From bbacc0c111c3c5d1f3192b8cc1642b9c3954f80d Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:09 -0700 Subject: KVM: Rename KVM_MEMORY_SLOTS -> KVM_USER_MEM_SLOTS It's easy to confuse KVM_MEMORY_SLOTS and KVM_MEM_SLOTS_NUM. One is the user accessible slots and the other is user + private. Make this more obvious. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2c497ab0d03..abad7f30771 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -314,7 +314,7 @@ struct kvm_irq_routing_table {}; #endif #ifndef KVM_MEM_SLOTS_NUM -#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) +#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif /* -- cgit v1.2.3-70-g09d2 From 0743247fbf0c4a27185b2aa1fdda91d0745dfed1 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:15 -0700 Subject: KVM: Make KVM_PRIVATE_MEM_SLOTS optional Seems like everyone copied x86 and defined 4 private memory slots that never actually get used. Even x86 only uses 3 of the 4. These aren't exposed so there's no need to add padding. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- arch/ia64/include/asm/kvm_host.h | 2 -- arch/powerpc/include/asm/kvm_host.h | 4 +--- arch/s390/include/asm/kvm_host.h | 2 -- arch/x86/include/asm/kvm_host.h | 4 ++-- include/linux/kvm_host.h | 4 ++++ 5 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index 48d7b0e1dba..cfa74983c67 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -24,8 +24,6 @@ #define __ASM_KVM_HOST_H #define KVM_USER_MEM_SLOTS 32 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index ac19ad60ae8..ab49c6cf891 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -38,9 +38,7 @@ #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS #define KVM_USER_MEM_SLOTS 32 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 4 -#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) +#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS #ifdef CONFIG_KVM_MMIO #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index ac334326404..711c5ab391c 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -21,8 +21,6 @@ #define KVM_MAX_VCPUS 64 #define KVM_USER_MEM_SLOTS 32 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 4 struct sca_entry { atomic_t scn; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c7df6ffd243..51d52108f10 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -34,8 +34,8 @@ #define KVM_MAX_VCPUS 254 #define KVM_SOFT_MAX_VCPUS 160 #define KVM_USER_MEM_SLOTS 32 -/* memory slots that does not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 4 +/* memory slots that are not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 3 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #define KVM_MMIO_SIZE 16 diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index abad7f30771..5a3581ceb03 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -313,6 +313,10 @@ struct kvm_irq_routing_table {}; #endif +#ifndef KVM_PRIVATE_MEM_SLOTS +#define KVM_PRIVATE_MEM_SLOTS 0 +#endif + #ifndef KVM_MEM_SLOTS_NUM #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif -- cgit v1.2.3-70-g09d2 From f82a8cfe9354f5cdea55ebeceba3fd19051d3ee8 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:21 -0700 Subject: KVM: struct kvm_memory_slot.user_alloc -> bool There's no need for this to be an int, it holds a boolean. Move to the end of the struct for alignment. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 6 +++--- arch/powerpc/kvm/powerpc.c | 4 ++-- arch/s390/kvm/kvm-s390.c | 4 ++-- arch/x86/kvm/vmx.c | 6 +++--- arch/x86/kvm/x86.c | 4 ++-- include/linux/kvm_host.h | 12 ++++++------ virt/kvm/kvm_main.c | 8 ++++---- 7 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 9bacfe207b4..ad3126a5864 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -955,7 +955,7 @@ long kvm_arch_vm_ioctl(struct file *filp, kvm_mem.guest_phys_addr; kvm_userspace_mem.memory_size = kvm_mem.memory_size; r = kvm_vm_ioctl_set_memory_region(kvm, - &kvm_userspace_mem, 0); + &kvm_userspace_mem, false); if (r) goto out; break; @@ -1580,7 +1580,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { unsigned long i; unsigned long pfn; @@ -1611,7 +1611,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, - int user_alloc) + bool user_alloc) { return; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 70739a08956..be83fca2e8f 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -412,7 +412,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { return kvmppc_core_prepare_memory_region(kvm, memslot, mem); } @@ -420,7 +420,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, - int user_alloc) + bool user_alloc) { kvmppc_core_commit_memory_region(kvm, mem, old); } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c9011bfaabb..f718bc65835 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -928,7 +928,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { /* A few sanity checks. We can have exactly one memory slot which has to start at guest virtual zero and which has to be located at a @@ -958,7 +958,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, - int user_alloc) + bool user_alloc) { int rc; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 9120ae1901e..b3101e36807 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3667,7 +3667,7 @@ static int alloc_apic_access_page(struct kvm *kvm) kvm_userspace_mem.flags = 0; kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false); if (r) goto out; @@ -3697,7 +3697,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) kvm_userspace_mem.guest_phys_addr = kvm->arch.ept_identity_map_addr; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false); if (r) goto out; @@ -4251,7 +4251,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) .flags = 0, }; - ret = kvm_set_memory_region(kvm, &tss_mem, 0); + ret = kvm_set_memory_region(kvm, &tss_mem, false); if (ret) return ret; kvm->arch.tss_addr = addr; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 816074757c9..1c9c834b72f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6839,7 +6839,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { int npages = memslot->npages; int map_flags = MAP_PRIVATE | MAP_ANONYMOUS; @@ -6875,7 +6875,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, - int user_alloc) + bool user_alloc) { int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5a3581ceb03..d897f035749 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -270,8 +270,8 @@ struct kvm_memory_slot { unsigned long *dirty_bitmap; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; - int user_alloc; int id; + bool user_alloc; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) @@ -451,10 +451,10 @@ id_to_memslot(struct kvm_memslots *slots, int id) int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); int __kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); void kvm_arch_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); @@ -462,11 +462,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, - int user_alloc); + bool user_alloc); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); /* flush all memory translations */ @@ -553,7 +553,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc); + bool user_alloc); int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5f0638cb696..42c1eb73a0e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -709,7 +709,7 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) */ int __kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { int r; gfn_t base_gfn; @@ -889,7 +889,7 @@ EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { int r; @@ -903,7 +903,7 @@ EXPORT_SYMBOL_GPL(kvm_set_memory_region); int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { if (mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; @@ -2148,7 +2148,7 @@ static long kvm_vm_ioctl(struct file *filp, sizeof kvm_userspace_mem)) goto out; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1); + r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, true); break; } case KVM_GET_DIRTY_LOG: { -- cgit v1.2.3-70-g09d2 From 6104f472a5ea287fbdcf4644e74867dfd905a018 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:26 -0700 Subject: KVM: struct kvm_memory_slot.flags -> u32 struct kvm_userspace_memory_region.flags is a u32 with a comment that bits 0 ~ 15 are visible to userspace and the other bits are reserved for kvm internal use. KVM_MEMSLOT_INVALID is the only internal use flag and it has a comment that bits 16 ~ 31 are internally used and the other bits are visible to userspace. Therefore, let's define this as a u32 so we don't waste bytes on LP64 systems. Move to the end of the struct for alignment. