From d6185f20a0efbf175e12831d0de330e4f21725aa Mon Sep 17 00:00:00 2001 From: Nadav Har'El Date: Thu, 22 Sep 2011 13:52:56 +0300 Subject: KVM: nVMX: Add KVM_REQ_IMMEDIATE_EXIT This patch adds a new vcpu->requests bit, KVM_REQ_IMMEDIATE_EXIT. This bit requests that when next entering the guest, we should run it only for as little as possible, and exit again. We use this new option in nested VMX: When L1 launches L2, but L0 wishes L1 to continue running so it can inject an event to it, we unfortunately cannot just pretend to have run L2 for a little while - We must really launch L2, otherwise certain one-off vmcs12 parameters (namely, L1 injection into L2) will be lost. So the existing code runs L2 in this case. But L2 could potentially run for a long time until it exits, and the injection into L1 will be delayed. The new KVM_REQ_IMMEDIATE_EXIT allows us to request that L2 will be entered, as necessary, but will exit as soon as possible after entry. Our implementation of this request uses smp_send_reschedule() to send a self-IPI, with interrupts disabled. The interrupts remain disabled until the guest is entered, and then, after the entry is complete (often including processing an injection and jumping to the relevant handler), the physical interrupt is noticed and causes an exit. On recent Intel processors, we could have achieved the same goal by using MTF instead of a self-IPI. Another technique worth considering in the future is to use VM_EXIT_ACK_INTR_ON_EXIT and a highest-priority vector IPI - to slightly improve performance by avoiding the useless interrupt handler which ends up being called when smp_send_reschedule() is used. Signed-off-by: Nadav Har'El Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 11 +++++++---- arch/x86/kvm/x86.c | 7 ++++++- include/linux/kvm_host.h | 1 + 3 files changed, 14 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 579a0b51696a..d75d91465246 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3945,12 +3945,15 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) static void enable_irq_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) - /* We can get here when nested_run_pending caused - * vmx_interrupt_allowed() to return false. In this case, do - * nothing - the interrupt will be injected later. + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { + /* + * We get here if vmx_interrupt_allowed() said we can't + * inject to L1 now because L2 must run. Ask L2 to exit + * right after entry, so we can inject to L1 more promptly. */ + kvm_make_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); return; + } cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4c938da2ba00..e24edbc7f2ec 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5648,6 +5648,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; + bool req_immediate_exit = 0; if (vcpu->requests) { if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) @@ -5687,7 +5688,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) record_steal_time(vcpu); if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - + req_immediate_exit = + kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); } r = kvm_mmu_reload(vcpu); @@ -5738,6 +5740,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (req_immediate_exit) + smp_send_reschedule(vcpu->cpu); + kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d52623199978..9fedeb356b95 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -50,6 +50,7 @@ #define KVM_REQ_APF_HALT 12 #define KVM_REQ_STEAL_UPDATE 13 #define KVM_REQ_NMI 14 +#define KVM_REQ_IMMEDIATE_EXIT 15 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 -- cgit v1.2.3 From 51cfe38ea50aa631f58ed8c340ed6f0143c325a8 Mon Sep 17 00:00:00 2001 From: Nadav Har'El Date: Thu, 22 Sep 2011 13:53:26 +0300 Subject: KVM: nVMX: Fix warning-causing idt-vectoring-info behavior When L0 wishes to inject an interrupt while L2 is running, it emulates an exit to L1 with EXIT_REASON_EXTERNAL_INTERRUPT. This was explained in the original nVMX patch 23, titled "Correct handling of interrupt injection". Unfortunately, it is possible (though rare) that at this point there is valid idt_vectoring_info in vmcs02. For example, L1 injected some interrupt to L2, and when L2 tried to run this interrupt's handler, it got a page fault - so it returns the original interrupt vector in idt_vectoring_info. The problem is that if this is the case, we cannot exit to L1 with EXTERNAL_INTERRUPT like we wished to, because the VMX spec guarantees that idt_vectoring_info and exit_reason_external_interrupt can never happen together. This is not just specified in the spec - a KVM L1 actually prints a kernel warning "unexpected, valid vectoring info" if we violate this guarantee, and some users noticed these warnings in L1's logs. In order to better emulate a processor, which would never return the external interrupt and the idt-vectoring-info together, we need to separate the two injection steps: First, complete L1's injection into L2 (i.e., enter L2, injecting to it the idt-vectoring-info); Second, after entry into L2 succeeds and it exits back to L0, exit to L1 with the EXIT_REASON_EXTERNAL_INTERRUPT. Most of this is already in the code - the only change we need is to remain in L2 (and not exit to L1) in this case. Note that the previous patch ensures (by using KVM_REQ_IMMEDIATE_EXIT) that although we do enter L2 first, it will exit immediately after processing its injection, allowing us to promptly inject to L1. Note how we test vmcs12->idt_vectoring_info_field; This isn't really the vmcs12 value (we haven't exited to L1 yet, so vmcs12 hasn't been updated), but rather the place we save, at the end of vmx_vcpu_run, the vmcs02 value of this field. This was explained in patch 25 ("Correct handling of idt vectoring info") of the original nVMX patch series. Thanks to Dave Allan and to Federico Simoncelli for reporting this bug, to Abel Gordon for helping me figure out the solution, and to Avi Kivity for helping to improve it. Signed-off-by: Nadav Har'El Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d75d91465246..6e28d582a514 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4080,11 +4080,12 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { - struct vmcs12 *vmcs12; - if (to_vmx(vcpu)->nested.nested_run_pending) + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + if (to_vmx(vcpu)->nested.nested_run_pending || + (vmcs12->idt_vectoring_info_field & + VECTORING_INFO_VALID_MASK)) return 0; nested_vmx_vmexit(vcpu); - vmcs12 = get_vmcs12(vcpu); vmcs12->vm_exit_reason = EXIT_REASON_EXTERNAL_INTERRUPT; vmcs12->vm_exit_intr_info = 0; /* fall through to normal code, but now in L1, not L2 */ -- cgit v1.2.3 From f759e2b4c728cee82e4bc1132d0e41177b79a0b1 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:53:17 +0800 Subject: KVM: MMU: avoid pte_list_desc running out in kvm_mmu_pte_write kvm_mmu_pte_write is unsafe since we need to alloc pte_list_desc in the function when spte is prefetched, unfortunately, we can not know how many spte need to be prefetched on this path, that means we can use out of the free pte_list_desc object in the cache, and BUG_ON() is triggered, also some path does not fill the cache, such as INS instruction emulated that does not trigger page fault Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f1b36cf3e3d0..232c5a30ddc8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -593,6 +593,11 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, return 0; } +static int mmu_memory_cache_free_objects(struct kvm_mmu_memory_cache *cache) +{ + return cache->nobjs; +} + static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc, struct kmem_cache *cache) { @@ -970,6 +975,14 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) return &linfo->rmap_pde; } +static bool rmap_can_add(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_memory_cache *cache; + + cache = &vcpu->arch.mmu_pte_list_desc_cache; + return mmu_memory_cache_free_objects(cache); +} + static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { struct kvm_mmu_page *sp; @@ -3586,6 +3599,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, break; } + /* + * No need to care whether allocation memory is successful + * or not since pte prefetch is skiped if it does not have + * enough objects in the cache. + */ + mmu_topup_memory_caches(vcpu); spin_lock(&vcpu->kvm->mmu_lock); if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) gentry = 0; @@ -3656,7 +3675,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mmu_page_zap_pte(vcpu->kvm, sp, spte); if (gentry && !((sp->role.word ^ vcpu->arch.mmu.base_role.word) - & mask.word)) + & mask.word) && rmap_can_add(vcpu)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); if (!remote_flush && need_remote_flush(entry, *spte)) remote_flush = true; @@ -3717,10 +3736,6 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, goto out; } - r = mmu_topup_memory_caches(vcpu); - if (r) - goto out; - er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len); switch (er) { -- cgit v1.2.3 From d5ae7ce835cc89556dc18e2070e754f026402efa Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:53:46 +0800 Subject: KVM: x86: tag the instructions which are used to write page table The idea is from Avi: | tag instructions that are typically used to modify the page tables, and | drop shadow if any other instruction is used. | The list would include, I'd guess, and, or, bts, btc, mov, xchg, cmpxchg, | and cmpxchg8b. This patch is used to tag the instructions and in the later path, shadow page is dropped if it is written by other instructions Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f1e3be18a08f..a10950a37928 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -125,8 +125,9 @@ #define Lock (1<<26) /* lock prefix is allowed for the instruction */ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) +#define PageTable (1 << 29) /* instruction used to write page table */ /* Source 2 operand type */ -#define Src2Shift (29) +#define Src2Shift (30) #define Src2None (OpNone << Src2Shift) #define Src2CL (OpCL << Src2Shift) #define Src2ImmByte (OpImmByte << Src2Shift) @@ -3033,10 +3034,10 @@ static struct opcode group7_rm7[] = { static struct opcode group1[] = { I(Lock, em_add), - I(Lock, em_or), + I(Lock | PageTable, em_or), I(Lock, em_adc), I(Lock, em_sbb), - I(Lock, em_and), + I(Lock | PageTable, em_and), I(Lock, em_sub), I(Lock, em_xor), I(0, em_cmp), @@ -3096,18 +3097,21 @@ static struct group_dual group7 = { { static struct opcode group8[] = { N, N, N, N, - D(DstMem | SrcImmByte | ModRM), D(DstMem | SrcImmByte | ModRM | Lock), - D(DstMem | SrcImmByte | ModRM | Lock), D(DstMem | SrcImmByte | ModRM | Lock), + D(DstMem | SrcImmByte | ModRM), + D(DstMem | SrcImmByte | ModRM | Lock | PageTable), + D(DstMem | SrcImmByte | ModRM | Lock), + D(DstMem | SrcImmByte | ModRM | Lock | PageTable), }; static struct group_dual group9 = { { - N, D(DstMem64 | ModRM | Lock), N, N, N, N, N, N, + N, D(DstMem64 | ModRM | Lock | PageTable), N, N, N, N, N, N, }, { N, N, N, N, N, N, N, N, } }; static struct opcode group11[] = { - I(DstMem | SrcImm | ModRM | Mov, em_mov), X7(D(Undefined)), + I(DstMem | SrcImm | ModRM | Mov | PageTable, em_mov), + X7(D(Undefined)), }; static struct gprefix pfx_0f_6f_0f_7f = { @@ -3120,7 +3124,7 @@ static struct opcode opcode_table[256] = { I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg), /* 0x08 - 0x0F */ - I6ALU(Lock, em_or), + I6ALU(Lock | PageTable, em_or), I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg), N, /* 0x10 - 0x17 */ @@ -3132,7 +3136,7 @@ static struct opcode opcode_table[256] = { I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg), /* 0x20 - 0x27 */ - I6ALU(Lock, em_and), N, N, + I6ALU(Lock | PageTable, em_and), N, N, /* 0x28 - 0x2F */ I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), /* 0x30 - 0x37 */ @@ -3165,11 +3169,11 @@ static struct opcode opcode_table[256] = { G(ByteOp | DstMem | SrcImm | ModRM | No64 | Group, group1), G(DstMem | SrcImmByte | ModRM | Group, group1), I2bv(DstMem | SrcReg | ModRM, em_test), - I2bv(DstMem | SrcReg | ModRM | Lock, em_xchg), + I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg), /* 0x88 - 0x8F */ - I2bv(DstMem | SrcReg | ModRM | Mov, em_mov), + I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov), I2bv(DstReg | SrcMem | ModRM | Mov, em_mov), - I(DstMem | SrcNone | ModRM | Mov, em_mov_rm_sreg), + I(DstMem | SrcNone | ModRM | Mov | PageTable, em_mov_rm_sreg), D(ModRM | SrcMem | NoAccess | DstReg), I(ImplicitOps | SrcMem16 | ModRM, em_mov_sreg_rm), G(0, group1A), @@ -3182,7 +3186,7 @@ static struct opcode opcode_table[256] = { II(ImplicitOps | Stack, em_popf, popf), N, N, /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), - I2bv(DstMem | SrcAcc | Mov | MemAbs, em_mov), + I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), I2bv(SrcSI | DstDI | Mov | String, em_mov), I2bv(SrcSI | DstDI | String, em_cmp), /* 0xA8 - 0xAF */ @@ -3280,12 +3284,13 @@ static struct opcode twobyte_table[256] = { D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), - DI(ImplicitOps, rsm), D(DstMem | SrcReg | ModRM | BitOp | Lock), + DI(ImplicitOps, rsm), + D(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ - D2bv(DstMem | SrcReg | ModRM | Lock), + D2bv(DstMem | SrcReg | ModRM | Lock | PageTable), I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), D(DstMem | SrcReg | ModRM | BitOp | Lock), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), @@ -3293,7 +3298,7 @@ static struct opcode twobyte_table[256] = { D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, - G(BitOp, group8), D(DstMem | SrcReg | ModRM | BitOp | Lock), + G(BitOp, group8), D(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable), D(DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xCF */ -- cgit v1.2.3 From 1cb3f3ae5a3855ba430430706da4201ace1d6ec4 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 17:02:48 +0800 Subject: KVM: x86: retry non-page-table writing instructions If the emulation is caused by #PF and it is non-page_table writing instruction, it means the VM-EXIT is caused by shadow page protected, we can zap the shadow page and retry this instruction directly The idea is from Avi Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_emulate.h | 1 + arch/x86/include/asm/kvm_host.h | 5 ++++ arch/x86/kvm/emulate.c | 5 ++++ arch/x86/kvm/mmu.c | 25 +++++++++++++++----- arch/x86/kvm/x86.c | 47 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 77 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index a026507893e9..9a4acf41709c 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -364,6 +364,7 @@ enum x86_intercept { #endif int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len); +bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt); #define EMULATION_FAILED -1 #define EMULATION_OK 0 #define EMULATION_RESTART 1 diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b4973f4dab98..4ceefa9567ed 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -444,6 +444,9 @@ struct kvm_vcpu_arch { cpumask_var_t wbinvd_dirty_mask; + unsigned long last_retry_eip; + unsigned long last_retry_addr; + struct { bool halted; gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)]; @@ -692,6 +695,7 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) +#define EMULTYPE_RETRY (1 << 3) int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, int emulation_type, void *insn, int insn_len); @@ -756,6 +760,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu); void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes, bool guest_initiated); +int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a10950a37928..8547958e3582 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3702,6 +3702,11 @@ done: return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } +bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt) +{ + return ctxt->d & PageTable; +} + static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) { /* The second termination condition only applies for REPE diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 232c5a30ddc8..7a22eb81b4ca 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1998,7 +1998,7 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; } -static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) { struct kvm_mmu_page *sp; struct hlist_node *node; @@ -2007,7 +2007,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; - + spin_lock(&kvm->mmu_lock); for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { pgprintk("%s: gfn %llx role %x\n", __func__, gfn, sp->role.word); @@ -2015,8 +2015,11 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } kvm_mmu_commit_zap_page(kvm, &invalid_list); + spin_unlock(&kvm->mmu_lock); + return r; } +EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) { @@ -3698,9 +3701,8 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - spin_lock(&vcpu->kvm->mmu_lock); r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - spin_unlock(&vcpu->kvm->mmu_lock); + return r; } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); @@ -3721,10 +3723,18 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); } +static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr) +{ + if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu)) + return vcpu_match_mmio_gpa(vcpu, addr); + + return vcpu_match_mmio_gva(vcpu, addr); +} + int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, void *insn, int insn_len) { - int r; + int r, emulation_type = EMULTYPE_RETRY; enum emulation_result er; r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false); @@ -3736,7 +3746,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, goto out; } - er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len); + if (is_mmio_page_fault(vcpu, cr2)) + emulation_type = 0; + + er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); switch (er) { case EMULATE_DONE: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e24edbc7f2ec..7ba1ab73fd03 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4836,6 +4836,50 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva) return false; } +static bool retry_instruction(struct x86_emulate_ctxt *ctxt, + unsigned long cr2, int emulation_type) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + + last_retry_eip = vcpu->arch.last_retry_eip; + last_retry_addr = vcpu->arch.last_retry_addr; + + /* + * If the emulation is caused by #PF and it is non-page_table + * writing instruction, it means the VM-EXIT is caused by shadow + * page protected, we can zap the shadow page and retry this + * instruction directly. + * + * Note: if the guest uses a non-page-table modifying instruction + * on the PDE that points to the instruction, then we will unmap + * the instruction and go to an infinite loop. So, we cache the + * last retried eip and the last fault address, if we meet the eip + * and the address again, we can break out of the potential infinite + * loop. + */ + vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; + + if (!(emulation_type & EMULTYPE_RETRY)) + return false; + + if (x86_page_table_writing_insn(ctxt)) + return false; + + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + return false; + + vcpu->arch.last_retry_eip = ctxt->eip; + vcpu->arch.last_retry_addr = cr2; + + if (!vcpu->arch.mmu.direct_map) + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + + kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); + + return true; +} + int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, int emulation_type, @@ -4877,6 +4921,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } + if (retry_instruction(ctxt, cr2, emulation_type)) + return EMULATE_DONE; + /* this is needed for vmware backdoor interface to work since it changes registers values during IO operation */ if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { -- cgit v1.2.3 From 6f6fbe98c3a9f3e9d69cd354a0459989e594e707 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:55:10 +0800 Subject: KVM: x86: cleanup port-in/port-out emulated Remove the same code between emulator_pio_in_emulated and emulator_pio_out_emulated Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 59 ++++++++++++++++++++++++------------------------------ 1 file changed, 26 insertions(+), 33 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7ba1ab73fd03..a2154487917d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4349,32 +4349,24 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) return r; } - -static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, void *val, - unsigned int count) +static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, + unsigned int count, bool in) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - if (vcpu->arch.pio.count) - goto data_avail; - - trace_kvm_pio(0, port, size, count); + trace_kvm_pio(!in, port, size, count); vcpu->arch.pio.port = port; - vcpu->arch.pio.in = 1; + vcpu->arch.pio.in = in; vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - data_avail: - memcpy(val, vcpu->arch.pio_data, size * count); vcpu->arch.pio.count = 0; return 1; } vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = KVM_EXIT_IO_IN; + vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; vcpu->run->io.size = size; vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; vcpu->run->io.count = count; @@ -4383,36 +4375,37 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, return 0; } -static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, - const void *val, unsigned int count) +static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int ret; - trace_kvm_pio(1, port, size, count); - - vcpu->arch.pio.port = port; - vcpu->arch.pio.in = 0; - vcpu->arch.pio.count = count; - vcpu->arch.pio.size = size; - - memcpy(vcpu->arch.pio_data, val, size * count); + if (vcpu->arch.pio.count) + goto data_avail; - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); + if (ret) { +data_avail: + memcpy(val, vcpu->arch.pio_data, size * count); vcpu->arch.pio.count = 0; return 1; } - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = KVM_EXIT_IO_OUT; - vcpu->run->io.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = count; - vcpu->run->io.port = port; - return 0; } +static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, + const void *val, unsigned int count) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + memcpy(vcpu->arch.pio_data, val, size * count); + return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); +} + static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { return kvm_x86_ops->get_segment_base(vcpu, seg); -- cgit v1.2.3 From d01f8d5e02cc79998e3160f7ad545f77891b00e5 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:55:36 +0800 Subject: KVM: MMU: do not mark accessed bit on pte write path In current code, the accessed bit is always set when page fault occurred, do not need to set it on pte write path Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/mmu.c | 22 +--------------------- 2 files changed, 1 insertion(+), 22 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4ceefa9567ed..f8ab0d760231 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -356,7 +356,6 @@ struct kvm_vcpu_arch { gfn_t last_pt_write_gfn; int last_pt_write_count; u64 *last_pte_updated; - gfn_t last_pte_gfn; struct fpu guest_fpu; u64 xcr0; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7a22eb81b4ca..b432a71a1839 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2207,11 +2207,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (set_mmio_spte(sptep, gfn, pfn, pte_access)) return 0; - /* - * We don't set the accessed bit, since we sometimes want to see - * whether the guest actually used the pte (in order to detect - * demand paging). - */ spte = PT_PRESENT_MASK; if (!speculative) spte |= shadow_accessed_mask; @@ -2362,10 +2357,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } } kvm_release_pfn_clean(pfn); - if (speculative) { + if (speculative) vcpu->arch.last_pte_updated = sptep; - vcpu->arch.last_pte_gfn = gfn; - } } static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) @@ -3533,18 +3526,6 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) return !!(spte && (*spte & shadow_accessed_mask)); } -static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - u64 *spte = vcpu->arch.last_pte_updated; - - if (spte - && vcpu->arch.last_pte_gfn == gfn - && shadow_accessed_mask - && !(*spte & shadow_accessed_mask) - && is_shadow_present_pte(*spte)) - set_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte); -} - void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes, bool guest_initiated) @@ -3615,7 +3596,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++vcpu->kvm->stat.mmu_pte_write; trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); if (guest_initiated) { - kvm_mmu_access_page(vcpu, gfn); if (gfn == vcpu->arch.last_pt_write_gfn && !last_updated_pte_accessed(vcpu)) { ++vcpu->arch.last_pt_write_count; -- cgit v1.2.3 From 505aef8f30a95f7e4abf2c07e54ded1521587ba0 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:56:06 +0800 Subject: KVM: MMU: cleanup FNAME(invlpg) Directly Use mmu_page_zap_pte to zap spte in FNAME(invlpg), also remove the same code between FNAME(invlpg) and FNAME(sync_page) Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 16 ++++++++++------ arch/x86/kvm/paging_tmpl.h | 44 +++++++++++++++++--------------------------- 2 files changed, 27 insertions(+), 33 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b432a71a1839..d15f908649e7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1809,7 +1809,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, } } -static void mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, +static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *spte) { u64 pte; @@ -1817,17 +1817,21 @@ static void mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, pte = *spte; if (is_shadow_present_pte(pte)) { - if (is_last_spte(pte, sp->role.level)) + if (is_last_spte(pte, sp->role.level)) { drop_spte(kvm, spte); - else { + if (is_large_pte(pte)) + --kvm->stat.lpages; + } else { child = page_header(pte & PT64_BASE_ADDR_MASK); drop_parent_pte(child, spte); } - } else if (is_mmio_spte(pte)) + return true; + } + + if (is_mmio_spte(pte)) mmu_spte_clear_no_track(spte); - if (is_large_pte(pte)) - --kvm->stat.lpages; + return false; } static void kvm_mmu_page_unlink_children(struct kvm *kvm, diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 92994100638b..d8d3906649da 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -656,6 +656,18 @@ out_unlock: return 0; } +static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) +{ + int offset = 0; + + WARN_ON(sp->role.level != 1); + + if (PTTYPE == 32) + offset = sp->role.quadrant << PT64_LEVEL_BITS; + + return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); +} + static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { struct kvm_shadow_walk_iterator iterator; @@ -663,7 +675,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) gpa_t pte_gpa = -1; int level; u64 *sptep; - int need_flush = 0; vcpu_clear_mmio_info(vcpu, gva); @@ -675,36 +686,20 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) sp = page_header(__pa(sptep)); if (is_last_spte(*sptep, level)) { - int offset, shift; - if (!sp->unsync) break; - shift = PAGE_SHIFT - - (PT_LEVEL_BITS - PT64_LEVEL_BITS) * level; - offset = sp->role.quadrant << shift; - - pte_gpa = (sp->gfn << PAGE_SHIFT) + offset; + pte_gpa = FNAME(get_level1_sp_gpa)(sp); pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); - if (is_shadow_present_pte(*sptep)) { - if (is_large_pte(*sptep)) - --vcpu->kvm->stat.lpages; - drop_spte(vcpu->kvm, sptep); - need_flush = 1; - } else if (is_mmio_spte(*sptep)) - mmu_spte_clear_no_track(sptep); - - break; + if (mmu_page_zap_pte(vcpu->kvm, sp, sptep)) + kvm_flush_remote_tlbs(vcpu->kvm); } if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) break; } - if (need_flush) - kvm_flush_remote_tlbs(vcpu->kvm); - atomic_inc(&vcpu->kvm->arch.invlpg_counter); spin_unlock(&vcpu->kvm->mmu_lock); @@ -769,19 +764,14 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - int i, offset, nr_present; + int i, nr_present = 0; bool host_writable; gpa_t first_pte_gpa; - offset = nr_present = 0; - /* direct kvm_mmu_page can not be unsync. */ BUG_ON(sp->role.direct); - if (PTTYPE == 32) - offset = sp->role.quadrant << PT64_LEVEL_BITS; - - first_pte_gpa = gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); + first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { unsigned pte_access; -- cgit v1.2.3 From f57f2ef58f6703e6df70ed52a198920cb3e8edba Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:56:39 +0800 Subject: KVM: MMU: fast prefetch spte on invlpg path Fast prefetch spte for the unsync shadow page on invlpg path Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 4 +--- arch/x86/kvm/mmu.c | 38 +++++++++++++++----------------------- arch/x86/kvm/paging_tmpl.h | 30 ++++++++++++++++++------------ arch/x86/kvm/x86.c | 4 ++-- 4 files changed, 36 insertions(+), 40 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8ab0d760231..3c9ea26c7aea 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -461,7 +461,6 @@ struct kvm_arch { unsigned int n_requested_mmu_pages; unsigned int n_max_mmu_pages; unsigned int indirect_shadow_pages; - atomic_t invlpg_counter; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. @@ -757,8 +756,7 @@ int fx_init(struct kvm_vcpu *vcpu); void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu); void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes, - bool guest_initiated); + const u8 *new, int bytes); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d15f908649e7..c01137f10c6b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3531,8 +3531,7 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes, - bool guest_initiated) + const u8 *new, int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; union kvm_mmu_page_role mask = { .word = 0 }; @@ -3541,7 +3540,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, LIST_HEAD(invalid_list); u64 entry, gentry, *spte; unsigned pte_size, page_offset, misaligned, quadrant, offset; - int level, npte, invlpg_counter, r, flooded = 0; + int level, npte, r, flooded = 0; bool remote_flush, local_flush, zap_page; /* @@ -3556,19 +3555,16 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter); - /* * Assume that the pte write on a page table of the same type * as the current vcpu paging mode since we update the sptes only * when they have the same mode. */ - if ((is_pae(vcpu) && bytes == 4) || !new) { + if (is_pae(vcpu) && bytes == 4) { /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ - if (is_pae(vcpu)) { - gpa &= ~(gpa_t)7; - bytes = 8; - } + gpa &= ~(gpa_t)7; + bytes = 8; + r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8)); if (r) gentry = 0; @@ -3594,22 +3590,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, */ mmu_topup_memory_caches(vcpu); spin_lock(&vcpu->kvm->mmu_lock); - if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) - gentry = 0; kvm_mmu_free_some_pages(vcpu); ++vcpu->kvm->stat.mmu_pte_write; trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - if (guest_initiated) { - if (gfn == vcpu->arch.last_pt_write_gfn - && !last_updated_pte_accessed(vcpu)) { - ++vcpu->arch.last_pt_write_count; - if (vcpu->arch.last_pt_write_count >= 3) - flooded = 1; - } else { - vcpu->arch.last_pt_write_gfn = gfn; - vcpu->arch.last_pt_write_count = 1; - vcpu->arch.last_pte_updated = NULL; - } + if (gfn == vcpu->arch.last_pt_write_gfn + && !last_updated_pte_accessed(vcpu)) { + ++vcpu->arch.last_pt_write_count; + if (vcpu->arch.last_pt_write_count >= 3) + flooded = 1; + } else { + vcpu->arch.last_pt_write_gfn = gfn; + vcpu->arch.last_pt_write_count = 1; + vcpu->arch.last_pte_updated = NULL; } mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index d8d3906649da..9efb86035774 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -672,20 +672,27 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; - gpa_t pte_gpa = -1; int level; u64 *sptep; vcpu_clear_mmio_info(vcpu, gva); - spin_lock(&vcpu->kvm->mmu_lock); + /* + * No need to check return value here, rmap_can_add() can + * help us to skip pte prefetch later. + */ + mmu_topup_memory_caches(vcpu); + spin_lock(&vcpu->kvm->mmu_lock); for_each_shadow_entry(vcpu, gva, iterator) { level = iterator.level; sptep = iterator.sptep; sp = page_header(__pa(sptep)); if (is_last_spte(*sptep, level)) { + pt_element_t gpte; + gpa_t pte_gpa; + if (!sp->unsync) break; @@ -694,22 +701,21 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (mmu_page_zap_pte(vcpu->kvm, sp, sptep)) kvm_flush_remote_tlbs(vcpu->kvm); + + if (!rmap_can_add(vcpu)) + break; + + if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, + sizeof(pt_element_t))) + break; + + FNAME(update_pte)(vcpu, sp, sptep, &gpte); } if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) break; } - - atomic_inc(&vcpu->kvm->arch.invlpg_counter); - spin_unlock(&vcpu->kvm->mmu_lock); - - if (pte_gpa == -1) - return; - - if (mmu_topup_memory_caches(vcpu)) - return; - kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0); } static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a2154487917d..9c980ce26e61 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4087,7 +4087,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); if (ret < 0) return 0; - kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1); + kvm_mmu_pte_write(vcpu, gpa, val, bytes); return 1; } @@ -4324,7 +4324,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (!exchanged) return X86EMUL_CMPXCHG_FAILED; - kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1); + kvm_mmu_pte_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; -- cgit v1.2.3 From f8734352c6f9c4f3d85f0c97b7731b7f925c62fd Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:56:58 +0800 Subject: KVM: MMU: remove unnecessary kvm_mmu_free_some_pages In kvm_mmu_pte_write, we do not need to alloc shadow page, so calling kvm_mmu_free_some_pages is really unnecessary Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index c01137f10c6b..7e57938bb86a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3590,7 +3590,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, */ mmu_topup_memory_caches(vcpu); spin_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_free_some_pages(vcpu); ++vcpu->kvm->stat.mmu_pte_write; trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); if (gfn == vcpu->arch.last_pt_write_gfn -- cgit v1.2.3 From 889e5cbced6c191bb7e25c1b30b43e59a12561f9 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:57:23 +0800 Subject: KVM: MMU: split kvm_mmu_pte_write function kvm_mmu_pte_write is too long, we split it for better readable Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 194 ++++++++++++++++++++++++++++++++--------------------- 1 file changed, 119 insertions(+), 75 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7e57938bb86a..986aea55366b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3530,48 +3530,28 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) return !!(spte && (*spte & shadow_accessed_mask)); } -void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes) +static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, + const u8 *new, int *bytes) { - gfn_t gfn = gpa >> PAGE_SHIFT; - union kvm_mmu_page_role mask = { .word = 0 }; - struct kvm_mmu_page *sp; - struct hlist_node *node; - LIST_HEAD(invalid_list); - u64 entry, gentry, *spte; - unsigned pte_size, page_offset, misaligned, quadrant, offset; - int level, npte, r, flooded = 0; - bool remote_flush, local_flush, zap_page; - - /* - * If we don't have indirect shadow pages, it means no page is - * write-protected, so we can exit simply. - */ - if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) - return; - - zap_page = remote_flush = local_flush = false; - offset = offset_in_page(gpa); - - pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); + u64 gentry; + int r; /* * Assume that the pte write on a page table of the same type * as the current vcpu paging mode since we update the sptes only * when they have the same mode. */ - if (is_pae(vcpu) && bytes == 4) { + if (is_pae(vcpu) && *bytes == 4) { /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ - gpa &= ~(gpa_t)7; - bytes = 8; - - r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8)); + *gpa &= ~(gpa_t)7; + *bytes = 8; + r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, min(*bytes, 8)); if (r) gentry = 0; new = (const u8 *)&gentry; } - switch (bytes) { + switch (*bytes) { case 4: gentry = *(const u32 *)new; break; @@ -3583,71 +3563,135 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, break; } - /* - * No need to care whether allocation memory is successful - * or not since pte prefetch is skiped if it does not have - * enough objects in the cache. - */ - mmu_topup_memory_caches(vcpu); - spin_lock(&vcpu->kvm->mmu_lock); - ++vcpu->kvm->stat.mmu_pte_write; - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); + return gentry; +} + +/* + * If we're seeing too many writes to a page, it may no longer be a page table, + * or we may be forking, in which case it is better to unmap the page. + */ +static bool detect_write_flooding(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + bool flooded = false; + if (gfn == vcpu->arch.last_pt_write_gfn && !last_updated_pte_accessed(vcpu)) { ++vcpu->arch.last_pt_write_count; if (vcpu->arch.last_pt_write_count >= 3) - flooded = 1; + flooded = true; } else { vcpu->arch.last_pt_write_gfn = gfn; vcpu->arch.last_pt_write_count = 1; vcpu->arch.last_pte_updated = NULL; } + return flooded; +} + +/* + * Misaligned accesses are too much trouble to fix up; also, they usually + * indicate a page is not used as a page table. + */ +static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, + int bytes) +{ + unsigned offset, pte_size, misaligned; + + pgprintk("misaligned: gpa %llx bytes %d role %x\n", + gpa, bytes, sp->role.word); + + offset = offset_in_page(gpa); + pte_size = sp->role.cr4_pae ? 8 : 4; + misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); + misaligned |= bytes < 4; + + return misaligned; +} + +static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) +{ + unsigned page_offset, quadrant; + u64 *spte; + int level; + + page_offset = offset_in_page(gpa); + level = sp->role.level; + *nspte = 1; + if (!sp->role.cr4_pae) { + page_offset <<= 1; /* 32->64 */ + /* + * A 32-bit pde maps 4MB while the shadow pdes map + * only 2MB. So we need to double the offset again + * and zap two pdes instead of one. + */ + if (level == PT32_ROOT_LEVEL) { + page_offset &= ~7; /* kill rounding error */ + page_offset <<= 1; + *nspte = 2; + } + quadrant = page_offset >> PAGE_SHIFT; + page_offset &= ~PAGE_MASK; + if (quadrant != sp->role.quadrant) + return NULL; + } + + spte = &sp->spt[page_offset / sizeof(*spte)]; + return spte; +} + +void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, + const u8 *new, int bytes) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + union kvm_mmu_page_role mask = { .word = 0 }; + struct kvm_mmu_page *sp; + struct hlist_node *node; + LIST_HEAD(invalid_list); + u64 entry, gentry, *spte; + int npte; + bool remote_flush, local_flush, zap_page, flooded, misaligned; + + /* + * If we don't have indirect shadow pages, it means no page is + * write-protected, so we can exit simply. + */ + if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) + return; + + zap_page = remote_flush = local_flush = false; + + pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); + + gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes); + + /* + * No need to care whether allocation memory is successful + * or not since pte prefetch is skiped if it does not have + * enough objects in the cache. + */ + mmu_topup_memory_caches(vcpu); + + spin_lock(&vcpu->kvm->mmu_lock); + ++vcpu->kvm->stat.mmu_pte_write; + trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); + + flooded = detect_write_flooding(vcpu, gfn); mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { - pte_size = sp->role.cr4_pae ? 8 : 4; - misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); - misaligned |= bytes < 4; + misaligned = detect_write_misaligned(sp, gpa, bytes); + if (misaligned || flooded) { - /* - * Misaligned accesses are too much trouble to fix - * up; also, they usually indicate a page is not used - * as a page table. - * - * If we're seeing too many writes to a page, - * it may no longer be a page table, or we may be - * forking, in which case it is better to unmap the - * page. - */ - pgprintk("misaligned: gpa %llx bytes %d role %x\n", - gpa, bytes, sp->role.word); zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } - page_offset = offset; - level = sp->role.level; - npte = 1; - if (!sp->role.cr4_pae) { - page_offset <<= 1; /* 32->64 */ - /* - * A 32-bit pde maps 4MB while the shadow pdes map - * only 2MB. So we need to double the offset again - * and zap two pdes instead of one. - */ - if (level == PT32_ROOT_LEVEL) { - page_offset &= ~7; /* kill rounding error */ - page_offset <<= 1; - npte = 2; - } - quadrant = page_offset >> PAGE_SHIFT; - page_offset &= ~PAGE_MASK; - if (quadrant != sp->role.quadrant) - continue; - } + + spte = get_written_sptes(sp, gpa, &npte); + if (!spte) + continue; + local_flush = true; - spte = &sp->spt[page_offset / sizeof(*spte)]; while (npte--) { entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte); -- cgit v1.2.3 From 5d9ca30e96f567b67a36727aa4ebb34911a2b84a Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:57:55 +0800 Subject: KVM: MMU: fix detecting misaligned accessed Sometimes, we only modify the last one byte of a pte to update status bit, for example, clear_bit is used to clear r/w bit in linux kernel and 'andb' instruction is used in this function, in this case, kvm_mmu_pte_write will treat it as misaligned access, and the shadow page table is zapped Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 986aea55366b..ca6f72ab4c3b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3602,6 +3602,14 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, offset = offset_in_page(gpa); pte_size = sp->role.cr4_pae ? 8 : 4; + + /* + * Sometimes, the OS only writes the last one bytes to update status + * bits, for example, in linux, andb instruction is used in clear_bit(). + */ + if (!(offset & (pte_size - 1)) && bytes == 1) + return false; + misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); misaligned |= bytes < 4; -- cgit v1.2.3 From a30f47cb150dd8d109923eeb65fe73e8b3e09046 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 22 Sep 2011 16:58:36 +0800 Subject: KVM: MMU: improve write flooding detected Detecting write-flooding does not work well, when we handle page written, if the last speculative spte is not accessed, we treat the page is write-flooding, however, we can speculative spte on many path, such as pte prefetch, page synced, that means the last speculative spte may be not point to the written page and the written page can be accessed via other sptes, so depends on the Accessed bit of the last speculative spte is not enough Instead of detected page accessed, we can detect whether the spte is accessed after it is written, if the spte is not accessed but it is written frequently, we treat is not a page table or it not used for a long time Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 6 ++-- arch/x86/kvm/mmu.c | 62 +++++++++++++++++------------------------ arch/x86/kvm/paging_tmpl.h | 12 ++++---- 3 files changed, 32 insertions(+), 48 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3c9ea26c7aea..c1f19de8b51c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -239,6 +239,8 @@ struct kvm_mmu_page { int clear_spte_count; #endif + int write_flooding_count; + struct rcu_head rcu; }; @@ -353,10 +355,6 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_page_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; - gfn_t last_pt_write_gfn; - int last_pt_write_count; - u64 *last_pte_updated; - struct fpu guest_fpu; u64 xcr0; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index ca6f72ab4c3b..e9534cec003f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1653,6 +1653,18 @@ static void init_shadow_page_table(struct kvm_mmu_page *sp) sp->spt[i] = 0ull; } +static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) +{ + sp->write_flooding_count = 0; +} + +static void clear_sp_write_flooding_count(u64 *spte) +{ + struct kvm_mmu_page *sp = page_header(__pa(spte)); + + __clear_sp_write_flooding_count(sp); +} + static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, @@ -1696,6 +1708,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, } else if (sp->unsync) kvm_mmu_mark_parents_unsync(sp); + __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); return sp; } @@ -1848,15 +1861,6 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) mmu_page_remove_parent_pte(sp, parent_pte); } -static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.last_pte_updated = NULL; -} - static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *parent_pte; @@ -1916,7 +1920,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, } sp->role.invalid = 1; - kvm_mmu_reset_last_pte_updated(kvm); return ret; } @@ -2361,8 +2364,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } } kvm_release_pfn_clean(pfn); - if (speculative) - vcpu->arch.last_pte_updated = sptep; } static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) @@ -3523,13 +3524,6 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page, kvm_mmu_flush_tlb(vcpu); } -static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) -{ - u64 *spte = vcpu->arch.last_pte_updated; - - return !!