, return ret; } -static void kvm_mmu_isolate_pages(struct list_head *invalid_list) -{ - struct kvm_mmu_page *sp; - - list_for_each_entry(sp, invalid_list, link) - kvm_mmu_isolate_page(sp); -} - -static void free_pages_rcu(struct rcu_head *head) -{ - struct kvm_mmu_page *next, *sp; - - sp = container_of(head, struct kvm_mmu_page, rcu); - while (sp) { - if (!list_empty(&sp->link)) - next = list_first_entry(&sp->link, - struct kvm_mmu_page, link); - else - next = NULL; - kvm_mmu_free_page(sp); - sp = next; - } -} - static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list) { @@ -2021,17 +2007,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, if (list_empty(invalid_list)) return; - kvm_flush_remote_tlbs(kvm); - - if (atomic_read(&kvm->arch.reader_counter)) { - kvm_mmu_isolate_pages(invalid_list); - sp = list_first_entry(invalid_list, struct kvm_mmu_page, link); - list_del_init(invalid_list); + /* + * wmb: make sure everyone sees our modifications to the page tables + * rmb: make sure we see changes to vcpu->mode + */ + smp_mb(); - trace_kvm_mmu_delay_free_pages(sp); - call_rcu(&sp->rcu, free_pages_rcu); - return; - } + /* + * Wait for all vcpus to exit guest mode and/or lockless shadow + * page table walks. + */ + kvm_flush_remote_tlbs(kvm); do { sp = list_first_entry(invalid_list, struct kvm_mmu_page, link); @@ -2039,7 +2025,6 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, kvm_mmu_isolate_page(sp); kvm_mmu_free_page(sp); } while (!list_empty(invalid_list)); - } /* diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cae342d29d1b..c4464356b35b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -128,7 +128,8 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, - EXITING_GUEST_MODE + EXITING_GUEST_MODE, + READING_SHADOW_PAGE_TABLES, }; /* -- cgit From 1526bf9ccf310f1d35c1275b8b477a249d25aaf2 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 15 May 2012 14:15:25 +0200 Subject: KVM: s390: add capability indicating COW support Currently qemu/kvm on s390 uses a guest mapping that does not allow the guest backing page table to be write-protected to support older systems. On those older systems a host write protection fault will be delivered to the guest. Newer systems allow to write-protect the guest backing memory and let the fault be delivered to the host, thus allowing COW. Use a capability bit to tell qemu if that is possible. Signed-off-by: Christian Borntraeger Acked-by: Heiko Carstens Signed-off-by: Marcelo Tosatti --- arch/s390/include/asm/sclp.h | 1 + arch/s390/kvm/kvm-s390.c | 4 ++++ drivers/s390/char/sclp_cmd.c | 12 +++++++++++- include/linux/kvm.h | 1 + 4 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index fed7bee650a0..bf238c55740b 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -48,6 +48,7 @@ int sclp_cpu_deconfigure(u8 cpu); void sclp_facilities_detect(void); unsigned long long sclp_get_rnmax(void); unsigned long long sclp_get_rzm(void); +u8 sclp_get_fac85(void); int sclp_sdias_blk_count(void); int sclp_sdias_copy(void *dest, int blk_num, int nr_blks); int sclp_chp_configure(struct chp_id chpid); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e5e3800b0125..5c761bffa02d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "kvm-s390.h" #include "gaccess.h" @@ -140,6 +141,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; + case KVM_CAP_S390_COW: + r = sclp_get_fac85() & 0x2; + break; default: r = 0; } diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c index 231a1d85127b..032171e335e9 100644 --- a/drivers/s390/char/sclp_cmd.c +++ b/drivers/s390/char/sclp_cmd.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -38,7 +39,8 @@ struct read_info_sccb { u64 facilities; /* 48-55 */ u8 _reserved2[84 - 56]; /* 56-83 */ u8 fac84; /* 84 */ - u8 _reserved3[91 - 85]; /* 85-90 */ + u8 fac85; /* 85 */ + u8 _reserved3[91 - 86]; /* 86-90 */ u8 flags; /* 91 */ u8 _reserved4[100 - 92]; /* 92-99 */ u32 rnsize2; /* 100-103 */ @@ -51,6 +53,7 @@ static int __initdata early_read_info_sccb_valid; u64 sclp_facilities; static u8 sclp_fac84; +static u8 sclp_fac85; static unsigned long long rzm; static unsigned long long rnmax; @@ -112,6 +115,7 @@ void __init sclp_facilities_detect(void) sccb = &early_read_info_sccb; sclp_facilities = sccb->facilities; sclp_fac84 = sccb->fac84; + sclp_fac85 = sccb->fac85; rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2; rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2; rzm <<= 20; @@ -127,6 +131,12 @@ unsigned long long sclp_get_rzm(void) return rzm; } +u8 sclp_get_fac85(void) +{ + return sclp_fac85; +} +EXPORT_SYMBOL_GPL(sclp_get_fac85); + /* * This function will be called after sclp_facilities_detect(), which gets * called from early.c code. Therefore the sccb should have valid contents. diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 8d696cf6edcc..09f2b3aa2da7 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -616,6 +616,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_KVMCLOCK_CTRL 76 #define KVM_CAP_SIGNAL_MSI 77 #define KVM_CAP_PPC_GET_SMMU_INFO 78 +#define KVM_CAP_S390_COW 79 #ifdef KVM_CAP_IRQ_ROUTING -- cgit