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d897f035749..fec607537fa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -266,10 +266,10 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; - unsigned long flags; unsigned long *dirty_bitmap; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; + u32 flags; int id; bool user_alloc; }; -- cgit v1.2.3-70-g09d2 From 1e702d9af5d633cf0eca76f6340b3c50fbb5a4e5 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 10 Dec 2012 10:33:32 -0700 Subject: KVM: struct kvm_memory_slot.id -> short We're currently offering a whopping 32 memory slots to user space, an int is a bit excessive for storing this. We would like to increase our memslots, but SHRT_MAX should be more than enough. Reviewed-by: Gleb Natapov Signed-off-by: Alex Williamson Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++-- virt/kvm/kvm_main.c | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fec607537fa..32fdc45ca35 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -270,7 +270,7 @@ struct kvm_memory_slot { struct kvm_arch_memory_slot arch; unsigned long userspace_addr; u32 flags; - int id; + short id; bool user_alloc; }; @@ -330,7 +330,7 @@ struct kvm_memslots { u64 generation; struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM]; /* The mapping table from slot id to the index in memslots[]. */ - int id_to_index[KVM_MEM_SLOTS_NUM]; + short id_to_index[KVM_MEM_SLOTS_NUM]; }; struct kvm { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 42c1eb73a0e..bd31096e369 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -474,6 +474,8 @@ static struct kvm *kvm_create_vm(unsigned long type) INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif + BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + r = -ENOMEM; kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!kvm->memslots) -- cgit v1.2.3-70-g09d2 From 116c14c0191f3378e6567af296529ac287e85aa2 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 21 Dec 2012 08:20:16 -0700 Subject: kvm: Fix memory slot generation updates Previous patch "kvm: Minor memory slot optimization" (b7f69c555ca43) overlooked the generation field of the memory slots. Re-using the original memory slots left us with with two slightly different memory slots with the same generation. To fix this, make update_memslots() take a new parameter to specify the last generation. This also makes generation management more explicit to avoid such problems in the future. Reported-by: Takuya Yoshikawa Signed-off-by: Alex Williamson Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 3 ++- virt/kvm/kvm_main.c | 9 +++++---- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 32fdc45ca35..cbe0d683e2e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -428,7 +428,8 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); -void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new); +void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new, + u64 last_generation); static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index bd31096e369..14cbae83be6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -672,7 +672,8 @@ static void sort_memslots(struct kvm_memslots *slots) slots->id_to_index[slots->memslots[i].id] = i; } -void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) +void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new, + u64 last_generation) { if (new) { int id = new->id; @@ -684,7 +685,7 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) sort_memslots(slots); } - slots->generation++; + slots->generation = last_generation + 1; } static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) @@ -819,7 +820,7 @@ int __kvm_set_memory_region(struct kvm *kvm, slot = id_to_memslot(slots, mem->slot); slot->flags |= KVM_MEMSLOT_INVALID; - update_memslots(slots, NULL); + update_memslots(slots, NULL, kvm->memslots->generation); old_memslots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); @@ -867,7 +868,7 @@ int __kvm_set_memory_region(struct kvm *kvm, memset(&new.arch, 0, sizeof(new.arch)); } - update_memslots(slots, &new); + update_memslots(slots, &new, kvm->memslots->generation); old_memslots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); -- cgit v1.2.3-70-g09d2 From d8346b7d9bab37e6cc712ff1622c65ff98bdfef8 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 20 Dec 2012 15:32:08 +0100 Subject: KVM: s390: Support for I/O interrupts. Add support for handling I/O interrupts (standard, subchannel-related ones and rudimentary adapter interrupts). The subchannel-identifying parameters are encoded into the interrupt type. I/O interrupts are floating, so they can't be injected on a specific vcpu. Reviewed-by: Alexander Graf Reviewed-by: Marcelo Tosatti Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- Documentation/virtual/kvm/api.txt | 4 ++ arch/s390/include/asm/kvm_host.h | 2 + arch/s390/kvm/interrupt.c | 103 +++++++++++++++++++++++++++++++++++++- include/uapi/linux/kvm.h | 9 ++++ 4 files changed, 116 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index a4df5535996..83bd92b5293 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2069,6 +2069,10 @@ KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm +KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an + I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); + I/O interruption parameters in parm (subchannel) and parm64 (intparm, + interruption subclass) Note that the vcpu ioctl is asynchronous to vcpu execution. diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 711c5ab391c..a8e35c43df7 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -74,6 +74,7 @@ struct kvm_s390_sie_block { __u64 epoch; /* 0x0038 */ __u8 reserved40[4]; /* 0x0040 */ #define LCTL_CR0 0x8000 +#define LCTL_CR6 0x0200 __u16 lctl; /* 0x0044 */ __s16 icpua; /* 0x0046 */ __u32 ictl; /* 0x0048 */ @@ -125,6 +126,7 @@ struct kvm_vcpu_stat { u32 deliver_prefix_signal; u32 deliver_restart_signal; u32 deliver_program_int; + u32 deliver_io_int; u32 exit_wait_state; u32 instruction_stidp; u32 instruction_spx; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c30615e605a..52cdf20906a 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -21,11 +21,26 @@ #include "gaccess.h" #include "trace-s390.h" +#define IOINT_SCHID_MASK 0x0000ffff +#define IOINT_SSID_MASK 0x00030000 +#define IOINT_CSSID_MASK 0x03fc0000 +#define IOINT_AI_MASK 0x04000000 + +static int is_ioint(u64 type) +{ + return ((type & 0xfffe0000u) != 0xfffe0000u); +} + static int psw_extint_disabled(struct kvm_vcpu *vcpu) { return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT); } +static int psw_ioint_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO); +} + static int psw_interrupts_disabled(struct kvm_vcpu *vcpu) { if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) || @@ -67,7 +82,15 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, case KVM_S390_SIGP_SET_PREFIX: case KVM_S390_RESTART: return 1; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + if (psw_ioint_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[6] & inti->io.io_int_word) + return 1; + return 0; default: + printk(KERN_WARNING "illegal interrupt type %llx\n", + inti->type); BUG(); } return 0; @@ -116,6 +139,12 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu, case KVM_S390_SIGP_STOP: __set_cpuflag(vcpu, CPUSTAT_STOP_INT); break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + if (psw_ioint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_IO_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR6; + break; default: BUG(); } @@ -297,6 +326,47 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, exception = 1; break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + { + __u32 param0 = ((__u32)inti->io.subchannel_id << 16) | + inti->io.subchannel_nr; + __u64 param1 = ((__u64)inti->io.io_int_parm << 32) | + inti->io.io_int_word; + VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); + vcpu->stat.deliver_io_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + param0, param1); + rc = put_guest_u16(vcpu, __LC_SUBCHANNEL_ID, + inti->io.subchannel_id); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u16(vcpu, __LC_SUBCHANNEL_NR, + inti->io.subchannel_nr); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u32(vcpu, __LC_IO_INT_PARM, + inti->io.io_int_parm); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u32(vcpu, __LC_IO_INT_WORD, + inti->io.io_int_word); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_IO_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_IO_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + break; + } default: BUG(); } @@ -545,7 +615,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, { struct kvm_s390_local_interrupt *li; struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *inti; + struct kvm_s390_interrupt_info *inti, *iter; int sigcpu; inti = kzalloc(sizeof(*inti), GFP_KERNEL); @@ -569,6 +639,22 @@ int kvm_s390_inject_vm(struct kvm *kvm, case KVM_S390_SIGP_STOP: case KVM_S390_INT_EXTERNAL_CALL: case KVM_S390_INT_EMERGENCY: + kfree(inti); + return -EINVAL; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + if (s390int->type & IOINT_AI_MASK) + VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)"); + else + VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x", + s390int->type & IOINT_CSSID_MASK, + s390int->type & IOINT_SSID_MASK, + s390int->type & IOINT_SCHID_MASK); + inti->type = s390int->type; + inti->io.subchannel_id = s390int->parm >> 16; + inti->io.subchannel_nr = s390int->parm & 0x0000ffffu; + inti->io.io_int_parm = s390int->parm64 >> 32; + inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull; + break; default: kfree(inti); return -EINVAL; @@ -579,7 +665,19 @@ int kvm_s390_inject_vm(struct kvm *kvm, mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; spin_lock(&fi->lock); - list_add_tail(&inti->list, &fi->list); + if (!is_ioint(inti->type)) + list_add_tail(&inti->list, &fi->list); + else { + /* Keep I/O interrupts sorted in isc order. */ + list_for_each_entry(iter, &fi->list, list) { + if (!is_ioint(iter->type)) + continue; + if (iter->io.io_int_word <= inti->io.io_int_word) + continue; + break; + } + list_add_tail(&inti->list, &iter->list); + } atomic_set(&fi->active, 1); sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); if (sigcpu == KVM_MAX_VCPUS) { @@ -653,6 +751,7 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, break; case KVM_S390_INT_VIRTIO: case KVM_S390_INT_SERVICE: + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: default: kfree(inti); return -EINVAL; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e6e5d4b1370..54540bdd334 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -401,6 +401,15 @@ struct kvm_s390_psw { #define KVM_S390_INT_SERVICE 0xffff2401u #define KVM_S390_INT_EMERGENCY 0xffff1201u #define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu + struct kvm_s390_interrupt { __u32 type; -- cgit v1.2.3-70-g09d2 From 48a3e950f4cee6a345ffbe9baf599f1e9a54c479 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 20 Dec 2012 15:32:09 +0100 Subject: KVM: s390: Add support for machine checks. Add support for injecting machine checks (only repressible conditions for now). This is a bit more involved than I/O interrupts, for these reasons: - Machine checks come in both floating and cpu varieties. - We don't have a bit for machine checks