(spte && (*spte & shadow_accessed_mask)); -} - static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, const u8 *new, int *bytes) { @@ -3570,22 +3564,16 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, * If we're seeing too many writes to a page, it may no longer be a page table, * or we may be forking, in which case it is better to unmap the page. */ -static bool detect_write_flooding(struct kvm_vcpu *vcpu, gfn_t gfn) +static bool detect_write_flooding(struct kvm_mmu_page *sp, u64 *spte) { - bool flooded = false; - - if (gfn == vcpu->arch.last_pt_write_gfn - && !last_updated_pte_accessed(vcpu)) { - ++vcpu->arch.last_pt_write_count; - if (vcpu->arch.last_pt_write_count >= 3) - flooded = true; - } else { - vcpu->arch.last_pt_write_gfn = gfn; - vcpu->arch.last_pt_write_count = 1; - vcpu->arch.last_pte_updated = NULL; - } + /* + * Skip write-flooding detected for the sp whose level is 1, because + * it can become unsync, then the guest page is not write-protected. + */ + if (sp->role.level == 1) + return false; - return flooded; + return ++sp->write_flooding_count >= 3; } /* @@ -3657,7 +3645,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, LIST_HEAD(invalid_list); u64 entry, gentry, *spte; int npte; - bool remote_flush, local_flush, zap_page, flooded, misaligned; + bool remote_flush, local_flush, zap_page; /* * If we don't have indirect shadow pages, it means no page is @@ -3683,12 +3671,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++vcpu->kvm->stat.mmu_pte_write; trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - flooded = detect_write_flooding(vcpu, gfn); mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { - misaligned = detect_write_misaligned(sp, gpa, bytes); + spte = get_written_sptes(sp, gpa, &npte); - if (misaligned || flooded) { + if (detect_write_misaligned(sp, gpa, bytes) || + detect_write_flooding(sp, spte)) { zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 9efb86035774..52e9d58cec2b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -497,6 +497,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, shadow_walk_next(&it)) { gfn_t table_gfn; + clear_sp_write_flooding_count(it.sptep); drop_large_spte(vcpu, it.sptep); sp = NULL; @@ -522,6 +523,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, shadow_walk_next(&it)) { gfn_t direct_gfn; + clear_sp_write_flooding_count(it.sptep); validate_direct_spte(vcpu, it.sptep, direct_access); drop_large_spte(vcpu, it.sptep); @@ -536,6 +538,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(it.sptep, sp); } + clear_sp_write_flooding_count(it.sptep); mmu_set_spte(vcpu, it.sptep, access, gw->pte_access, user_fault, write_fault, emulate, it.level, gw->gfn, pfn, prefault, map_writable); @@ -599,11 +602,9 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, */ if (!r) { pgprintk("%s: guest page fault\n", __func__); - if (!prefault) { + if (!prefault) inject_page_fault(vcpu, &walker.fault); - /* reset fork detector */ - vcpu->arch.last_pt_write_count = 0; - } + return 0; } @@ -641,9 +642,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, pgprintk("%s: shadow pte %p %llx emulate %d\n", __func__, sptep, *sptep, emulate); - if (!emulate) - vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ - ++vcpu->stat.pf_fixed; trace_kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); spin_unlock(&vcpu->kvm->mmu_lock); -- cgit v1.2.3 From b297e672e24687546ac74af5ae5e8c4a022b9806 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Mon, 10 Oct 2011 11:46:15 -0400 Subject: KVM: Fix include dependency for mmu_notifier The kvm_host struct can include an mmu_notifier struct but mmu_notifier.h is not included directly. Signed-off-by: Eric B Munson Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9fedeb356b95..c6a2ec925846 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 3f2e5260f5a17d37be3e3c83aca2f335b9bf3893 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Wed, 14 Sep 2011 09:58:32 +0200 Subject: KVM: x86: Simplify kvm timer handler The vcpu reference of a kvm_timer can't become NULL while the timer is valid, so drop this redundant test. This also makes it pointless to carry a separate __kvm_timer_fn, fold it into kvm_timer_fn. Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/timer.c | 26 ++++---------------------- 1 file changed, 4 insertions(+), 22 deletions(-) diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c index ae432ea1cd83..6b85cc647f34 100644 --- a/arch/x86/kvm/timer.c +++ b/arch/x86/kvm/timer.c @@ -18,9 +18,10 @@ #include #include "kvm_timer.h" -static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) +enum hrtimer_restart kvm_timer_fn(struct hrtimer *data) { - int restart_timer = 0; + struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); + struct kvm_vcpu *vcpu = ktimer->vcpu; wait_queue_head_t *q = &vcpu->wq; /* @@ -40,26 +41,7 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) if (ktimer->t_ops->is_periodic(ktimer)) { hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); - restart_timer = 1; - } - - return restart_timer; -} - -enum hrtimer_restart kvm_timer_fn(struct hrtimer *data) -{ - int restart_timer; - struct kvm_vcpu *vcpu; - struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); - - vcpu = ktimer->vcpu; - if (!vcpu) - return HRTIMER_NORESTART; - - restart_timer = __kvm_timer_fn(vcpu, ktimer); - if (restart_timer) return HRTIMER_RESTART; - else + } else return HRTIMER_NORESTART; } - -- cgit v1.2.3 From 1a214246cbb431f7430f7d0c0fb66218a6f442d2 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 19 Oct 2011 09:15:10 +0300 Subject: KVM: make checks stricter in coalesced_mmio_in_range() My testing version of Smatch complains that addr and len come from the user and they can wrap. The path is: -> kvm_vm_ioctl() -> kvm_vm_ioctl_unregister_coalesced_mmio() -> coalesced_mmio_in_range() I don't know what the implications are of wrapping here, but we may as well fix it, if only to silence the warning. Signed-off-by: Dan Carpenter Signed-off-by: Marcelo Tosatti --- virt/kvm/coalesced_mmio.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index a6ec206f36ba..88b2fe3ddf42 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -28,9 +28,15 @@ static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, * (addr,len) is fully included in * (zone->addr, zone->size) */ - - return (dev->zone.addr <= addr && - addr + len <= dev->zone.addr + dev->zone.size); + if (len < 0) + return 0; + if (addr + len < addr) + return 0; + if (addr < dev->zone.addr) + return 0; + if (addr + len > dev->zone.addr + dev->zone.size) + return 0; + return 1; } static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev) -- cgit v1.2.3 From 5202397df819d3c5a3f201bd4af6b86542115fb6 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Tue, 1 Nov 2011 17:28:47 -0700 Subject: KVM guest: remove KVM guest pv mmu support This has not been used for some years now. It's time to remove it. Signed-off-by: Chris Wright Signed-off-by: Avi Kivity --- arch/x86/kernel/kvm.c | 181 -------------------------------------------------- 1 file changed, 181 deletions(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a9c2116001d6..f0c6fd6f176b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -39,8 +39,6 @@ #include #include -#define MMU_QUEUE_SIZE 1024 - static int kvmapf = 1; static int parse_no_kvmapf(char *arg) @@ -60,21 +58,10 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); -struct kvm_para_state { - u8 mmu_queue[MMU_QUEUE_SIZE]; - int mmu_queue_len; -}; - -static DEFINE_PER_CPU(struct kvm_para_state, para_state); static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); static int has_steal_clock = 0; -static struct kvm_para_state *kvm_para_state(void) -{ - return &per_cpu(para_state, raw_smp_processor_id()); -} - /* * No need for any "IO delay" on KVM */ @@ -271,151 +258,6 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) } } -static void kvm_mmu_op(void *buffer, unsigned len) -{ - int r; - unsigned long a1, a2; - - do { - a1 = __pa(buffer); - a2 = 0; /* on i386 __pa() always returns <4G */ - r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2); - buffer += r; - len -= r; - } while (len); -} - -static void mmu_queue_flush(struct kvm_para_state *state) -{ - if (state->mmu_queue_len) { - kvm_mmu_op(state->mmu_queue, state->mmu_queue_len); - state->mmu_queue_len = 0; - } -} - -static void kvm_deferred_mmu_op(void *buffer, int len) -{ - struct kvm_para_state *state = kvm_para_state(); - - if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) { - kvm_mmu_op(buffer, len); - return; - } - if (state->mmu_queue_len + len > sizeof state->mmu_queue) - mmu_queue_flush(state); - memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len); - state->mmu_queue_len += len; -} - -static void kvm_mmu_write(void *dest, u64 val) -{ - __u64 pte_phys; - struct kvm_mmu_op_write_pte wpte; - -#ifdef CONFIG_HIGHPTE - struct page *page; - unsigned long dst = (unsigned long) dest; - - page = kmap_atomic_to_page(dest); - pte_phys = page_to_pfn(page); - pte_phys <<= PAGE_SHIFT; - pte_phys += (dst & ~(PAGE_MASK)); -#else - pte_phys = (unsigned long)__pa(dest); -#endif - wpte.header.op = KVM_MMU_OP_WRITE_PTE; - wpte.pte_val = val; - wpte.pte_phys = pte_phys; - - kvm_deferred_mmu_op(&wpte, sizeof wpte); -} - -/* - * We only need to hook operations that are MMU writes. We hook these so that - * we can use lazy MMU mode to batch these operations. We could probably - * improve the performance of the host code if we used some of the information - * here to simplify processing of batched writes. - */ -static void kvm_set_pte(pte_t *ptep, pte_t pte) -{ - kvm_mmu_write(ptep, pte_val(pte)); -} - -static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - kvm_mmu_write(ptep, pte_val(pte)); -} - -static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd) -{ - kvm_mmu_write(pmdp, pmd_val(pmd)); -} - -#if PAGETABLE_LEVELS >= 3 -#ifdef CONFIG_X86_PAE -static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte) -{ - kvm_mmu_write(ptep, pte_val(pte)); -} - -static void kvm_pte_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - kvm_mmu_write(ptep, 0); -} - -static void kvm_pmd_clear(pmd_t *pmdp) -{ - kvm_mmu_write(pmdp, 0); -} -#endif - -static void kvm_set_pud(pud_t *pudp, pud_t pud) -{ - kvm_mmu_write(pudp, pud_val(pud)); -} - -#if PAGETABLE_LEVELS == 4 -static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd) -{ - kvm_mmu_write(pgdp, pgd_val(pgd)); -} -#endif -#endif /* PAGETABLE_LEVELS >= 3 */ - -static void kvm_flush_tlb(void) -{ - struct kvm_mmu_op_flush_tlb ftlb = { - .header.op = KVM_MMU_OP_FLUSH_TLB, - }; - - kvm_deferred_mmu_op(&ftlb, sizeof ftlb); -} - -static void kvm_release_pt(unsigned long pfn) -{ - struct kvm_mmu_op_release_pt rpt = { - .header.op = KVM_MMU_OP_RELEASE_PT, - .pt_phys = (u64)pfn << PAGE_SHIFT, - }; - - kvm_mmu_op(&rpt, sizeof rpt); -} - -static void kvm_enter_lazy_mmu(void) -{ - paravirt_enter_lazy_mmu(); -} - -static void kvm_leave_lazy_mmu(void) -{ - struct kvm_para_state *state = kvm_para_state(); - - mmu_queue_flush(state); - paravirt_leave_lazy_mmu(); -} - static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; @@ -424,29 +266,6 @@ static void __init paravirt_ops_setup(void) if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; - if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) { - pv_mmu_ops.set_pte = kvm_set_pte; - pv_mmu_ops.set_pte_at = kvm_set_pte_at; - pv_mmu_ops.set_pmd = kvm_set_pmd; -#if PAGETABLE_LEVELS >= 3 -#ifdef CONFIG_X86_PAE - pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic; - pv_mmu_ops.pte_clear = kvm_pte_clear; - pv_mmu_ops.pmd_clear = kvm_pmd_clear; -#endif - pv_mmu_ops.set_pud = kvm_set_pud; -#if PAGETABLE_LEVELS == 4 - pv_mmu_ops.set_pgd = kvm_set_pgd; -#endif -#endif - pv_mmu_ops.flush_tlb_user = kvm_flush_tlb; - pv_mmu_ops.release_pte = kvm_release_pt; - pv_mmu_ops.release_pmd = kvm_release_pt; - pv_mmu_ops.release_pud = kvm_release_pt; - - pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu; - pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu; - } #ifdef CONFIG_X86_IO_APIC no_timer_check = 1; #endif -- cgit v1.2.3 From fb92045843a8cd99c7b843d9b567a680a3854ba1 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Tue, 1 Nov 2011 17:31:18 -0700 Subject: KVM: MMU: remove KVM host pv mmu support The host side pv mmu support has been marked for feature removal in January 2011. It's not in use, is slower than shadow or hardware assisted paging, and a maintenance burden. It's November 2011, time to remove it. Signed-off-by: Chris Wright Signed-off-by: Avi Kivity --- Documentation/feature-removal-schedule.txt | 9 -- arch/x86/include/asm/kvm_host.h | 13 --- arch/x86/kvm/mmu.c | 135 ----------------------------- arch/x86/kvm/x86.c | 12 --- 4 files changed, 169 deletions(-) diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 3d849122b5b1..165019d527e6 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -362,15 +362,6 @@ Who: anybody or Florian Mickler ---------------------------- -What: KVM paravirt mmu host support -When: January 2011 -Why: The paravirt mmu host support is slower than non-paravirt mmu, both - on newer and older hardware. It is already not exposed to the guest, - and kept only for live migration purposes. -Who: Avi Kivity - ----------------------------- - What: iwlwifi 50XX module parameters When: 3.0 Why: The "..50" modules parameters were used to configure 5000 series and diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c1f19de8b51c..6d8326409974 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -244,13 +244,6 @@ struct kvm_mmu_page { struct rcu_head rcu; }; -struct kvm_pv_mmu_op_buffer { - void *ptr; - unsigned len; - unsigned processed; - char buf[512] __aligned(sizeof(long)); -}; - struct kvm_pio_request { unsigned long count; int in; @@ -347,10 +340,6 @@ struct kvm_vcpu_arch { */ struct kvm_mmu *walk_mmu; - /* only needed in kvm_pv_mmu_op() path, but it's hot so - * put it here to avoid allocation */ - struct kvm_pv_mmu_op_buffer mmu_op_buffer; - struct kvm_mmu_memory_cache mmu_pte_list_desc_cache; struct kvm_mmu_memory_cache mmu_page_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; @@ -667,8 +656,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); -int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes, - gpa_t addr, unsigned long *ret); u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); extern bool tdp_enabled; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e9534cec003f..a9b3a32bed08 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2028,20 +2028,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); -static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) -{ - struct kvm_mmu_page *sp; - struct hlist_node *node; - LIST_HEAD(invalid_list); - - for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { - pgprintk("%s: zap %llx %x\n", - __func__, gfn, sp->role.word); - kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - } - kvm_mmu_commit_zap_page(kvm, &invalid_list); -} - static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) { int slot = memslot_id(kvm, gfn); @@ -4004,127 +3990,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) return nr_mmu_pages; } -static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer, - unsigned len) -{ - if (len > buffer->len) - return NULL; - return buffer->ptr; -} - -static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer, - unsigned len) -{ - void *ret; - - ret = pv_mmu_peek_buffer(buffer, len); - if (!ret) - return ret; - buffer->ptr += len; - buffer->len -= len; - buffer->processed += len; - return ret; -} - -static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, - gpa_t addr, gpa_t value) -{ - int bytes = 8; - int r; - - if (!is_long_mode(vcpu) && !is_pae(vcpu)) - bytes = 4; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - if (!emulator_write_phys(vcpu, addr, &value, bytes)) - return -EFAULT; - - return 1; -} - -static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) -{ - (void)kvm_set_cr3(vcpu, kvm_read_cr3(vcpu)); - return 1; -} - -static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr) -{ - spin_lock(&vcpu->kvm->mmu_lock); - mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT); - spin_unlock(&vcpu->kvm->mmu_lock); - return 