enabling, but have to use a roundabout approach with trapping PSW changing instructions and watching for opened machine checks. Reviewed-by: Alexander Graf Reviewed-by: Marcelo Tosatti Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- Documentation/virtual/kvm/api.txt | 4 ++ arch/s390/include/asm/kvm_host.h | 8 +++ arch/s390/kvm/intercept.c | 2 + arch/s390/kvm/interrupt.c | 112 +++++++++++++++++++++++++++++++ arch/s390/kvm/kvm-s390.h | 3 + arch/s390/kvm/priv.c | 135 ++++++++++++++++++++++++++++++++++++++ arch/s390/kvm/trace-s390.h | 6 +- include/uapi/linux/kvm.h | 1 + 8 files changed, 268 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 83bd92b5293..8a0de309932 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2073,6 +2073,10 @@ KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); I/O interruption parameters in parm (subchannel) and parm64 (intparm, interruption subclass) +KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm, + machine check interrupt code in parm64 (note that + machine checks needing further payload are not + supported by this ioctl) Note that the vcpu ioctl is asynchronous to vcpu execution. diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index a8e35c43df7..29363d155cd 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -75,8 +75,10 @@ struct kvm_s390_sie_block { __u8 reserved40[4]; /* 0x0040 */ #define LCTL_CR0 0x8000 #define LCTL_CR6 0x0200 +#define LCTL_CR14 0x0002 __u16 lctl; /* 0x0044 */ __s16 icpua; /* 0x0046 */ +#define ICTL_LPSW 0x00400000 __u32 ictl; /* 0x0048 */ __u32 eca; /* 0x004c */ __u8 icptcode; /* 0x0050 */ @@ -187,6 +189,11 @@ struct kvm_s390_emerg_info { __u16 code; }; +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; +}; + struct kvm_s390_interrupt_info { struct list_head list; u64 type; @@ -197,6 +204,7 @@ struct kvm_s390_interrupt_info { struct kvm_s390_emerg_info emerg; struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; + struct kvm_s390_mchk_info mchk; }; }; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index df6c0ad085a..950c13ecaf6 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -97,10 +97,12 @@ static int handle_lctl(struct kvm_vcpu *vcpu) static const intercept_handler_t instruction_handlers[256] = { [0x01] = kvm_s390_handle_01, + [0x82] = kvm_s390_handle_lpsw, [0x83] = kvm_s390_handle_diag, [0xae] = kvm_s390_handle_sigp, [0xb2] = kvm_s390_handle_b2, [0xb7] = handle_lctl, + [0xb9] = kvm_s390_handle_b9, [0xe5] = kvm_s390_handle_e5, [0xeb] = handle_lctlg, }; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 52cdf20906a..b3b4748485e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -41,6 +41,11 @@ static int psw_ioint_disabled(struct kvm_vcpu *vcpu) return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO); } +static int psw_mchk_disabled(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK); +} + static int psw_interrupts_disabled(struct kvm_vcpu *vcpu) { if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) || @@ -82,6 +87,12 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, case KVM_S390_SIGP_SET_PREFIX: case KVM_S390_RESTART: return 1; + case KVM_S390_MCHK: + if (psw_mchk_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14) + return 1; + return 0; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: if (psw_ioint_disabled(vcpu)) return 0; @@ -116,6 +127,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags); vcpu->arch.sie_block->lctl = 0x0000; + vcpu->arch.sie_block->ictl &= ~ICTL_LPSW; } static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) @@ -139,6 +151,12 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu, case KVM_S390_SIGP_STOP: __set_cpuflag(vcpu, CPUSTAT_STOP_INT); break; + case KVM_S390_MCHK: + if (psw_mchk_disabled(vcpu)) + vcpu->arch.sie_block->ictl |= ICTL_LPSW; + else + vcpu->arch.sie_block->lctl |= LCTL_CR14; + break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: if (psw_ioint_disabled(vcpu)) __set_cpuflag(vcpu, CPUSTAT_IO_INT); @@ -326,6 +344,32 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, exception = 1; break; + case KVM_S390_MCHK: + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + inti->mchk.mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + inti->mchk.cr14, + inti->mchk.mcic); + rc = kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_PREFIXED); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u64(vcpu, __LC_MCCK_CODE, inti->mchk.mcic); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_MCK_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: { __u32 param0 = ((__u32)inti->io.subchannel_id << 16) | @@ -588,6 +632,61 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) } } +void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; + struct kvm_s390_interrupt_info *n, *inti = NULL; + int deliver; + + __reset_intercept_indicators(vcpu); + if (atomic_read(&li->active)) { + do { + deliver = 0; + spin_lock_bh(&li->lock); + list_for_each_entry_safe(inti, n, &li->list, list) { + if ((inti->type == KVM_S390_MCHK) && + __interrupt_is_deliverable(vcpu, inti)) { + list_del(&inti->list); + deliver = 1; + break; + } + __set_intercept_indicator(vcpu, inti); + } + if (list_empty(&li->list)) + atomic_set(&li->active, 0); + spin_unlock_bh(&li->lock); + if (deliver) { + __do_deliver_interrupt(vcpu, inti); + kfree(inti); + } + } while (deliver); + } + + if (atomic_read(&fi->active)) { + do { + deliver = 0; + spin_lock(&fi->lock); + list_for_each_entry_safe(inti, n, &fi->list, list) { + if ((inti->type == KVM_S390_MCHK) && + __interrupt_is_deliverable(vcpu, inti)) { + list_del(&inti->list); + deliver = 1; + break; + } + __set_intercept_indicator(vcpu, inti); + } + if (list_empty(&fi->list)) + atomic_set(&fi->active, 0); + spin_unlock(&fi->lock); + if (deliver) { + __do_deliver_interrupt(vcpu, inti); + kfree(inti); + } + } while (deliver); + } +} + int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -641,6 +740,13 @@ int kvm_s390_inject_vm(struct kvm *kvm, case KVM_S390_INT_EMERGENCY: kfree(inti); return -EINVAL; + case KVM_S390_MCHK: + VM_EVENT(kvm, 5, "inject: machine check parm64:%llx", + s390int->parm64); + inti->type = s390int->type; + inti->mchk.cr14 = s390int->parm; /* upper bits are not used */ + inti->mchk.mcic = s390int->parm64; + break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: if (s390int->type & IOINT_AI_MASK) VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)"); @@ -749,6 +855,12 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, inti->type = s390int->type; inti->emerg.code = s390int->parm; break; + case KVM_S390_MCHK: + VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx", + s390int->parm64); + inti->type = s390int->type; + inti->mchk.mcic = s390int->parm64; + break; case KVM_S390_INT_VIRTIO: case KVM_S390_INT_SERVICE: case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index dccc0242b7c..1f7cc6ccf10 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -106,6 +106,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); void kvm_s390_tasklet(unsigned long parm); void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu); +void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu); int kvm_s390_inject_vm(struct kvm *kvm, struct kvm_s390_interrupt *s390int); int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, @@ -117,6 +118,8 @@ int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action); int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); int kvm_s390_handle_e5(struct kvm_vcpu *vcpu); int kvm_s390_handle_01(struct kvm_vcpu *vcpu); +int kvm_s390_handle_b9(struct kvm_vcpu *vcpu); +int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu); /* implemented in sigp.c */ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index d715842f56c..d3cbcd3c9ad 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include "gaccess.h" #include "kvm-s390.h" #include "trace.h" @@ -166,6 +168,99 @@ static int handle_stfl(struct kvm_vcpu *vcpu) return 0; } +static void handle_new_psw(struct kvm_vcpu *vcpu) +{ + /* Check whether the new psw is enabled for machine checks. */ + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK) + kvm_s390_deliver_pending_machine_checks(vcpu); +} + +#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA) +#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL +#define PSW_ADDR_24 0x00000000000fffffUL +#define PSW_ADDR_31 0x000000007fffffffUL + +int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) +{ + u64 addr; + psw_compat_t new_psw; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, + PGM_PRIVILEGED_OPERATION); + + addr = kvm_s390_get_base_disp_s(vcpu); + + if (addr & 7) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out; + } + + if (!(new_psw.mask & PSW32_MASK_BASE)) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + vcpu->arch.sie_block->gpsw.mask = + (new_psw.mask & ~PSW32_MASK_BASE) << 32; + vcpu->arch.sie_block->gpsw.addr = new_psw.addr; + + if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) || + (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) && + (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) || + ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) == + PSW_MASK_EA)) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + handle_new_psw(vcpu); +out: + return 0; +} + +static int handle_lpswe(struct kvm_vcpu *vcpu) +{ + u64 addr; + psw_t new_psw; + + addr = kvm_s390_get_base_disp_s(vcpu); + + if (addr & 7) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) { + kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + goto out; + } + + vcpu->arch.sie_block->gpsw.mask = new_psw.mask; + vcpu->arch.sie_block->gpsw.addr = new_psw.addr; + + if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) || + (((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) == + PSW_MASK_BA) && + (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_31)) || + (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) && + (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) || + ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) == + PSW_MASK_EA)) { + kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + goto out; + } + + handle_new_psw(vcpu); +out: + return 0; +} + static int handle_stidp(struct kvm_vcpu *vcpu) { u64 operand2; @@ -292,6 +387,7 @@ static const intercept_handler_t priv_handlers[256] = { [0x5f] = handle_chsc, [0x7d] = handle_stsi, [0xb1] = handle_stfl, + [0xb2] = handle_lpswe, }; int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) @@ -316,6 +412,45 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } +static int handle_epsw(struct kvm_vcpu *vcpu) +{ + int reg1, reg2; + + reg1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 24; + reg2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; + + /* This basically extracts the mask half of the psw. */ + vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32; + if (reg2) { + vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg2] |= + vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff; + } + return 0; +} + +static const intercept_handler_t b9_handlers[256] = { + [0x8d] = handle_epsw, +}; + +int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) +{ + intercept_handler_t handler; + + /* This is handled just as for the B2 instructions. */ + handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; + if (handler) { + if ((handler != handle_epsw) && + (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)) + return kvm_s390_inject_program_int(vcpu, + PGM_PRIVILEGED_OPERATION); + else + return handler(vcpu); + } + return -EOPNOTSUPP; +} + static int handle_tprot(struct kvm_vcpu *vcpu) { u64 address1, address2; diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h index 90fdf85b5ff..95fbc1ab88d 100644 --- a/arch/s390/kvm/trace-s390.h +++ b/arch/s390/kvm/trace-s390.h @@ -141,13 +141,13 @@ TRACE_EVENT(kvm_s390_inject_vcpu, * Trace point for the actual delivery of interrupts. */ TRACE_EVENT(kvm_s390_deliver_interrupt, - TP_PROTO(unsigned int id, __u64 type, __u32 data0, __u64 data1), + TP_PROTO(unsigned int id, __u64 type, __u64 data0, __u64 data1), TP_ARGS(id, type, data0, data1), TP_STRUCT__entry( __field(int, id) __field(__u32, inttype) - __field(__u32, data0) + __field(__u64, data0) __field(__u64, data1) ), @@ -159,7 +159,7 @@ TRACE_EVENT(kvm_s390_deliver_interrupt, ), TP_printk("deliver interrupt (vcpu %d): type:%x (%s) " \ - "data:%08x %016llx", + "data:%08llx %016llx", __entry->id, __entry->inttype, __print_symbolic(__entry->inttype, kvm_s390_int_type), __entry->data0, __entry->data1) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 54540bdd334..80bb3b80111 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -397,6 +397,7 @@ struct kvm_s390_psw { #define KVM_S390_PROGRAM_INT 0xfffe0001u #define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u #define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_MCHK 0xfffe1000u #define KVM_S390_INT_VIRTIO 0xffff2603u #define KVM_S390_INT_SERVICE 0xffff2401u #define KVM_S390_INT_EMERGENCY 0xffff1201u -- cgit v1.2.3-70-g09d2 From fa6b7fe9928d50444c29b29c8563746c6b0c6299 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 20 Dec 2012 15:32:12 +0100 Subject: KVM: s390: Add support for channel I/O instructions. Add a new capability, KVM_CAP_S390_CSS_SUPPORT, which will pass intercepts for channel I/O instructions to userspace. Only I/O instructions interacting with I/O interrupts need to be handled in-kernel: - TEST PENDING INTERRUPTION (tpi) dequeues and stores pending interrupts entirely in-kernel. - TEST SUBCHANNEL (tsch) dequeues pending interrupts in-kernel and exits via KVM_EXIT_S390_TSCH to userspace for subchannel- related processing. Reviewed-by: Marcelo Tosatti Reviewed-by: Alexander Graf Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- Documentation/virtual/kvm/api.txt | 30 +++++++++++++ arch/s390/include/asm/kvm_host.h | 1 + arch/s390/kvm/intercept.c | 1 + arch/s390/kvm/interrupt.c | 37 ++++++++++++++++ arch/s390/kvm/kvm-s390.c | 12 ++++++ arch/s390/kvm/kvm-s390.h | 2 + arch/s390/kvm/priv.c | 91 +++++++++++++++++++++++++++++++++++++-- arch/s390/kvm/trace-s390.h | 20 +++++++++ include/trace/events/kvm.h | 2 +- include/uapi/linux/kvm.h | 11 +++++ 10 files changed, 202 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 73bd159c555..f2d6391178b 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2350,6 +2350,22 @@ The possible hypercalls are defined in the Power Architecture Platform Requirements (PAPR) document available from www.power.org (free developer registration required to access it). + /* KVM_EXIT_S390_TSCH */ + struct { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; + __u32 ipb; + __u8 dequeued; + } s390_tsch; + +s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled +and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O +interrupt for the target subchannel has been dequeued and subchannel_id, +subchannel_nr, io_int_parm and io_int_word contain the parameters for that +interrupt. ipb is needed for instruction parameter decoding. + /* Fix the size of the union. */ char padding[256]; }; @@ -2471,3 +2487,17 @@ For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV: where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value. - The tsize field of mas1 shall be set to 4K on TLB0, even though the hardware ignores this value for TLB0. + +6.4 KVM_CAP_S390_CSS_SUPPORT + +Architectures: s390 +Parameters: none +Returns: 0 on success; -1 on error + +This capability enables support for handling of channel I/O instructions. + +TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are +handled in-kernel, while the other I/O instructions are passed to userspace. + +When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST +SUBCHANNEL intercepts. diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 29363d155cd..16bd5d169cd 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -262,6 +262,7 @@ struct kvm_arch{ debug_info_t *dbf; struct kvm_s390_float_interrupt float_int; struct gmap *gmap; + int css_support; }; extern int sie64a(struct kvm_s390_sie_block *, u64 *); diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 71af87dbb42..f26ff1e31bd 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -264,6 +264,7 @@ static const intercept_handler_t intercept_funcs[] = { [0x0C >> 2] = handle_instruction_and_prog, [0x10 >> 2] = handle_noop, [0x14 >> 2] = handle_noop, + [0x18 >> 2] = handle_noop, [0x1C >> 2] = kvm_s390_handle_wait, [0x20 >> 2] = handle_validity, [0x28 >> 2] = handle_stop, diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index b3b4748485e..9a128357fd1 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -709,6 +709,43 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) return 0; } +struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, + u64 cr6, u64 schid) +{ + struct kvm_s390_float_interrupt *fi; + struct kvm_s390_interrupt_info *inti, *iter; + + if ((!schid && !cr6) || (schid && cr6)) + return NULL; + mutex_lock(&kvm->lock); + fi = &kvm->arch.float_int; + spin_lock(&fi->lock); + inti = NULL; + list_for_each_entry(iter, &fi->list, list) { + if (!is_ioint(iter->type)) + continue; + if (cr6 && ((cr6 & iter->io.io_int_word) == 0)) + continue; + if (schid) { + if (((schid & 0x00000000ffff0000) >> 16) != + iter->io.subchannel_id) + continue; + if ((schid & 0x000000000000ffff) != + iter->io.subchannel_nr) + continue; + } + inti = iter; + break; + } + if (inti) + list_del_init(&inti->list); + if (list_empty(&fi->list)) + atomic_set(&fi->active, 0); + spin_unlock(&fi->lock); + mutex_unlock(&kvm->lock); + return inti; +} + int kvm_s390_inject_vm(struct kvm *kvm, struct kvm_s390_interrupt *s390int) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5ff26033825..5b01f095390 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -141,6 +141,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_SYNC_REGS: case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: + case KVM_CAP_S390_CSS_SUPPORT: r = 1; break; case KVM_CAP_NR_VCPUS: @@ -235,6 +236,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (!kvm->arch.gmap) goto out_nogmap; } + + kvm->arch.css_support = 0; + return 0; out_nogmap: debug_unregister(kvm->arch.dbf); @@ -658,6 +662,7 @@ rerun_vcpu: case KVM_EXIT_INTR: case KVM_EXIT_S390_RESET: case KVM_EXIT_S390_UCONTROL: + case KVM_EXIT_S390_TSCH: break; default: BUG(); @@ -818,6 +823,13 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return -EINVAL; switch (cap->cap) { + case KVM_CAP_S390_CSS_SUPPORT: + if (!vcpu->kvm->arch.css_support) { + vcpu->kvm->arch.css_support = 1; + trace_kvm_s390_enable_css(vcpu->kvm); + } + r = 0; + break; default: r = -EINVAL; break; diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 211b340385a..3e05deff21b 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -113,6 +113,8 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt *s390int); int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action); +struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, + u64 cr6, u64 schid); /* implemented in priv.c */ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 8ad776f8785..0ef9894606e 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -127,15 +127,98 @@ static int handle_skey(struct kvm_vcpu *vcpu) return 0; } -static int handle_io_inst(struct kvm_vcpu *vcpu) +static int handle_tpi(struct kvm_vcpu *vcpu) { - VCPU_EVENT(vcpu, 4, "%s", "I/O instruction"); - /* condition code 3 */ + u64 addr; + struct kvm_s390_interrupt_info *inti; + int cc; + + addr = kvm_s390_get_base_disp_s(vcpu); + + inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->run->s.regs.crs[6], 0); + if (inti) { + if (addr) { + /* + * Store the two-word I/O interruption code into the + * provided area. + */ + put_guest_u16(vcpu, addr, inti->io.subchannel_id); + put_guest_u16(vcpu, addr + 2, inti->io.subchannel_nr); + put_guest_u32(vcpu, addr + 4, inti->io.io_int_parm); + } else { + /* + * Store the three-word I/O interruption code into + * the appropriate