1; -} - -static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu, - struct kvm_pv_mmu_op_buffer *buffer) -{ - struct kvm_mmu_op_header *header; - - header = pv_mmu_peek_buffer(buffer, sizeof *header); - if (!header) - return 0; - switch (header->op) { - case KVM_MMU_OP_WRITE_PTE: { - struct kvm_mmu_op_write_pte *wpte; - - wpte = pv_mmu_read_buffer(buffer, sizeof *wpte); - if (!wpte) - return 0; - return kvm_pv_mmu_write(vcpu, wpte->pte_phys, - wpte->pte_val); - } - case KVM_MMU_OP_FLUSH_TLB: { - struct kvm_mmu_op_flush_tlb *ftlb; - - ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb); - if (!ftlb) - return 0; - return kvm_pv_mmu_flush_tlb(vcpu); - } - case KVM_MMU_OP_RELEASE_PT: { - struct kvm_mmu_op_release_pt *rpt; - - rpt = pv_mmu_read_buffer(buffer, sizeof *rpt); - if (!rpt) - return 0; - return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys); - } - default: return 0; - } -} - -int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes, - gpa_t addr, unsigned long *ret) -{ - int r; - struct kvm_pv_mmu_op_buffer *buffer = &vcpu->arch.mmu_op_buffer; - - buffer->ptr = buffer->buf; - buffer->len = min_t(unsigned long, bytes, sizeof buffer->buf); - buffer->processed = 0; - - r = kvm_read_guest(vcpu->kvm, addr, buffer->buf, buffer->len); - if (r) - goto out; - - while (buffer->len) { - r = kvm_pv_mmu_op_one(vcpu, buffer); - if (r < 0) - goto out; - if (r == 0) - break; - } - - r = 1; -out: - *ret = buffer->processed; - return r; -} - int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) { struct kvm_shadow_walk_iterator iterator; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9c980ce26e61..a3b25a524c9b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5273,15 +5273,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); -static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0, - unsigned long a1) -{ - if (is_long_mode(vcpu)) - return a0; - else - return a0 | ((gpa_t)a1 << 32); -} - int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { u64 param, ingpa, outgpa, ret; @@ -5377,9 +5368,6 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; - case KVM_HC_MMU_OP: - r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret); - break; default: ret = -KVM_ENOSYS; break; -- cgit v1.2.3 From 6da64fdb8c0c683016b70c96200057347aa8fbb0 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Tue, 8 Nov 2011 20:32:19 +0100 Subject: KVM: Use kmemdup rather than duplicating its implementation Use kmemdup rather than duplicating its implementation The semantic patch that makes this change is available in scripts/coccinelle/api/memdup.cocci. More information about semantic patching is available at http://coccinelle.lip6.fr/ Signed-off-by: Thomas Meyer Signed-off-by: Marcelo Tosatti --- virt/kvm/kvm_main.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d9cfb782cb81..4c5b9a239674 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -775,10 +775,10 @@ skip_lpage: if (!npages) { r = -ENOMEM; - slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), + GFP_KERNEL); if (!slots) goto out_free; - memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); if (mem->slot >= slots->nmemslots) slots->nmemslots = mem->slot + 1; slots->generation++; @@ -810,10 +810,10 @@ skip_lpage: } r = -ENOMEM; - slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), + GFP_KERNEL); if (!slots) goto out_free; - memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); if (mem->slot >= slots->nmemslots) slots->nmemslots = mem->slot + 1; slots->generation++; @@ -2520,10 +2520,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, if (bus->dev_count > NR_IOBUS_DEVS-1) return -ENOSPC; - new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); + new_bus = kmemdup(bus, sizeof(struct kvm_io_bus), GFP_KERNEL); if (!new_bus) return -ENOMEM; - memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); kvm_io_bus_insert_dev(new_bus, dev, addr, len); rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); -- cgit v1.2.3 From d6eebf8b80316ea61718dc115cd6a20c16195327 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Mon, 14 Nov 2011 18:21:34 +0900 Subject: KVM: MMU: Clean up BUG_ON() conditions in rmap_write_protect() Remove redundant checks and use is_large_pte() macro. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a9b3a32bed08..973f25480afa 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1027,7 +1027,6 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) spte = rmap_next(kvm, rmapp, NULL); while (spte) { - BUG_ON(!spte); BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); if (is_writable_pte(*spte)) { @@ -1043,9 +1042,8 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) rmapp = gfn_to_rmap(kvm, gfn, i); spte = rmap_next(kvm, rmapp, NULL); while (spte) { - BUG_ON(!spte); BUG_ON(!(*spte & PT_PRESENT_MASK)); - BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); + BUG_ON(!is_large_pte(*spte)); pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); if (is_writable_pte(*spte)) { drop_spte(kvm, spte); -- cgit v1.2.3 From 9b9b1492364758de82c19c36f07baa9ae162c7e5 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Mon, 14 Nov 2011 18:22:28 +0900 Subject: KVM: MMU: Split gfn_to_rmap() into two functions rmap_write_protect() calls gfn_to_rmap() for each level with gfn fixed. This results in calling gfn_to_memslot() repeatedly with that gfn. This patch introduces __gfn_to_rmap() which takes the slot as an argument to avoid this. This is also needed for the following dirty logging optimization. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 973f25480afa..fa71085f75a3 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -958,23 +958,29 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) } } -/* - * Take gfn and return the reverse mapping to it. - */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) +static unsigned long *__gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level, + struct kvm_memory_slot *slot) { - struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; - slot = gfn_to_memslot(kvm, gfn); if (likely(level == PT_PAGE_TABLE_LEVEL)) return &slot->rmap[gfn - slot->base_gfn]; linfo = lpage_info_slot(gfn, slot, level); - return &linfo->rmap_pde; } +/* + * Take gfn and return the reverse mapping to it. + */ +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) +{ + struct kvm_memory_slot *slot; + + slot = gfn_to_memslot(kvm, gfn); + return __gfn_to_rmap(kvm, gfn, level, slot); +} + static bool rmap_can_add(struct kvm_vcpu *vcpu) { struct kvm_mmu_memory_cache *cache; @@ -1019,12 +1025,14 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) static int rmap_write_protect(struct kvm *kvm, u64 gfn) { + struct kvm_memory_slot *slot; unsigned long *rmapp; u64 *spte; int i, write_protected = 0; - rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL); + slot = gfn_to_memslot(kvm, gfn); + rmapp = __gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL, slot); spte = rmap_next(kvm, rmapp, NULL); while (spte) { BUG_ON(!(*spte & PT_PRESENT_MASK)); @@ -1039,7 +1047,7 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) /* check for huge page mappings */ for (i = PT_DIRECTORY_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - rmapp = gfn_to_rmap(kvm, gfn, i); + rmapp = __gfn_to_rmap(kvm, gfn, i, slot); spte = rmap_next(kvm, rmapp, NULL); while (spte) { BUG_ON(!(*spte & PT_PRESENT_MASK)); -- cgit v1.2.3 From 7850ac5420803996e2960d15b924021f28e0dffc Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Mon, 14 Nov 2011 18:23:34 +0900 Subject: KVM: Count the number of dirty pages for dirty logging Needed for the next patch which uses this number to decide how to write protect a slot. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 9 +++------ include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 4 +++- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a3b25a524c9b..220c83b0fbda 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3466,10 +3466,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - int r, i; + int r; struct kvm_memory_slot *memslot; unsigned long n; - unsigned long is_dirty = 0; mutex_lock(&kvm->slots_lock); @@ -3484,11 +3483,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, n = kvm_dirty_bitmap_bytes(memslot); - for (i = 0; !is_dirty && i < n/sizeof(long); i++) - is_dirty = memslot->dirty_bitmap[i]; - /* If nothing is dirty, don't bother messing with page tables. */ - if (is_dirty) { + if (memslot->nr_dirty_pages) { struct kvm_memslots *slots, *old_slots; unsigned long *dirty_bitmap; @@ -3503,6 +3499,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, goto out; memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); slots->memslots[log->slot].dirty_bitmap = dirty_bitmap; + slots->memslots[log->slot].nr_dirty_pages = 0; slots->generation++; old_slots = kvm->memslots; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c6a2ec925846..7c654aa46b6c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -181,6 +181,7 @@ struct kvm_memory_slot { unsigned long *rmap; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_head; + unsigned long nr_dirty_pages; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; unsigned long userspace_addr; int user_alloc; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4c5b9a239674..af5c988cafcc 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -625,6 +625,7 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) return -ENOMEM; memslot->dirty_bitmap_head = memslot->dirty_bitmap; + memslot->nr_dirty_pages = 0; return 0; } #endif /* !CONFIG_S390 */ @@ -1491,7 +1492,8 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; - __set_bit_le(rel_gfn, memslot->dirty_bitmap); + if (!__test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap)) + memslot->nr_dirty_pages++; } } -- cgit v1.2.3 From 95d4c16ce78cb6b7549a09159c409d52ddd18dae Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Mon, 14 Nov 2011 18:24:50 +0900 Subject: KVM: Optimize dirty logging by rmap_write_protect() Currently, write protecting a slot needs to walk all the shadow pages and checks ones which have a pte mapping a page in it. The walk is overly heavy when dirty pages in that slot are not so many and checking the shadow pages would result in unwanted cache pollution. To mitigate this problem, we use rmap_write_protect() and check only the sptes which can be reached from gfns marked in the dirty bitmap when the number of dirty pages are less than that of shadow pages. This criterion is reasonable in its meaning and worked well in our test: write protection became some times faster than before when the ratio of dirty pages are low and was not worse even when the ratio was near the criterion. Note that the locking for this write protection becomes fine grained. The reason why this is safe is descripted in the comments. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/mmu.c | 14 +++++++--- arch/x86/kvm/x86.c | 58 ++++++++++++++++++++++++++++++++++++----- 3 files changed, 63 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6d8326409974..69b652547489 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -648,6 +648,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, int kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot); +int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, + struct kvm_memory_slot *slot); void kvm_mmu_zap_all(struct kvm *kvm); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index fa71085f75a3..aecdea265f7e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1023,15 +1023,13 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) rmap_remove(kvm, sptep); } -static int rmap_write_protect(struct kvm *kvm, u64 gfn) +int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, + struct kvm_memory_slot *slot) { - struct kvm_memory_slot *slot; unsigned long *rmapp; u64 *spte; int i, write_protected = 0; - slot = gfn_to_memslot(kvm, gfn); - rmapp = __gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL, slot); spte = rmap_next(kvm, rmapp, NULL); while (spte) { @@ -1066,6 +1064,14 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) return write_protected; } +static int rmap_write_protect(struct kvm *kvm, u64 gfn) +{ + struct kvm_memory_slot *slot; + + slot = gfn_to_memslot(kvm, gfn); + return kvm_mmu_rmap_write_protect(kvm, gfn, slot); +} + static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, unsigned long data) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 220c83b0fbda..af546b768ffd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3460,6 +3460,50 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, return 0; } +/** + * write_protect_slot - write protect a slot for dirty logging + * @kvm: the kvm instance + * @memslot: the slot we protect + * @dirty_bitmap: the bitmap indicating which pages are dirty + * @nr_dirty_pages: the number of dirty pages + * + * We have two ways to find all sptes to protect: + * 1. Use kvm_mmu_slot_remove_write_access() which walks all shadow pages and + * checks ones that have a spte mapping a page in the slot. + * 2. Use kvm_mmu_rmap_write_protect() for each gfn found in the bitmap. + * + * Generally speaking, if there are not so many dirty pages compared to the + * number of shadow pages, we should use the latter. + * + * Note that letting others write into a page marked dirty in the old bitmap + * by using the remaining tlb entry is not a problem. That page will become + * write protected again when we flush the tlb and then be reported dirty to + * the user space by copying the old bitmap. + */ +static void write_protect_slot(struct kvm *kvm, + struct kvm_memory_slot *memslot, + unsigned long *dirty_bitmap, + unsigned long nr_dirty_pages) +{ + /* Not many dirty pages compared to # of shadow pages. */ + if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) { + unsigned long gfn_offset; + + for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) { + unsigned long gfn = memslot->base_gfn + gfn_offset; + + spin_lock(&kvm->mmu_lock); + kvm_mmu_rmap_write_protect(kvm, gfn, memslot); + spin_unlock(&kvm->mmu_lock); + } + kvm_flush_remote_tlbs(kvm); + } else { + spin_lock(&kvm->mmu_lock); + kvm_mmu_slot_remove_write_access(kvm, memslot->id); + spin_unlock(&kvm->mmu_lock); + } +} + /* * Get (and clear) the dirty memory log for a memory slot. */ @@ -3468,7 +3512,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, { int r; struct kvm_memory_slot *memslot; - unsigned long n; + unsigned long n, nr_dirty_pages; mutex_lock(&kvm->slots_lock); @@ -3482,9 +3526,10 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, goto out; n = kvm_dirty_bitmap_bytes(memslot); + nr_dirty_pages = memslot->nr_dirty_pages; /* If nothing is dirty, don't bother messing with page tables. */ - if (memslot->nr_dirty_pages) { + if (nr_dirty_pages) { struct kvm_memslots *slots, *old_slots; unsigned long *dirty_bitmap; @@ -3498,8 +3543,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (!slots) goto out; memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); - slots->memslots[log->slot].dirty_bitmap = dirty_bitmap; - slots->memslots[log->slot].nr_dirty_pages = 0; + memslot = &slots->memslots[log->slot]; + memslot->dirty_bitmap = dirty_bitmap; + memslot->nr_dirty_pages = 0; slots->generation++; old_slots = kvm->memslots; @@ -3508,9 +3554,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap; kfree(old_slots); - spin_lock(&kvm->mmu_lock); - kvm_mmu_slot_remove_write_access(kvm, log->slot); - spin_unlock(&kvm->mmu_lock); + write_protect_slot(kvm, memslot, dirty_bitmap, nr_dirty_pages); r = -EFAULT; if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) -- cgit v1.2.3 From 46199f33c29533e7ad2a7d2128dc30175d1d4157 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 17 Nov 2011 10:56:09 +0200 Subject: KVM: VMX: remove unneeded vmx_load_host_state() calls. vmx_load_host_state() does not handle msrs switching (except MSR_KERNEL_GS_BASE) since commit 26bb0981b3f. Remove call to it where it is no longer make sense. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6e28d582a514..ba24022f4575 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1747,7 +1747,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) int save_nmsrs, index; unsigned long *msr_bitmap; - vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { @@ -2142,12 +2141,10 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) return 1; /* Otherwise falls through */ default: - vmx_load_host_state(to_vmx(vcpu)); if (vmx_get_vmx_msr(vcpu, msr_index, pdata)) return 0; msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { - vmx_load_host_state(to_vmx(vcpu)); data = msr->data; break; } @@ -2171,7 +2168,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) switch (msr_index) { case MSR_EFER: - vmx_load_host_state(vmx); ret = kvm_set_msr_common(vcpu, msr_index, data); break; #ifdef CONFIG_X86_64 @@ -2220,7 +2216,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) break; msr = find_msr_entry(vmx, msr_index); if (msr) { - vmx_load_host_state(vmx); msr->data = data; break; } -- cgit v1.2.3 From d7841a4b1b6e8509881e1ec21c024c82ccf565a6 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 22 Nov 2011 15:16:54 +0900 Subject: KVM: x86 emulator: Use opcode::execute for IN/OUT IN : E4, E5, EC, ED OUT: E6, E7, EE, EF Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 54 ++++++++++++++++++++++++++------------------------ 1 file changed, 28 insertions(+), 26 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8547958e3582..8ba4ea8cac72 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2776,6 +2776,24 @@ static int em_jcxz(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_in(struct x86_emulate_ctxt *ctxt) +{ + if (!pio_in_emulated(ctxt, ctxt->dst.bytes, ctxt->src.val, + &ctxt->dst.val)) + return X86EMUL_IO_NEEDED; + + return X86EMUL_CONTINUE; +} + +static int em_out(struct x86_emulate_ctxt *ctxt) +{ + ctxt->ops->pio_out_emulated(ctxt, ctxt->src.bytes, ctxt->dst.val, + &ctxt->src.val, 1); + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + static int em_cli(struct x86_emulate_ctxt *ctxt) { if (emulator_bad_iopl(ctxt)) @@ -3004,6 +3022,8 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) #define D2bv(_f) D((_f) | ByteOp), D(_f) #define D2bvIP(_f, _i, _p) DIP((_f) | ByteOp, _i, _p), DIP(_f, _i, _p) #define I2bv(_f, _e) I((_f) | ByteOp, _e), I(_f, _e) +#define I2bvIP(_f, _e, _i, _p) \ + IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p) #define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e), \ I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ @@ -3217,13 +3237,13 @@ static struct opcode opcode_table[256] = { /* 0xE0 - 0xE7 */ X3(I(SrcImmByte, em_loop)), I(SrcImmByte, em_jcxz), - D2bvIP(SrcImmUByte | DstAcc, in, check_perm_in), - D2bvIP(SrcAcc | DstImmUByte, out, check_perm_out), + I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in), + I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out), /* 0xE8 - 0xEF */ D(SrcImm | Stack), D(SrcImm | ImplicitOps), I(SrcImmFAddr | No64, em_jmp_far), D(SrcImmByte | ImplicitOps), - D2bvIP(SrcDX | DstAcc, in, check_perm_in), - D2bvIP(SrcAcc | DstDX, out, check_perm_out), + I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in), + I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out), /* 0xF0 - 0xF7 */ N, DI(ImplicitOps, icebp), N, N, DI(ImplicitOps | Priv, hlt), D(ImplicitOps), @@ -3325,6 +3345,7 @@ static struct opcode twobyte_table[256] = { #undef D2bv #undef D2bvIP #undef I2bv +#undef I2bvIP #undef I6ALU static unsigned imm_size(struct x86_emulate_ctxt *ctxt) @@ -3867,11 +3888,12 @@ special_insn: case 0x6c: /* insb */ case 0x6d: /* insw/insd */ ctxt->src.val = ctxt->regs[VCPU_REGS_RDX]; - goto do_io_in; + rc = em_in(ctxt); + break; case 0x6e: /* outsb */ case 0x6f: /* outsw/outsd */ ctxt->dst.val = ctxt->regs[VCPU_REGS_RDX]; - goto do_io_out; + rc = em_out(ctxt); break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) @@ -3915,12 +3937,6 @@ special_insn: ctxt->src.val = ctxt->regs[VCPU_REGS_RCX]; rc = em_grp2(ctxt); break; - case 0xe4: /* inb */ - case 0xe5: /* in */ - goto do_io_in; - case 0xe6: /* outb */ - case 0xe7: /* out */ - goto do_io_out; case 0xe8: /* call (near) */ { long int rel = ctxt->src.val; ctxt->src.val = (unsigned long) ctxt->_eip; @@ -3933,20 +3949,6 @@ special_insn: jmp_rel(ctxt, ctxt->src.val); ctxt->dst.type = OP_NONE; /* Disable writeback. */ break; - case 0xec: /* in al,dx */ - case 0xed: /* in (e/r)ax,dx */ - do_io_in: - if (!pio_in_emulated(ctxt, ctxt->dst.bytes, ctxt->src.val, - &ctxt->dst.val)) - goto done; /* IO is needed */ - break; - case 0xee: /* out dx,al */ - case 0xef: /* out dx,(e/r)ax */ - do_io_out: - ops->pio_out_emulated(ctxt, ctxt->src.bytes, ctxt->dst.val, - &ctxt->src.val, 1); - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - break; case 0xf4: /* hlt */ ctxt->ops->halt(ctxt); break; -- cgit v1.2.3 From ce7faab24fbfb0b5207636ee4795e924bcf97e8a Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 22 Nov 2011 15:17:48 +0900 Subject: KVM: x86 emulator: Use opcode::execute for BT family BT : 0F A3 BTS: 0F AB BTR: 0F B3 BTC: 0F BB Group 8: 0F BA Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 77 +++++++++++++++++++++++++------------------------- 1 file changed, 38 insertions(+), 39 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8ba4ea8cac72..7a9ce6dbd1ce 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2813,6 +2813,35 @@ static int em_sti(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_bt(struct x86_emulate_ctxt *ctxt) +{ + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + /* only subword offset */ + ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; + + emulate_2op_SrcV_nobyte(ctxt, "bt"); + return X86EMUL_CONTINUE; +} + +static int em_bts(struct x86_emulate_ctxt *ctxt) +{ + emulate_2op_SrcV_nobyte(ctxt, "bts"); + return X86EMUL_CONTINUE; +} + +static int em_btr(struct x86_emulate_ctxt *ctxt) +{ + emulate_2op_SrcV_nobyte(ctxt, "btr"); + return X86EMUL_CONTINUE; +} + +static int em_btc(struct x86_emulate_ctxt *ctxt) +{ + emulate_2op_SrcV_nobyte(ctxt, "btc"); + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -3117,10 +3146,10 @@ static struct group_dual group7 = { { static struct opcode group8[] = { N, N, N, N, - D(DstMem | SrcImmByte | ModRM), - D(DstMem | SrcImmByte | ModRM | Lock | PageTable), - D(DstMem | SrcImmByte | ModRM | Lock), - D(DstMem | SrcImmByte | ModRM | Lock | PageTable), + I(DstMem | SrcImmByte | ModRM, em_bt), + I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_bts), + I(DstMem | SrcImmByte | ModRM | Lock, em_btr), + I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_btc), }; static struct group_dual group9 = { { @@ -3299,26 +3328,27 @@ static struct opcode twobyte_table[256] = { X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), - DI(ImplicitOps, cpuid), D(DstMem | SrcReg | ModRM | BitOp), + DI(ImplicitOps, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), DI(ImplicitOps, rsm), - D(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable), + I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ D2bv(DstMem | SrcReg | ModRM | Lock | PageTable), I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), - D(DstMem | SrcReg | ModRM | BitOp | Lock), + I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, - G(BitOp, group8), D(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable), + G(BitOp, group8), + I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), D(DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xCF */ @@ -4103,21 +4133,10 @@ twobyte_insn: case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); break; - case 0xa3: - bt: /* bt */ - ctxt->dst.type = OP_NONE; - /* only subword offset */ - ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; - emulate_2op_SrcV_nobyte(ctxt, "bt"); - break; case 0xa4: /* shld imm8, r, r/m */ case 0xa5: /* shld cl, r, r/m */ emulate_2op_cl(ctxt, "shld"); break; - case 0xab: - bts: /* bts */ - emulate_2op_SrcV_nobyte(ctxt, "bts"); - break; case 0xac: /* shrd imm8, r, r/m */ case 0xad: /* shrd cl, r, r/m */ emulate_2op_cl(ctxt, "shrd"); @@ -4141,31 +4160,11 @@ twobyte_insn: ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX]; } break; - case 0xb3: - btr: /* btr */ - emulate_2op_SrcV_nobyte(ctxt, "btr"); - break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val : (u16) ctxt->src.val; break; - case 0xba: /* Grp8 */ - switch (ctxt->modrm_reg & 3) { - case 0: - goto bt; - case 1: - goto bts; - case 2: - goto btr; - case 3: - goto btc; - } - break; - case 0xbb: - btc: /* btc */ - emulate_2op_SrcV_nobyte(ctxt, "btc"); - break; case 0xbc: { /* bsf */ u8 zf; __asm__ ("bsf %2, %0; setz %1" -- cgit v1.2.3 From d4ddafcdf2201326ec9717172767cfad0ede1472 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 22 Nov 2011 15:18:35 +0900 Subject: KVM: x86 emulator: Use opcode::execute for CALL CALL: E8 Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 7a9ce6dbd1ce..6b7a03b18f89 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2482,6 +2482,15 @@ static int em_das(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_call(struct x86_emulate_ctxt *ctxt) +{ + long rel = ctxt->src.val; + + ctxt->src.val = (unsigned long)ctxt->_eip; + jmp_rel(ctxt, rel); + return em_push(ctxt); +} + static int em_call_far(struct x86_emulate_ctxt *ctxt) { u16 sel, old_cs; @@ -3269,7 +3278,7 @@ static struct opcode opcode_table[256] = { I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in), I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out), /* 0xE8 - 0xEF */ - D(SrcImm | Stack), D(SrcImm | ImplicitOps), + I(SrcImm | Stack, em_call), D(SrcImm | ImplicitOps), I(SrcImmFAddr | No64, em_jmp_far), D(SrcImmByte | ImplicitOps), I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in), I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out), @@ -3967,13 +3976,6 @@ special_insn: ctxt->src.val = ctxt->regs[VCPU_REGS_RCX]; rc = em_grp2(ctxt); break; - case 0xe8: /* call (near) */ { - long int rel = ctxt->src.val; - ctxt->src.val = (unsigned long) ctxt->_eip; - jmp_rel(ctxt, rel); - rc = em_push(ctxt); - break; - } case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ jmp_rel(ctxt, ctxt->src.val); -- cgit v1.2.3 From bc00f8d2c2df33c6e7fc8a12c94c0c74d491e566 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 22 Nov 2011 15:19:19 +0900 Subject: KVM: x86 emulator: Use opcode::execute for MOV to cr/dr MOV: 0F 22 (move to control registers) MOV: 0F 23 (move to debug registers) Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 52 +++++++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 22 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 6b7a03b18f89..7fe5ed126f6f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2638,6 +2638,34 @@ static int em_mov(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_cr_write(struct x86_emulate_ctxt *ctxt) +{ + if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + return emulate_gp(ctxt, 0); + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static int em_dr_write(struct x86_emulate_ctxt *ctxt) +{ + unsigned long val; + + if (ctxt->mode == X86EMUL_MODE_PROT64) + val = ctxt->src.val & ~0ULL; + else + val = ctxt->src.val & ~0U; + + /* #UD condition is already handled. */ + if (ctxt->ops->set_dr(ctxt, ctxt->modrm_reg, val) < 0) + return emulate_gp(ctxt, 0); + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) { if (ctxt->modrm_reg > VCPU_SREG_GS) @@ -3304,8 +3332,8 @@ static struct opcode twobyte_table[256] = { /* 0x20 - 0x2F */ DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read), DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read), - DIP(ModRM | SrcMem | Priv | Op3264, cr_write, check_cr_write), - DIP(ModRM | SrcMem | Priv | Op3264, dr_write, check_dr_write), + IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write), + IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write), N, N, N, N, N, N, N, N, N, N, N, N, /* 0x30 - 0x3F */ @@ -4080,26 +4108,6 @@ twobyte_insn: case 0x21: /* mov from dr to reg */ ops->get_dr(ctxt, ctxt->modrm_reg, &ctxt->dst.val); break; - case 0x22: /* mov reg, cr */ - if (ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) { - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - ctxt->dst.type = OP_NONE; - break; - case 0x23: /* mov from reg to dr */ - if (ops->set_dr(ctxt, ctxt->modrm_reg, ctxt->src.val & - ((ctxt->mode == X86EMUL_MODE_PROT64) ? - ~0ULL : ~0U)) < 0) { - /* #UD condition is already handled by the code above */ - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - - ctxt->dst.type = OP_NONE; /* no writeback */ - break; case 0x30: /* wrmsr */ msr_data = (u32)ctxt->regs[VCPU_REGS_RAX] -- cgit v1.2.3 From e1e210b0a7f7b4d14577bdc76719963f7facc0e7 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 22 Nov 2011 15:20:03 +0900 Subject: KVM: x86 emulator: Use opcode::execute for WRMSR/RDMSR WRMSR: 0F 30 RDMSR: 0F 32 Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 52 +++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 7fe5ed126f6f..906c5eb34aa7 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2666,6 +2666,30 @@ static int em_dr_write(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_wrmsr(struct x86_emulate_ctxt *ctxt) +{ + u64 msr_data; + + msr_data = (u32)ctxt->regs[VCPU_REGS_RAX] + | ((u64)ctxt->regs[VCPU_REGS_RDX] << 32); + if (ctxt->ops->set_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], msr_data)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + +static int em_rdmsr(struct x86_emulate_ctxt *ctxt) +{ + u64 msr_data; + + if (ctxt->ops->get_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], &msr_data)) + return emulate_gp(ctxt, 0); + + ctxt->regs[VCPU_REGS_RAX] = (u32)msr_data; + ctxt->regs[VCPU_REGS_RDX] = msr_data >> 32; + return X86EMUL_CONTINUE; +} + static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) { if (ctxt->modrm_reg > VCPU_SREG_GS) @@ -3337,9 +3361,9 @@ static struct opcode twobyte_table[256] = { N, N, N, N, N, N, N, N, N, N, N, N, /* 0x30 - 0x3F */ - DI(ImplicitOps | Priv, wrmsr), + II(ImplicitOps | Priv, em_wrmsr, wrmsr), IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), - DI(ImplicitOps | Priv, rdmsr), + II(ImplicitOps | Priv, em_rdmsr, rdmsr), DIP(ImplicitOps | Priv, rdpmc, check_rdpmc), I(ImplicitOps | VendorSpecific, em_sysenter), I(ImplicitOps | Priv | VendorSpecific, em_sysexit), @@ -3818,7 +3842,6 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) { struct x86_emulate_ops *ops = ctxt->ops; - u64 msr_data; int rc = X86EMUL_CONTINUE; int saved_dst_type = ctxt->dst.type; @@ -4108,29 +4131,6 @@ twobyte_insn: case 0x21: /* mov from dr to reg */ ops->get_dr(ctxt, ctxt->modrm_reg, &ctxt->dst.val); break; - case 0x30: - /* wrmsr */ - msr_data = (u32)ctxt->regs[VCPU_REGS_RAX] - | ((u64)ctxt->regs[VCPU_REGS_RDX] << 32); - if (ops->set_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], msr_data)) { - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - rc = X86EMUL_CONTINUE; - break; - case 0x32: - /* rdmsr */ - if (ops->get_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], &msr_data)) { - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } else { - ctxt->regs[VCPU_REGS_RAX] = (u32)msr_data; - ctxt->regs[VCPU_REGS_RDX] = msr_data >> 32; - } - rc = X86EMUL_CONTINUE; - break; case 0x40 ... 0x4f: /* cmov */ ctxt->dst.val = ctxt->dst.orig_val = ctxt->src.val; if (!test_cc(ctxt->b, ctxt->eflags)) -- cgit v1.2.3 From e940b5c20f89282fe826c5e2237932ab280497cf Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 22 Nov 2011 15:20:47 +0900 Subject: KVM: x86 emulator: Use opcode::execute for CMPXCHG CMPXCHG: 0F B0, 0F B1 Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 906c5eb34aa7..799000d8bf8b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1832,6 +1832,24 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) return rc; } +static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) +{ + /* Save real source value, then compare EAX against destination. */ + ctxt->src.orig_val = ctxt->src.val; + ctxt->src.val = ctxt->regs[VCPU_REGS_RAX]; + emulate_2op_SrcV(ctxt, "cmp"); + + if (ctxt->eflags & EFLG_ZF) { + /* Success: write back to memory. */ + ctxt->dst.val = ctxt->src.orig_val; + } else { + /* Failure: write the value we saw to EAX. */ + ctxt->dst.type = OP_REG; + ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX]; + } + return X86EMUL_CONTINUE; +} + static int em_lseg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; @@ -3400,7 +3418,7 @@ static struct opcode twobyte_table[256] = { D(DstMem | SrcReg | Src2CL | ModRM), D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ - D2bv(DstMem | SrcReg | ModRM | Lock | PageTable), + I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg), I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), @@ -4153,23 +4171,6 @@ twobyte_insn: break; case 0xae: /* clflush */ break; - case 0xb0 ... 0xb1: /* cmpxchg */ - /* - * Save real source value, then compare EAX against - * destination. - */ - ctxt->src.orig_val = ctxt->src.val; - ctxt->src.val = ctxt->regs[VCPU_REGS_RAX]; - emulate_2op_SrcV(ctxt, "cmp"); - if (ctxt->eflags & EFLG_ZF) { - /* Success: write back to memory. */ - ctxt->dst.val = ctxt->src.orig_val; - } else { - /* Failure: write the value we saw to EAX. */ - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX]; - } - break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val -- cgit v1.2.3 From ff227392cd7b858b2b04732e02697122fd1b35b0 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 22 Nov 2011 15:21:33 +0900 Subject: KVM: x86 emulator: Use opcode::execute for BSF/BSR BSF: 0F BC BSR: 0F BD Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 60 +++++++++++++++++++++++++++++--------------------- 1 file changed, 35 insertions(+), 25 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 799000d8bf8b..4cd3313b4131 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2921,6 +2921,40 @@ static int em_btc(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_bsf(struct x86_emulate_ctxt *ctxt) +{ + u8 zf; + + __asm__ ("bsf %2, %0; setz %1" + : "=r"(ctxt->dst.val), "=q"(zf) + : "r"(ctxt->src.val)); + + ctxt->eflags &= ~X86_EFLAGS_ZF; + if (zf) { + ctxt->eflags |= X86_EFLAGS_ZF; + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + } + return X86EMUL_CONTINUE; +} + +static int em_bsr(struct x86_emulate_ctxt *ctxt) +{ + u8 zf; + + __asm__ ("bsr %2, %0; setz %1" + : "=r"(ctxt->dst.val), "=q"(zf) + : "r"(ctxt->src.val)); + + ctxt->eflags &= ~X86_EFLAGS_ZF; + if (zf) { + ctxt->eflags |= X86_EFLAGS_ZF; + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + } + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -3428,7 +3462,7 @@ static struct opcode twobyte_table[256] = { N, N, G(BitOp, group8), I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), - D(DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM), + I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xCF */ D2bv(DstMem | SrcReg | ModRM | Lock), @@ -4176,30 +4210,6 @@ twobyte_insn: ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val : (u16) ctxt->src.val; break; - case 0xbc: { /* bsf */ - u8 zf; - __asm__ ("bsf %2, %0; setz %1" - : "=r"(ctxt->dst.val), "=q"(zf) - : "r"(ctxt->src.val)); - ctxt->eflags &= ~X86_EFLAGS_ZF; - if (zf) { - ctxt->eflags |= X86_EFLAGS_ZF; - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - } - break; - } - case 0xbd: { /* bsr */ - u8 zf; - __asm__ ("bsr %2, %0; setz %1" - : "=r"(ctxt->dst.val), "=q"(zf) - : "r"(ctxt->src.val)); - ctxt->eflags &= ~X86_EFLAGS_ZF; - if (zf) { - ctxt->eflags |= X86_EFLAGS_ZF; - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - } - break; - } case 0xbe ... 0xbf: /* movsx */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->d & ByteOp) ? (s8) ctxt->src.val : -- cgit v1.2.3 From 93a5cef07d686a0341d056b0f930a762c7174a13 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 24 Nov 2011 17:37:48 +0800 Subject: KVM: introduce KVM_MEM_SLOTS_NUM macro Introduce KVM_MEM_SLOTS_NUM macro to instead of KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 4 +++- arch/x86/kvm/mmu.c | 2 +- include/linux/kvm_host.h | 7 +++++-- virt/kvm/kvm_main.c | 2 +- 4 files changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 69b652547489..1769f3dde611 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -31,6 +31,8 @@ #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 +#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) + #define KVM_MMIO_SIZE 16 #define KVM_PIO_PAGE_OFFSET 1 @@ -228,7 +230,7 @@ struct kvm_mmu_page { * One bit set per slot which has memory * in this shadow page. */ - DECLARE_BITMAP(slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); + DECLARE_BITMAP(slot_bitmap, KVM_MEM_SLOTS_NUM); bool unsync; int root_count; /* Currently serving as active root */ unsigned int unsync_children; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index aecdea265f7e..715dcb4fb798 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1349,7 +1349,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, PAGE_SIZE); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); + bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM); sp->parent_ptes = 0; mmu_page_add_parent_pte(vcpu, sp, parent_pte); kvm_mod_used_mmu_pages(vcpu->kvm, +1); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7c654aa46b6c..924df0d7ac5f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -227,11 +227,14 @@ struct kvm_irq_routing_table {}; #endif +#ifndef KVM_MEM_SLOTS_NUM +#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) +#endif + struct kvm_memslots { int nmemslots; u64 generation; - struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS + - KVM_PRIVATE_MEM_SLOTS]; + struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM]; }; struct kvm { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index af5c988cafcc..9ad94c9996e7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -663,7 +663,7 @@ int __kvm_set_memory_region(struct kvm *kvm, (void __user *)(unsigned long)mem->userspace_addr, mem->memory_size))) goto out; - if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) + if (mem->slot >= KVM_MEM_SLOTS_NUM) goto out; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; -- cgit v1.2.3 From be593d6286075801bba6d60fa466a39c24cc7616 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 24 Nov 2011 17:38:24 +0800 Subject: KVM: introduce update_memslots function Introduce update_memslots to update slot which will be update to kvm->memslots Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 22 +++++++++++++++------- 3 files changed, 17 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index af546b768ffd..917a287d21c8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3546,7 +3546,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, memslot = &slots->memslots[log->slot]; memslot->dirty_bitmap = dirty_bitmap; memslot->nr_dirty_pages = 0; - slots->generation++; + update_memslots(slots, NULL); old_slots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 924df0d7ac5f..23f795c66220 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -320,6 +320,7 @@ 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); 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 9ad94c9996e7..b5ed7770ced3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -630,6 +630,19 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) } #endif /* !CONFIG_S390 */ +void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) +{ + if (new) { + int id = new->id; + + slots->memslots[id] = *new; + if (id >= slots->nmemslots) + slots->nmemslots = id + 1; + } + + slots->generation++; +} + /* * Allocate some memory and give it an address in the guest physical address * space. @@ -780,10 +793,8 @@ skip_lpage: GFP_KERNEL); if (!slots) goto out_free; - if (mem->slot >= slots->nmemslots) - slots->nmemslots = mem->slot + 1; - slots->generation++; slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID; + update_memslots(slots, NULL); old_memslots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); @@ -815,9 +826,6 @@ skip_lpage: GFP_KERNEL); if (!slots) goto out_free; - if (mem->slot >= slots->nmemslots) - slots->nmemslots = mem->slot + 1; - slots->generation++; /* actual memory is freed via old in kvm_free_physmem_slot below */ if (!npages) { @@ -827,7 +835,7 @@ skip_lpage: new.lpage_info[i] = NULL; } - slots->memslots[mem->slot] = new; + update_memslots(slots, &new); old_memslots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); -- cgit v1.2.3 From be6ba0f0962a39091c52eb9167ddea201fe80716 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 24 Nov 2011 17:39:18 +0800 Subject: KVM: introduce kvm_for_each_memslot macro Introduce kvm_for_each_memslot to walk all valid memslot Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 6 ++---- arch/x86/kvm/mmu.c | 12 ++++++------ include/linux/kvm_host.h | 4 ++++ virt/kvm/iommu.c | 17 +++++++++-------- virt/kvm/kvm_main.c | 14 ++++++-------- 5 files changed, 27 insertions(+), 26 deletions(-) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 43f4c92816ef..42ad1f9c9f01 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1366,14 +1366,12 @@ static void kvm_release_vm_pages(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int i, j; + int j; unsigned long base_gfn; slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) { - memslot = &slots->memslots[i]; + kvm_for_each_memslot(memslot, slots) { base_gfn = memslot->base_gfn; - for (j = 0; j < memslot->npages; j++) { if (memslot->rmap[j]) put_page((struct page *)memslot->rmap[j]); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 715dcb4fb798..d737443cdfdb 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1128,15 +1128,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, int (*handler)(struct kvm *kvm, unsigned long *rmapp, unsigned long data)) { - int i, j; + int j; int ret; int retval = 0; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) { - struct kvm_memory_slot *memslot = &slots->memslots[i]; + kvm_for_each_memslot(memslot, slots) { unsigned long start = memslot->userspace_addr; unsigned long end; @@ -3985,15 +3985,15 @@ nomem: */ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) { - int i; unsigned int nr_mmu_pages; unsigned int nr_pages = 0; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) - nr_pages += slots->memslots[i].npages; + kvm_for_each_memslot(memslot, slots) + nr_pages += memslot->npages; nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; nr_mmu_pages = max(nr_mmu_pages, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 23f795c66220..392af47a4353 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -308,6 +308,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ idx++) +#define kvm_for_each_memslot(memslot, slots) \ + for (memslot = &slots->memslots[0]; \ + memslot < slots->memslots + (slots)->nmemslots; memslot++) + int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index a195c07fa829..4e5f7b7f1d2b 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -134,14 +134,15 @@ unmap_pages: static int kvm_iommu_map_memslots(struct kvm *kvm) { - int i, idx, r = 0; + int idx, r = 0; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) { - r = kvm_iommu_map_pages(kvm, &slots->memslots[i]); + kvm_for_each_memslot(memslot, slots) { + r = kvm_iommu_map_pages(kvm, memslot); if (r) break; } @@ -311,16 +312,16 @@ static void kvm_iommu_put_pages(struct kvm *kvm, static int kvm_iommu_unmap_memslots(struct kvm *kvm) { - int i, idx; + int idx; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) { - kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn, - slots->memslots[i].npages); - } + kvm_for_each_memslot(memslot, slots) + kvm_iommu_put_pages(kvm, memslot->base_gfn, memslot->npages); + srcu_read_unlock(&kvm->srcu, idx); return 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b5ed7770ced3..4c2900c5d81d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -547,11 +547,11 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free, void kvm_free_physmem(struct kvm *kvm) { - int i; struct kvm_memslots *slots = kvm->memslots; + struct kvm_memory_slot *memslot; - for (i = 0; i < slots->nmemslots; ++i) - kvm_free_physmem_slot(&slots->memslots[i], NULL); + kvm_for_each_memslot(memslot, slots) + kvm_free_physmem_slot(memslot, NULL); kfree(kvm->memslots); } @@ -975,15 +975,13 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva); static struct kvm_memory_slot *__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { - int i; - - for (i = 0; i < slots->nmemslots; ++i) { - struct kvm_memory_slot *memslot = &slots->memslots[i]; + struct kvm_memory_slot *memslot; + kvm_for_each_memslot(memslot, slots) if (gfn >= memslot->base_gfn && gfn < memslot->base_gfn + memslot->npages) return memslot; - } + return NULL; } -- cgit v1.2.3 From 28a37544fb0223eb9805d2567b88f7360edec52a Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 24 Nov 2011 19:04:35 +0800 Subject: KVM: introduce id_to_memslot function Introduce id_to_memslot to get memslot by slot id Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 2 +- arch/powerpc/kvm/book3s.c | 2 +- arch/x86/kvm/vmx.c | 6 ++++-- arch/x86/kvm/x86.c | 18 +++++++++--------- include/linux/kvm_host.h | 6 ++++++ virt/kvm/kvm_main.c | 13 +++++++++---- 6 files changed, 30 insertions(+), 17 deletions(-) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 42ad1f9c9f01..92d9f1e4740f 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1818,7 +1818,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_MEMORY_SLOTS) goto out; - memslot = &kvm->memslots->memslots[log->slot]; + memslot = id_to_memslot(kvm->memslots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index a459479995c6..e41ac6f7dcf1 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -498,7 +498,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { - memslot = &kvm->memslots->memslots[log->slot]; + memslot = id_to_memslot(kvm->memslots, log->slot); ga = memslot->base_gfn << PAGE_SHIFT; ga_end = ga + (memslot->npages << PAGE_SHIFT); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ba24022f4575..8f19d91ec3e7 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2711,11 +2711,13 @@ static gva_t rmode_tss_base(struct kvm *kvm) { if (!kvm->arch.tss_addr) { struct kvm_memslots *slots; + struct kvm_memory_slot *slot; gfn_t base_gfn; slots = kvm_memslots(kvm); - base_gfn = slots->memslots[0].base_gfn + - kvm->memslots->memslots[0].npages - 3; + slot = id_to_memslot(slots, 0); + base_gfn = slot->base_gfn + slot->npages - 3; + return base_gfn << PAGE_SHIFT; } return