lowcore area. + */ + put_guest_u16(vcpu, 184, inti->io.subchannel_id); + put_guest_u16(vcpu, 186, inti->io.subchannel_nr); + put_guest_u32(vcpu, 188, inti->io.io_int_parm); + put_guest_u32(vcpu, 192, inti->io.io_int_word); + } + cc = 1; + } else + cc = 0; + kfree(inti); + /* Set condition code and we're done. */ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44; return 0; } +static int handle_tsch(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_interrupt_info *inti; + + inti = kvm_s390_get_io_int(vcpu->kvm, 0, + vcpu->run->s.regs.gprs[1]); + + /* + * Prepare exit to userspace. + * We indicate whether we dequeued a pending I/O interrupt + * so that userspace can re-inject it if the instruction gets + * a program check. While this may re-order the pending I/O + * interrupts, this is no problem since the priority is kept + * intact. + */ + vcpu->run->exit_reason = KVM_EXIT_S390_TSCH; + vcpu->run->s390_tsch.dequeued = !!inti; + if (inti) { + vcpu->run->s390_tsch.subchannel_id = inti->io.subchannel_id; + vcpu->run->s390_tsch.subchannel_nr = inti->io.subchannel_nr; + vcpu->run->s390_tsch.io_int_parm = inti->io.io_int_parm; + vcpu->run->s390_tsch.io_int_word = inti->io.io_int_word; + } + vcpu->run->s390_tsch.ipb = vcpu->arch.sie_block->ipb; + kfree(inti); + return -EREMOTE; +} + +static int handle_io_inst(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 4, "%s", "I/O instruction"); + + if (vcpu->kvm->arch.css_support) { + /* + * Most I/O instructions will be handled by userspace. + * Exceptions are tpi and the interrupt portion of tsch. + */ + if (vcpu->arch.sie_block->ipa == 0xb236) + return handle_tpi(vcpu); + if (vcpu->arch.sie_block->ipa == 0xb235) + return handle_tsch(vcpu); + /* Handle in userspace. */ + return -EOPNOTSUPP; + } else { + /* + * Set condition code 3 to stop the guest from issueing channel + * I/O instructions. + */ + vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + return 0; + } +} + static int handle_stfl(struct kvm_vcpu *vcpu) { unsigned int facility_list; diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h index 95fbc1ab88d..13f30f58a2d 100644 --- a/arch/s390/kvm/trace-s390.h +++ b/arch/s390/kvm/trace-s390.h @@ -204,6 +204,26 @@ TRACE_EVENT(kvm_s390_stop_request, ); +/* + * Trace point for enabling channel I/O instruction support. + */ +TRACE_EVENT(kvm_s390_enable_css, + TP_PROTO(void *kvm), + TP_ARGS(kvm), + + TP_STRUCT__entry( + __field(void *, kvm) + ), + + TP_fast_assign( + __entry->kvm = kvm; + ), + + TP_printk("enabling channel I/O support (kvm @ %p)\n", + __entry->kvm) + ); + + #endif /* _TRACE_KVMS390_H */ /* This part must be outside protection */ diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 7ef9e759f49..a23f47c884c 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -14,7 +14,7 @@ ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR), \ ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\ ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL), \ - ERSN(S390_UCONTROL) + ERSN(S390_UCONTROL), ERSN(S390_TSCH) TRACE_EVENT(kvm_userspace_exit, TP_PROTO(__u32 reason, int errno), diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 80bb3b80111..8bb0bf83afc 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -168,6 +168,7 @@ struct kvm_pit_config { #define KVM_EXIT_PAPR_HCALL 19 #define KVM_EXIT_S390_UCONTROL 20 #define KVM_EXIT_WATCHDOG 21 +#define KVM_EXIT_S390_TSCH 22 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -285,6 +286,15 @@ struct kvm_run { __u64 ret; __u64 args[9]; } papr_hcall; + /* KVM_EXIT_S390_TSCH */ + struct { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; + __u32 ipb; + __u8 dequeued; + } s390_tsch; /* Fix the size of the union. */ char padding[256]; }; @@ -645,6 +655,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_IRQFD_RESAMPLE 82 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83 #define KVM_CAP_PPC_HTAB_FD 84 +#define KVM_CAP_S390_CSS_SUPPORT 85 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3-70-g09d2 From 1c810636556c8d53a37406b34a64d9b9b0161aa6 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 4 Jan 2013 18:12:48 +0100 Subject: KVM: PPC: BookE: Implement EPR exit The External Proxy Facility in FSL BookE chips allows the interrupt controller to automatically acknowledge an interrupt as soon as a core gets its pending external interrupt delivered. Today, user space implements the interrupt controller, so we need to check on it during such a cycle. This patch implements logic for user space to enable EPR exiting, disable EPR exiting and EPR exiting itself, so that user space can acknowledge an interrupt when an external interrupt has successfully been delivered into the guest vcpu. Signed-off-by: Alexander Graf --- Documentation/virtual/kvm/api.txt | 40 +++++++++++++++++++++++++++++++++++-- arch/powerpc/include/asm/kvm_host.h | 2 ++ arch/powerpc/include/asm/kvm_ppc.h | 9 +++++++++ arch/powerpc/kvm/booke.c | 14 ++++++++++++- arch/powerpc/kvm/powerpc.c | 10 ++++++++++ include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 6 ++++++ 7 files changed, 79 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 4fc2bfcb16d..a98ed09269d 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2246,8 +2246,8 @@ executed a memory-mapped I/O instruction which could not be satisfied by kvm. The 'data' member contains the written data if 'is_write' is true, and should be filled by application code otherwise. -NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR - and KVM_EXIT_PAPR the corresponding +NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR, + KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding operations are complete (and guest state is consistent) only after userspace has re-entered the kernel with KVM_RUN. The kernel side will first finish incomplete operations and then check for pending signals. Userspace @@ -2366,6 +2366,25 @@ interrupt for the target subchannel has been dequeued and subchannel_id, subchannel_nr, io_int_parm and io_int_word contain the parameters for that interrupt. ipb is needed for instruction parameter decoding. + /* KVM_EXIT_EPR */ + struct { + __u32 epr; + } epr; + +On FSL BookE PowerPC chips, the interrupt controller has a fast patch +interrupt acknowledge path to the core. When the core successfully +delivers an interrupt, it automatically populates the EPR register with +the interrupt vector number and acknowledges the interrupt inside +the interrupt controller. + +In case the interrupt controller lives in user space, we need to do +the interrupt acknowledge cycle through it to fetch the next to be +delivered interrupt vector using this exit. + +It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an +external interrupt has just been delivered into the guest. User space +should put the acknowledged interrupt vector into the 'epr' field. + /* Fix the size of the union. */ char padding[256]; }; @@ -2501,3 +2520,20 @@ handled in-kernel, while the other I/O instructions are passed to userspace. When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST SUBCHANNEL intercepts. + +6.5 KVM_CAP_PPC_EPR + +Architectures: ppc +Parameters: args[0] defines whether the proxy facility is active +Returns: 0 on success; -1 on error + +This capability enables or disables the delivery of interrupts through the +external proxy facility. + +When enabled (args[0] != 0), every time the guest gets an external interrupt +delivered, it automatically exits into user space with a KVM_EXIT_EPR exit +to receive the topmost interrupt vector. + +When disabled (args[0] == 0), behavior is as if this facility is unsupported. + +When this capability is enabled, KVM_EXIT_EPR can occur. diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index ab49c6cf891..8a72d59467e 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -520,6 +520,8 @@ struct kvm_vcpu_arch { u8 sane; u8 cpu_type; u8 hcall_needed; + u8 epr_enabled; + u8 epr_needed; u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 5f5f69abd28..493630e209c 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -264,6 +264,15 @@ static inline void kvm_linear_init(void) {} #endif +static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr) +{ +#ifdef CONFIG_KVM_BOOKE_HV + mtspr(SPRN_GEPR, epr); +#elif defined(CONFIG_BOOKE) + vcpu->arch.epr = epr; +#endif +} + int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, struct kvm_config_tlb *cfg); int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu, diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 964f4475f55..940ec806187 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -306,7 +306,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, { int allowed = 0; ulong msr_mask = 0; - bool update_esr = false, update_dear = false; + bool update_esr = false, update_dear = false, update_epr = false; ulong crit_raw = vcpu->arch.shared->critical; ulong crit_r1 = kvmppc_get_gpr(vcpu, 1); bool crit; @@ -330,6 +330,9 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, keep_irq = true; } + if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_enabled) + update_epr = true; + switch (priority) { case BOOKE_IRQPRIO_DTLB_MISS: case BOOKE_IRQPRIO_DATA_STORAGE: @@ -408,6 +411,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, set_guest_esr(vcpu, vcpu->arch.queued_esr); if (update_dear == true) set_guest_dear(vcpu, vcpu->arch.queued_dear); + if (update_epr == true) + kvm_make_request(KVM_REQ_EPR_EXIT, vcpu); new_msr &= msr_mask; #if defined(CONFIG_64BIT) @@ -615,6 +620,13 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) r = 0; } + if (kvm_check_request(KVM_REQ_EPR_EXIT, vcpu)) { + vcpu->run->epr.epr = 0; + vcpu->arch.epr_needed = true; + vcpu->run->exit_reason = KVM_EXIT_EPR; + r = 0; + } + return r; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index e2225e5b8a4..934413cd3a1 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -306,6 +306,7 @@ int kvm_dev_ioctl_check_extension(long ext) #ifdef CONFIG_BOOKE case KVM_CAP_PPC_BOOKE_SREGS: case KVM_CAP_PPC_BOOKE_WATCHDOG: + case KVM_CAP_PPC_EPR: #else case KVM_CAP_PPC_SEGSTATE: case KVM_CAP_PPC_HIOR: @@ -721,6 +722,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) for (i = 0; i < 9; ++i) kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]); vcpu->arch.hcall_needed = 0; +#ifdef CONFIG_BOOKE + } else if (vcpu->arch.epr_needed) { + kvmppc_set_epr(vcpu, run->epr.epr); + vcpu->arch.epr_needed = 0; +#endif } r = kvmppc_vcpu_run(run, vcpu); @@ -762,6 +768,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = 0; vcpu->arch.papr_enabled = true; break; + case KVM_CAP_PPC_EPR: + r = 0; + vcpu->arch.epr_enabled = cap->args[0]; + break; #ifdef CONFIG_BOOKE case KVM_CAP_PPC_BOOKE_WATCHDOG: r = 0; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cbe0d683e2e..4dd7d7531e6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -122,6 +122,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_WATCHDOG 18 #define KVM_REQ_MASTERCLOCK_UPDATE 19 #define KVM_REQ_MCLOCK_INPROGRESS 20 +#define KVM_REQ_EPR_EXIT 21 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8bb0bf83afc..9a2db5767ed 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -169,6 +169,7 @@ struct kvm_pit_config { #define KVM_EXIT_S390_UCONTROL 20 #define KVM_EXIT_WATCHDOG 21 #define KVM_EXIT_S390_TSCH 22 +#define KVM_EXIT_EPR 23 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -295,6 +296,10 @@ struct kvm_run { __u32 ipb; __u8 dequeued; } s390_tsch; + /* KVM_EXIT_EPR */ + struct { + __u32 epr; + } epr; /* Fix the size of the union. */ char padding[256]; }; @@ -656,6 +661,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_PPC_BOOKE_WATCHDOG 83 #define KVM_CAP_PPC_HTAB_FD 84 #define KVM_CAP_S390_CSS_SUPPORT 85 +#define KVM_CAP_PPC_EPR 86 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3-70-g09d2 From f79ed82da494bc2ea677c6fc28b5439eacf4f5cc Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Tue, 8 Jan 2013 13:00:01 +0100 Subject: KVM: trace: Fix exit decoding. trace_kvm_userspace_exit has been missing the KVM_EXIT_WATCHDOG exit. CC: Bharat Bhushan Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index a23f47c884c..19911dddaeb 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -14,7 +14,7 @@ ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR), \ ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\ ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL), \ - ERSN(S390_UCONTROL), ERSN(S390_TSCH) + ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH) TRACE_EVENT(kvm_userspace_exit, TP_PROTO(__u32 reason, int errno), -- cgit v1.2.3-70-g09d2 From c7c9c56ca26f7b9458711b2d78b60b60e0d38ba7 Mon Sep 17 00:00:00 2001 From: Yang Zhang Date: Fri, 25 Jan 2013 10:18:51 +0800 Subject: x86, apicv: add virtual interrupt delivery support Virtual interrupt delivery avoids KVM to inject vAPIC interrupts manually, which is fully taken care of by the hardware. This needs some special awareness into existing interrupr injection path: - for pending interrupt, instead of direct injection, we may need update architecture specific indicators before resuming to guest. - A pending interrupt, which is masked by ISR, should be also considered in above update action, since hardware will decide when to inject it at right time. Current has_interrupt and get_interrupt only returns a valid vector from injection p.o.v. Reviewed-by: Marcelo Tosatti Signed-off-by: Kevin Tian Signed-off-by: Yang Zhang Signed-off-by: Gleb Natapov --- arch/ia64/kvm/lapic.h | 6 ++ arch/x86/include/asm/kvm_host.h | 5 ++ arch/x86/include/asm/vmx.h | 11 ++++ arch/x86/kvm/irq.c | 56 +++++++++++++++++-- arch/x86/kvm/lapic.c | 106 +++++++++++++++++++++++++++-------- arch/x86/kvm/lapic.h | 27 +++++++++ arch/x86/kvm/svm.c | 18 ++++++ arch/x86/kvm/vmx.c | 119 ++++++++++++++++++++++++++++++++++++---- arch/x86/kvm/x86.c | 23 +++++++- include/linux/kvm_host.h | 3 + virt/kvm/ioapic.c | 39 +++++++++++++ virt/kvm/ioapic.h | 4 ++ virt/kvm/irq_comm.c | 25 +++++++++ virt/kvm/kvm_main.c | 5 ++ 14 files changed, 407 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h index c5f92a926a9..c3e2935b6db 100644 --- a/arch/ia64/kvm/lapic.h +++ b/arch/ia64/kvm/lapic.h @@ -27,4 +27,10 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq); #define kvm_apic_present(x) (true) #define kvm_lapic_enabled(x) (true) +static inline bool kvm_apic_vid_enabled(void) +{ + /* IA64 has no apicv supporting, do nothing here */ + return false; +} + #endif diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d42c2839be9..635a74d2240 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -699,6 +699,10 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); + int (*vm_has_apicv)(struct kvm *kvm); + void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); + void (*hwapic_isr_update)(struct kvm *kvm, int isr); + void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*get_tdp_level)(void); @@ -994,6 +998,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long hva); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int cpuid_maxphyaddr(struct kvm_vcpu *vcpu); +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 0a54df0b36f..694586ca645 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -62,6 +62,7 @@ #define EXIT_REASON_MCE_DURING_VMENTRY 41 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43 #define EXIT_REASON_APIC_ACCESS 44 +#define EXIT_REASON_EOI_INDUCED 45 #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_WBINVD 54 @@ -144,6 +145,7 @@ #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 #define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080 #define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100 +#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 #define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000 @@ -181,6 +183,7 @@ enum vmcs_field { GUEST_GS_SELECTOR = 0x0000080a, GUEST_LDTR_SELECTOR = 0x0000080c, GUEST_TR_SELECTOR = 0x0000080e, + GUEST_INTR_STATUS = 0x00000810, HOST_ES_SELECTOR = 0x00000c00, HOST_CS_SELECTOR = 0x00000c02, HOST_SS_SELECTOR = 0x00000c04, @@ -208,6 +211,14 @@ enum vmcs_field { APIC_ACCESS_ADDR_HIGH = 0x00002015, EPT_POINTER = 0x0000201a, EPT_POINTER_HIGH = 0x0000201b, + EOI_EXIT_BITMAP0 = 0x0000201c, + EOI_EXIT_BITMAP0_HIGH = 0x0000201d, + EOI_EXIT_BITMAP1 = 0x0000201e, + EOI_EXIT_BITMAP1_HIGH = 0x0000201f, + EOI_EXIT_BITMAP2 = 0x00002020, + EOI_EXIT_BITMAP2_HIGH = 0x00002021, + EOI_EXIT_BITMAP3 = 0x00002022, + EOI_EXIT_BITMAP3_HIGH = 0x00002023, GUEST_PHYSICAL_ADDRESS = 0x00002400, GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401, VMCS_LINK_POINTER = 0x00002800, diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index b111aee815f..484bc874688 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -37,6 +37,38 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL(kvm_cpu_has_pending_timer); +/* + * check if there is pending interrupt from + * non-APIC source without intack. + */ +static int kvm_cpu_has_extint(struct kvm_vcpu *v) +{ + if (kvm_apic_accept_pic_intr(v)) + return pic_irqchip(v->kvm)->output; /* PIC */ + else + return 0; +} + +/* + * check if there is injectable interrupt: + * when virtual interrupt delivery enabled, + * interrupt from apic will handled by hardware, + * we don't need to check it here. + */ +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +{ + if (!irqchip_in_kernel(v->kvm)) + return v->arch.interrupt.pending; + + if (kvm_cpu_has_extint(v)) + return 1; + + if (kvm_apic_vid_enabled(v->kvm)) + return 0; + + return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ +} + /* * check if there is pending interrupt without * intack. @@ -46,27 +78,41 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) if (!irqchip_in_kernel(v->kvm)) return v->arch.interrupt.pending; - if (kvm_apic_accept_pic_intr(v) && pic_irqchip(v->kvm)->output) - return pic_irqchip(v->kvm)->output; /* PIC */ + if (kvm_cpu_has_extint(v)) + return 1; return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ } EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); +/* + * Read pending interrupt(from non-APIC source) + * vector and intack. + */ +static int kvm_cpu_get_extint(struct kvm_vcpu *v) +{ + if (kvm_cpu_has_extint(v)) + return kvm_pic_read_irq(v->kvm); /* PIC */ + return -1; +} + /* * Read pending interrupt vector and intack. */ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { + int vector; + if (!irqchip_in_kernel(v->kvm)) return v->arch.interrupt.nr; - if (kvm_apic_accept_pic_intr(v) && pic_irqchip(v->kvm)->output) - return kvm_pic_read_irq(v->kvm); /* PIC */ + vector = kvm_cpu_get_extint(v); + + if (kvm_apic_vid_enabled(v->kvm) || vector != -1) + return vector; /* PIC */ return kvm_get_apic_interrupt(v); /* APIC */ } -EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f69fc5077a8..02b51dd4e4a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -145,21 +145,51 @@ static inline int kvm_apic_id(struct kvm_lapic *apic) return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } -static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr) +void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, + struct kvm_lapic_irq *irq, + u64 *eoi_exit_bitmap) { - u16 cid; - ldr >>= 32 - map->ldr_bits; - cid = (ldr >> map->cid_shift) & map->cid_mask; + struct kvm_lapic **dst; + struct kvm_apic_map *map; + unsigned long bitmap = 1; + int i; - BUG_ON(cid >= ARRAY_SIZE(map->logical_map)); + rcu_read_lock(); + map = rcu_dereference(vcpu->kvm->arch.apic_map); - return cid; -} + if (unlikely(!map)) { + __set_bit(irq->vector, (unsigned long *)eoi_exit_bitmap); + goto out; + } -static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) -{ - ldr >>= (32 - map->ldr_bits); - return ldr & map->lid_mask; + if (irq->dest_mode == 0) { /* physical mode */ + if (irq->delivery_mode == APIC_DM_LOWEST || + irq->dest_id == 0xff) { + __set_bit(irq->vector, + (unsigned long *)eoi_exit_bitmap); + goto out; + } + dst = &map->phys_map[irq->dest_id & 0xff]; + } else { + u32 mda = irq->dest_id << (32 - map->ldr_bits); + + dst = map->logical_map[apic_cluster_id(map, mda)]; + + bitmap = apic_logical_id(map, mda); + } + + for_each_set_bit(i, &bitmap, 16) { + if (!dst[i]) + continue; + if (dst[i]->vcpu == vcpu) { + __set_bit(irq->vector, + (unsigned long *)eoi_exit_bitmap); + break; + } + } + +out: + rcu_read_unlock(); } static void recalculate_apic_map(struct kvm *kvm) @@ -225,6 +255,8 @@ out: if (old) kfree_rcu(old, rcu); + + kvm_ioapic_make_eoibitmap_request(kvm); } static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id) @@ -340,6 +372,10 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) { int result; + /* + * Note that irr_pending is just a hint. It will be always + * true with virtual interrupt delivery enabled. + */ if (!apic->irr_pending) return -1; @@ -456,6 +492,8 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) static inline int apic_find_highest_isr(struct kvm_lapic *apic) { int result; + + /* Note that isr_count is always 1 with vid enabled */ if (!apic->isr_count) return -1; if (likely(apic->highest_isr_cache != -1)) @@ -735,6 +773,19 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } +static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) +{ + if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && + kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { + int trigger_mode; + if (apic_test_vector(vector, apic->regs + APIC_TMR)) + trigger_mode = IOAPIC_LEVEL_TRIG; + else + trigger_mode = IOAPIC_EDGE_TRIG; + kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); + } +} + static int apic_set_eoi(struct kvm_lapic *apic) { int vector = apic_find_highest_isr(apic); @@ -751,19 +802,26 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); - if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && - kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { - int trigger_mode; - if (apic_test_vector(vector, apic->regs + APIC_TMR)) - trigger_mode = IOAPIC_LEVEL_TRIG; - else - trigger_mode = IOAPIC_EDGE_TRIG; - kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); - } + kvm_ioapic_send_eoi(apic, vector); kvm_make_request(KVM_REQ_EVENT, apic->vcpu); return vector; } +/* + * this interface assumes a trap-like exit, which has already finished + * desired side effect including vISR and vPPR update. + */ +void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + trace_kvm_eoi(apic, vector); + + kvm_ioapic_send_eoi(apic, vector); + kvm_make_request(KVM_REQ_EVENT, apic->vcpu); +} +EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); + static void apic_send_ipi(struct kvm_lapic *apic) { u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR); @@ -1375,8 +1433,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = false; - apic->isr_count = 0; + apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm); + apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm); apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -1591,8 +1649,10 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; - apic->isr_count = count_vectors(apic->regs + APIC_ISR); + apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ? + 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); kvm_make_request(KVM_REQ_EVENT, vcpu); } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 22a5397b638..1676d34ddb4 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -65,6 +65,7 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset); +void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector); void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); @@ -131,4 +132,30 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) return apic->vcpu->arch.apic_base & X2APIC_ENABLE; } +static inline bool kvm_apic_vid_enabled(struct kvm *kvm) +{ + return kvm_x86_ops->vm_has_apicv(kvm); +} + +static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr) +{ + u16 cid; + ldr >>= 32 - map->ldr_bits; + cid = (ldr >> map->cid_shift) & map->cid_mask; + + BUG_ON(cid >= ARRAY_SIZE(map->logical_map)); + + return cid; +} + +static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) +{ + ldr >>= (32 - map->ldr_bits); + return ldr & map->lid_mask; +} + +void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, + struct kvm_lapic_irq *irq, + u64 *eoi_bitmap); + #endif diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 38407e9fd1b..e1b1ce21bc0 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3576,6 +3576,21 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } +static int svm_vm_has_apicv(struct kvm *kvm) +{ + return 0; +} + +static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + return; +} + +static void svm_hwapic_isr_update(struct kvm *kvm, int isr) +{ + return; +} + static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4296,6 +4311,9 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, + .vm_has_apicv = svm_vm_has_apicv, + .load_eoi_exitmap = svm_load_eoi_exitmap, + .hwapic_isr_update = svm_hwapic_isr_update, .set_tss_addr = svm_set_tss_addr, .get_tdp_level = get_npt_level, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3ce8a162933..0cf74a641de 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -84,8 +84,8 @@ module_param(vmm_exclusive, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv_reg = 1; -module_param(enable_apicv_reg, bool, S_IRUGO); +static bool __read_mostly enable_apicv_reg_vid = 1; +module_param(enable_apicv_reg_vid, bool, S_IRUGO); /* * If nested=1, nested virtualization is supported, i.e., guests may use @@ -781,6 +781,12 @@ static inline bool cpu_has_vmx_apic_register_virt(void) SECONDARY_EXEC_APIC_REGISTER_VIRT; } +static inline bool cpu_has_vmx_virtual_intr_delivery(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; +} + static inline bool cpu_has_vmx_flexpriority(void) { return cpu_has_vmx_tpr_shadow() && @@ -2571,7 +2577,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_PAUSE_LOOP_EXITING | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_ENABLE_INVPCID | - SECONDARY_EXEC_APIC_REGISTER_VIRT; + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2586,7 +2593,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) _cpu_based_2nd_exec_control &= ~( SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { /* CR3 accesses and invlpg don't need to cause VM Exits when EPT @@ -2785,8 +2793,14 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ple()) ple_gap = 0; - if (!cpu_has_vmx_apic_register_virt()) - enable_apicv_reg = 0; + if (!cpu_has_vmx_apic_register_virt() || + !cpu_has_vmx_virtual_intr_delivery()) + enable_apicv_reg_vid = 0; + + if (enable_apicv_reg_vid) + kvm_x86_ops->update_cr8_intercept = NULL; + else + kvm_x86_ops->hwapic_irr_update = NULL; if (nested) nested_vmx_setup_ctls_msrs(); @@ -3928,6 +3942,11 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) return exec_control; } +static int vmx_vm_has_apicv(struct kvm *kvm) +{ + return enable_apicv_reg_vid && irqchip_in_kernel(kvm); +} + static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; @@ -3945,8 +3964,9 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!enable_apicv_reg || !irqchip_in_kernel(vmx->vcpu.kvm)) - exec_control &= ~SECONDARY_EXEC_APIC_REGISTER_VIRT; + if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; return exec_control; } @@ -3992,6 +4012,15 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmx_secondary_exec_control(vmx)); } + if (enable_apicv_reg_vid) { + vmcs_write64(EOI_EXIT_BITMAP0, 0); + vmcs_write64(EOI_EXIT_BITMAP1, 0); + vmcs_write64(EOI_EXIT_BITMAP2, 0); + vmcs_write64(EOI_EXIT_BITMAP3, 0); + + vmcs_write16(GUEST_INTR_STATUS, 0); + } + if (ple_gap) { vmcs_write32(PLE_GAP, ple_gap); vmcs_write32(PLE_WINDOW, ple_window); @@ -4906,6 +4935,16 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return emulate_instruction(vcpu, 0) == EMULATE_DONE; } +static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) +{ + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + int vector = exit_qualification & 0xff; + + /* EOI-induced VM exit is trap-like and thus no need to adjust IP */ + kvm_apic_set_eoi_accelerated(vcpu, vector); + return 1; +} + static int handle_apic_write(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -5851,6 +5890,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_APIC_WRITE] = handle_apic_write, + [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced, [EXIT_REASON_WBINVD] = handle_wbinvd, [EXIT_REASON_XSETBV] = handle_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, @@ -6208,7 +6248,8 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) * There is not point to enable virtualize x2apic without enable * apicv */ - if (!cpu_has_vmx_virtualize_x2apic_mode() || !enable_apicv_reg) + if (!cpu_has_vmx_virtualize_x2apic_mode() || + !vmx_vm_has_apicv(vcpu->kvm)) return; if (!vm_need_tpr_shadow(vcpu->kvm)) @@ -6228,6 +6269,56 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) vmx_set_msr_bitmap(vcpu); } +static void vmx_hwapic_isr_update(struct kvm *kvm, int isr) +{ + u16 status; + u8 old; + + if (!vmx_vm_has_apicv(kvm)) + return; + + if (isr == -1) + isr = 0; + + status = vmcs_read16(GUEST_INTR_STATUS); + old = status >> 8; + if (isr != old) { + status &= 0xff; + status |= isr << 8; + vmcs_write16(GUEST_INTR_STATUS, status); + } +} + +static void vmx_set_rvi(int vector) +{ + u16 status; + u8 old; + + status = vmcs_read16(GUEST_INTR_STATUS); + old = (u8)status & 0xff; + if ((u8)vector != old) { + status &= ~0xff; + status |= (u8)vector; + vmcs_write16(GUEST_INTR_STATUS, status); + } +} + +static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) +{ + if (max_irr == -1) + return; + + vmx_set_rvi(max_irr); +} + +static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); + vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); + vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); + vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); +} + static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -7492,6 +7583,10 @@ static struct kvm_x86_ops vmx_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, + .vm_has_apicv = vmx_vm_has_apicv, + .load_eoi_exitmap = vmx_load_eoi_exitmap, + .hwapic_irr_update = vmx_hwapic_irr_update, + .hwapic_isr_update = vmx_hwapic_isr_update, .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, @@ -7594,7 +7689,7 @@ static int __init vmx_init(void) memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); - if (enable_apicv_reg) { + if (enable_apicv_reg_vid) { for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); @@ -7606,6 +7701,10 @@ static int __init vmx_init(void) vmx_enable_intercept_msr_read_x2apic(0x839); /* TPR */ vmx_disable_intercept_msr_write_x2apic(0x808); + /* EOI */ + vmx_disable_intercept_msr_write_x2apic(0x80b); + /* SELF-IPI */ + vmx_disable_intercept_msr_write_x2apic(0x83f); } if (enable_ept) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b9f55299ed7..cf512e70c79 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5565,7 +5565,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) vcpu->arch.nmi_injected = true; kvm_x86_ops->set_nmi(vcpu); } - } else if (kvm_cpu_has_interrupt(vcpu)) { + } else if (kvm_cpu_has_injectable_intr(vcpu)) { if (kvm_x86_ops->interrupt_allowed(vcpu)) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); @@ -5633,6 +5633,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) #endif } +static void update_eoi_exitmap(struct kvm_vcpu *vcpu) +{ + u64 eoi_exit_bitmap[4]; + + memset(eoi_exit_bitmap, 0, 32); + + kvm_ioapic_calculate_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; @@ -5686,6 +5696,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_handle_pmu_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) kvm_deliver_pmi(vcpu); + if (kvm_check_request(KVM_REQ_EOIBITMAP, vcpu)) + update_eoi_exitmap(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -5694,10 +5706,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); - else if (kvm_cpu_has_interrupt(vcpu) || req_int_win) + else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) kvm_x86_ops->enable_irq_window(vcpu); if (kvm_lapic_enabled(vcpu)) { + /* + * Update architecture specific hints for APIC + * virtual interrupt delivery. + */ + if (kvm_x86_ops->hwapic_irr_update) + kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_lapic_find_highest_irr(vcpu)); update_cr8_intercept(vcpu); kvm_lapic_sync_to_vapic(vcpu); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4dd7d7531e6..0350e0d5e03 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -123,6 +123,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MASTERCLOCK_UPDATE 19 #define KVM_REQ_MCLOCK_INPROGRESS 20 #define KVM_REQ_EPR_EXIT 21 +#define KVM_REQ_EOIBITMAP 22 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -538,6 +539,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); void kvm_make_mclock_inprogress_request(struct kvm *kvm); +void kvm_make_update_eoibitmap_request(struct kvm *kvm); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -691,6 +693,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, int irq_source_id, int level); +bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index f3abbef46c4..ce82b940195 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -115,6 +116,42 @@ static void update_handled_vectors(struct kvm_ioapic *ioapic) smp_wmb(); } +void kvm_ioapic_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, + u64 *eoi_exit_bitmap) +{ + struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; + union kvm_ioapic_redirect_entry *e; + struct kvm_lapic_irq irqe; + int index; + + spin_lock(&ioapic->lock); + /* traverse ioapic entry to set eoi exit bitmap*/ + for (index = 0; index < IOAPIC_NUM_PINS; index++) { + e = &ioapic->redirtbl[index]; + if (!e->fields.mask && + (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || + kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, + index))) { + irqe.dest_id = e->fields.dest_id; + irqe.vector = e->fields.vector; + irqe.dest_mode = e->fields.dest_mode; + irqe.delivery_mode = e->fields.delivery_mode << 8; + kvm_calculate_eoi_exitmap(vcpu, &irqe, eoi_exit_bitmap); + } + } + spin_unlock(&ioapic->lock); +} +EXPORT_SYMBOL_GPL(kvm_ioapic_calculate_eoi_exitmap); + +void kvm_ioapic_make_eoibitmap_request(struct kvm *kvm) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + + if (!kvm_apic_vid_enabled(kvm) || !ioapic) + return; + kvm_make_update_eoibitmap_request(kvm); +} + static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; @@ -156,6 +193,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && ioapic->irr & (1 << index)) ioapic_service(ioapic, index); + kvm_ioapic_make_eoibitmap_request(ioapic->kvm); break; } } @@ -455,6 +493,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); update_handled_vectors(ioapic); + kvm_ioapic_make_eoibitmap_request(kvm); spin_unlock(&ioapic->lock); return 0; } diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index a30abfe6ed1..0400a466c50 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -82,5 +82,9 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); +void kvm_ioapic_make_eoibitmap_request(struct kvm *kvm); +void kvm_ioapic_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, + u64 *eoi_exit_bitmap); + #endif diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 656fa455e15..ff6d40e2c06 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -22,6 +22,7 @@ #include #include +#include #include #include @@ -237,6 +238,28 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) return ret; } +bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) +{ + struct kvm_irq_ack_notifier *kian; + struct hlist_node *n; + int gsi; + + rcu_read_lock(); + gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + if (gsi != -1) + hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, + link) + if (kian->gsi == gsi) { + rcu_read_unlock(); + return true; + } + + rcu_read_unlock(); + + return false; +} +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; @@ -261,6 +284,7 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm, mutex_lock(&kvm->irq_lock); hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); mutex_unlock(&kvm->irq_lock); + kvm_ioapic_make_eoibitmap_request(kvm); } void kvm_unregister_irq_ack_notifier(struct kvm *kvm, @@ -270,6 +294,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); synchronize_rcu(); + kvm_ioapic_make_eoibitmap_request(kvm); } int kvm_request_irq_source_id(struct kvm *kvm) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3fec2cdd951..abc23e27173 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -217,6 +217,11 @@ void kvm_make_mclock_inprogress_request(struct kvm *kvm) make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); } +void kvm_make_update_eoibitmap_request(struct kvm *kvm) +{ + make_all_cpus_request(kvm, KVM_REQ_EOIBITMAP); +} + int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { struct page *page; -- cgit v1.2.3-70-g09d2 From 7a905b1485adf863607b5fc9e32a3fa3838bcc23 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Thu, 7 Feb 2013 18:55:57 +0900 Subject: KVM: Remove user_alloc from struct kvm_memory_slot This field was needed to differentiate memory slots created by the new API, KVM_SET_USER_MEMORY_REGION, from those by the old equivalent, KVM_SET_MEMORY_REGION, whose support was dropped long before: commit b74a07beed0e64bfba413dcb70dd6749c57f43dc KVM: Remove kernel-allocated memory regions Although we also have private memory slots to which KVM allocates memory with vm_mmap(), !user_alloc slots in other words, the slot id should be enough for differentiating them. Note: corresponding function parameters will be removed later. Reviewed-by: Marcelo Tosatti Signed-off-by: Takuya Yoshikawa Signed-off-by: Gleb Natapov --- arch/x86/kvm/x86.c | 37 ++++++++++++++++--------------------- include/linux/kvm_host.h | 1 - virt/kvm/kvm_main.c | 1 - 3 files changed, 16 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 373e17a0d39..3c5bb6fe528 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6897,33 +6897,28 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, bool user_alloc) { int npages = memslot->npages; - int map_flags = MAP_PRIVATE | MAP_ANONYMOUS; - /* Prevent internal slot pages from being moved by fork()/COW. */ - if (memslot->id >= KVM_USER_MEM_SLOTS) - map_flags = MAP_SHARED | MAP_ANONYMOUS; - - /*To keep backward compatibility with older userspace, - *x86 needs to handle !user_alloc case. + /* + * Only private memory slots need to be mapped here since + * KVM_SET_MEMORY_REGION ioctl is no longer supported. */ - if (!user_alloc) { - if (npages && !old.npages) { - unsigned long userspace_addr; + if ((memslot->id >= KVM_USER_MEM_SLOTS) && npages && !old.npages) { + unsigned long userspace_addr; - userspace_addr = vm_mmap(NULL, 0, - npages * PAGE_SIZE, - PROT_READ | PROT_WRITE, - map_flags, - 0); + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); - if (IS_ERR((void *)userspace_addr)) - return PTR_ERR((void *)userspace_addr); + if (IS_ERR((void *)userspace_addr)) + return PTR_ERR((void *)userspace_addr); - memslot->userspace_addr = userspace_addr; - } + memslot->userspace_addr = userspace_addr; } - return 0; } @@ -6935,7 +6930,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT; - if (!user_alloc && !old.user_alloc && old.npages && !npages) { + if ((mem->slot >= KVM_USER_MEM_SLOTS) && old.npages && !npages) { int ret; ret = vm_munmap(old.userspace_addr, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0350e0d5e03..722cae78bbc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -273,7 +273,6 @@ struct kvm_memory_slot { unsigned long userspace_addr; u32 flags; short id; - bool user_alloc; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2e93630b4ad..adc68feb5c5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -839,7 +839,6 @@ int __kvm_set_memory_region(struct kvm *kvm, r = -ENOMEM; if (change == KVM_MR_CREATE) { - new.user_alloc = user_alloc; new.userspace_addr = mem->userspace_addr; if (kvm_arch_create_memslot(&new, npages)) -- cgit v1.2.3-70-g09d2