kvm->arch.tss_addr; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 917a287d21c8..b6776c613e6d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3520,7 +3520,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_MEMORY_SLOTS) goto out; - memslot = &kvm->memslots->memslots[log->slot]; + memslot = id_to_memslot(kvm->memslots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; @@ -3531,27 +3531,27 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, /* If nothing is dirty, don't bother messing with page tables. */ if (nr_dirty_pages) { struct kvm_memslots *slots, *old_slots; - unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap, *dirty_bitmap_head; - dirty_bitmap = memslot->dirty_bitmap_head; - if (memslot->dirty_bitmap == dirty_bitmap) - dirty_bitmap += n / sizeof(long); - memset(dirty_bitmap, 0, n); + dirty_bitmap = memslot->dirty_bitmap; + dirty_bitmap_head = memslot->dirty_bitmap_head; + if (dirty_bitmap == dirty_bitmap_head) + dirty_bitmap_head += n / sizeof(long); + memset(dirty_bitmap_head, 0, n); r = -ENOMEM; slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!slots) goto out; memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); - memslot = &slots->memslots[log->slot]; - memslot->dirty_bitmap = dirty_bitmap; + memslot = id_to_memslot(slots, log->slot); memslot->nr_dirty_pages = 0; + memslot->dirty_bitmap = dirty_bitmap_head; update_memslots(slots, NULL); old_slots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); - dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap; kfree(old_slots); write_protect_slot(kvm, memslot, dirty_bitmap, nr_dirty_pages); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 392af47a4353..123925cd3ae8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -333,6 +333,12 @@ static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) || lockdep_is_held(&kvm->slots_lock)); } +static inline struct kvm_memory_slot * +id_to_memslot(struct kvm_memslots *slots, int id) +{ + return &slots->memslots[id]; +} + #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4c2900c5d81d..7b6084999424 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -634,8 +634,9 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) { if (new) { int id = new->id; + struct kvm_memory_slot *old = id_to_memslot(slots, id); - slots->memslots[id] = *new; + *old = *new; if (id >= slots->nmemslots) slots->nmemslots = id + 1; } @@ -681,7 +682,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; - memslot = &kvm->memslots->memslots[mem->slot]; + memslot = id_to_memslot(kvm->memslots, mem->slot); base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; @@ -788,12 +789,16 @@ skip_lpage: #endif /* not defined CONFIG_S390 */ if (!npages) { + struct kvm_memory_slot *slot; + r = -ENOMEM; slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), GFP_KERNEL); if (!slots) goto out_free; - slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID; + slot = id_to_memslot(slots, mem->slot); + slot->flags |= KVM_MEMSLOT_INVALID; + update_memslots(slots, NULL); old_memslots = kvm->memslots; @@ -897,7 +902,7 @@ int kvm_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_MEMORY_SLOTS) goto out; - memslot = &kvm->memslots->memslots[log->slot]; + memslot = id_to_memslot(kvm->memslots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; -- cgit v1.2.3 From bf3e05bc1e2781d5d8d3ddb2d8bf2d6ec207e5cb Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 24 Nov 2011 17:40:57 +0800 Subject: KVM: sort memslots by its size and use line search Sort memslots base on its size and use line search to find it, so that the larger memslots have better fit The idea is from Avi Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 18 +++++++++-- virt/kvm/kvm_main.c | 79 ++++++++++++++++++++++++++++++++++-------------- 2 files changed, 72 insertions(+), 25 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 123925cd3ae8..9efdf5c703a5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -231,8 +231,12 @@ struct kvm_irq_routing_table {}; #define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) #endif +/* + * Note: + * memslots are not sorted by id anymore, please use id_to_memslot() + * to get the memslot by its id. + */ struct kvm_memslots { - int nmemslots; u64 generation; struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM]; }; @@ -310,7 +314,8 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + (slots)->nmemslots; memslot++) + memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ + memslot++) int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); @@ -336,7 +341,14 @@ static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) static inline struct kvm_memory_slot * id_to_memslot(struct kvm_memslots *slots, int id) { - return &slots->memslots[id]; + int i; + + for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) + if (slots->memslots[i].id == id) + return &slots->memslots[i]; + + WARN_ON(1); + return NULL; } #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7b6084999424..6e8eb15dd30b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -440,6 +440,15 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ +static void kvm_init_memslots_id(struct kvm *kvm) +{ + int i; + struct kvm_memslots *slots = kvm->memslots; + + for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) + slots->memslots[i].id = i; +} + static struct kvm *kvm_create_vm(void) { int r, i; @@ -465,6 +474,7 @@ static struct kvm *kvm_create_vm(void) kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!kvm->memslots) goto out_err_nosrcu; + kvm_init_memslots_id(kvm); if (init_srcu_struct(&kvm->srcu)) goto out_err_nosrcu; for (i = 0; i < KVM_NR_BUSES; i++) { @@ -630,15 +640,54 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) } #endif /* !CONFIG_S390 */ +static struct kvm_memory_slot * +search_memslots(struct kvm_memslots *slots, gfn_t gfn) +{ + struct kvm_memory_slot *memslot; + + kvm_for_each_memslot(memslot, slots) + if (gfn >= memslot->base_gfn && + gfn < memslot->base_gfn + memslot->npages) + return memslot; + + return NULL; +} + +static int cmp_memslot(const void *slot1, const void *slot2) +{ + struct kvm_memory_slot *s1, *s2; + + s1 = (struct kvm_memory_slot *)slot1; + s2 = (struct kvm_memory_slot *)slot2; + + if (s1->npages < s2->npages) + return 1; + if (s1->npages > s2->npages) + return -1; + + return 0; +} + +/* + * Sort the memslots base on its size, so the larger slots + * will get better fit. + */ +static void sort_memslots(struct kvm_memslots *slots) +{ + sort(slots->memslots, KVM_MEM_SLOTS_NUM, + sizeof(struct kvm_memory_slot), cmp_memslot, NULL); +} + void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) { if (new) { int id = new->id; struct kvm_memory_slot *old = id_to_memslot(slots, id); + unsigned long npages = old->npages; *old = *new; - if (id >= slots->nmemslots) - slots->nmemslots = id + 1; + if (new->npages != npages) + sort_memslots(slots); } slots->generation++; @@ -980,14 +1029,7 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva); static struct kvm_memory_slot *__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { - struct kvm_memory_slot *memslot; - - kvm_for_each_memslot(memslot, slots) - if (gfn >= memslot->base_gfn - && gfn < memslot->base_gfn + memslot->npages) - return memslot; - - return NULL; + return search_memslots(slots, gfn); } struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) @@ -998,20 +1040,13 @@ EXPORT_SYMBOL_GPL(gfn_to_memslot); int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { - int i; - struct kvm_memslots *slots = kvm_memslots(kvm); - - for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *memslot = &slots->memslots[i]; + struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); - if (memslot->flags & KVM_MEMSLOT_INVALID) - continue; + if (!memslot || memslot->id >= KVM_MEMORY_SLOTS || + memslot->flags & KVM_MEMSLOT_INVALID) + return 0; - if (gfn >= memslot->base_gfn - && gfn < memslot->base_gfn + memslot->npages) - return 1; - } - return 0; + return 1; } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); -- cgit v1.2.3 From f85e2cb5dbaf905e9470d3fe099b31619da431fc Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 24 Nov 2011 17:41:54 +0800 Subject: KVM: introduce a table to map slot id to index in memslots array The operation of getting dirty log is frequent when framebuffer-based displays are used(for example, Xwindow), so, we introduce a mapping table to speed up id_to_memslot() Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 13 +++++++------ virt/kvm/kvm_main.c | 7 ++++++- 2 files changed, 13 insertions(+), 7 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9efdf5c703a5..8c5c30361b0d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -239,6 +239,8 @@ struct kvm_irq_routing_table {}; 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]; }; struct kvm { @@ -341,14 +343,13 @@ static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) static inline struct kvm_memory_slot * id_to_memslot(struct kvm_memslots *slots, int id) { - int i; + int index = slots->id_to_index[id]; + struct kvm_memory_slot *slot; - for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - if (slots->memslots[i].id == id) - return &slots->memslots[i]; + slot = &slots->memslots[index]; - WARN_ON(1); - return NULL; + WARN_ON(slot->id != id); + return slot; } #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6e8eb15dd30b..e289486edc6d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -446,7 +446,7 @@ static void kvm_init_memslots_id(struct kvm *kvm) struct kvm_memslots *slots = kvm->memslots; for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->memslots[i].id = i; + slots->id_to_index[i] = slots->memslots[i].id = i; } static struct kvm *kvm_create_vm(void) @@ -674,8 +674,13 @@ static int cmp_memslot(const void *slot1, const void *slot2) */ static void sort_memslots(struct kvm_memslots *slots) { + int i; + sort(slots->memslots, KVM_MEM_SLOTS_NUM, sizeof(struct kvm_memory_slot), cmp_memslot, NULL); + + for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) + slots->id_to_index[slots->memslots[i].id] = i; } void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new) -- cgit v1.2.3 From 60f9a9ef5492cae66aca2ad9873360161320d5af Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Thu, 24 Nov 2011 18:09:11 +0800 Subject: KVM: IA64: fix struct redefinition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is the same struct definition in ia64 and kvm common code: arch/ia64/kvm//kvm-ia64.c: At top level: arch/ia64/kvm//kvm-ia64.c:777:8: error: redefinition of ‘struct kvm_io_range’ include/linux/kvm_host.h:62:8: note: originally defined here So, rename kvm_io_range to kvm_ia64_io_range in ia64 code Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 92d9f1e4740f..405052002493 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -774,13 +774,13 @@ struct kvm *kvm_arch_alloc_vm(void) return kvm; } -struct kvm_io_range { +struct kvm_ia64_io_range { unsigned long start; unsigned long size; unsigned long type; }; -static const struct kvm_io_range io_ranges[] = { +static const struct kvm_ia64_io_range io_ranges[] = { {VGA_IO_START, VGA_IO_SIZE, GPFN_FRAME_BUFFER}, {MMIO_START, MMIO_SIZE, GPFN_LOW_MMIO}, {LEGACY_IO_START, LEGACY_IO_SIZE, GPFN_LEGACY_IO}, -- cgit v1.2.3 From d77fe6354d5b67f4d4eb62a47621da2b3ee3539e Mon Sep 17 00:00:00 2001 From: Julian Stecklina Date: Wed, 23 Nov 2011 13:54:30 +0100 Subject: KVM: Allow aligned byte and word writes to IOAPIC registers. This fixes byte accesses to IOAPIC_REG_SELECT as mandated by at least the ICH10 and Intel Series 5 chipset specs. It also makes ioapic_mmio_write consistent with ioapic_mmio_read, which also allows byte and word accesses. Signed-off-by: Julian Stecklina Signed-off-by: Avi Kivity --- virt/kvm/ioapic.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 3eed61eb4867..71e2253edee7 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -332,9 +332,18 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, (void*)addr, len, val); ASSERT(!(addr & 0xf)); /* check alignment */ - if (len == 4 || len == 8) + switch (len) { + case 8: + case 4: data = *(u32 *) val; - else { + break; + case 2: + data = *(u16 *) val; + break; + case 1: + data = *(u8 *) val; + break; + default: printk(KERN_WARNING "ioapic: Unsupported size %d\n", len); return 0; } @@ -343,7 +352,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, spin_lock(&ioapic->lock); switch (addr) { case IOAPIC_REG_SELECT: - ioapic->ioregsel = data; + ioapic->ioregsel = data & 0xFF; /* 8-bit register */ break; case IOAPIC_REG_WINDOW: -- cgit v1.2.3 From 2b5e97e1fadf1ade87558f2a2003616879f9e228 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 23 Nov 2011 12:27:39 +0900 Subject: KVM: x86 emulator: Use opcode::execute for INS/OUTS from/to port in DX INSB : 6C INSW/INSD : 6D OUTSB : 6E OUTSW/OUTSD: 6F The I/O port address is read from the DX register when we decode the operand because we see the SrcDX/DstDX flag is set. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4cd3313b4131..ac8e5ed78834 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3321,8 +3321,8 @@ static struct opcode opcode_table[256] = { I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op), I(SrcImmByte | Mov | Stack, em_push), I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op), - D2bvIP(DstDI | SrcDX | Mov | String, ins, check_perm_in), /* insb, insw/insd */ - D2bvIP(SrcSI | DstDX | String, outs, check_perm_out), /* outsb, outsw/outsd */ + I2bvIP(DstDI | SrcDX | Mov | String, em_in, ins, check_perm_in), /* insb, insw/insd */ + I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */ /* 0x70 - 0x7F */ X16(D(SrcImmByte)), /* 0x80 - 0x87 */ @@ -4027,16 +4027,6 @@ special_insn: goto cannot_emulate; ctxt->dst.val = (s32) ctxt->src.val; break; - case 0x6c: /* insb */ - case 0x6d: /* insw/insd */ - ctxt->src.val = ctxt->regs[VCPU_REGS_RDX]; - rc = em_in(ctxt); - break; - case 0x6e: /* outsb */ - case 0x6f: /* outsw/outsd */ - ctxt->dst.val = ctxt->regs[VCPU_REGS_RDX]; - rc = em_out(ctxt); - break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) jmp_rel(ctxt, ctxt->src.val); -- cgit v1.2.3 From 00b27a3efb116062ca5a276ad5cb01ea1b80b5f6 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 23 Nov 2011 16:30:32 +0200 Subject: KVM: Move cpuid code to new file The cpuid code has grown; put it into a separate file. Signed-off-by: Avi Kivity --- arch/x86/kvm/Makefile | 2 +- arch/x86/kvm/cpuid.c | 625 +++++++++++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/cpuid.h | 46 ++++ arch/x86/kvm/lapic.c | 1 + arch/x86/kvm/vmx.c | 1 + arch/x86/kvm/x86.c | 634 +------------------------------------------------- arch/x86/kvm/x86.h | 5 +- 7 files changed, 679 insertions(+), 635 deletions(-) create mode 100644 arch/x86/kvm/cpuid.c create mode 100644 arch/x86/kvm/cpuid.h diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index f15501f431c8..161b76ae87c4 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o timer.o + i8254.o timer.o cpuid.o kvm-intel-y += vmx.o kvm-amd-y += svm.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c new file mode 100644 index 000000000000..0a332ec5203c --- /dev/null +++ b/arch/x86/kvm/cpuid.c @@ -0,0 +1,625 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * cpuid support routines + * + * derived from arch/x86/kvm/x86.c + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * Copyright IBM Corporation, 2008 + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include +#include +#include +#include +#include "cpuid.h" +#include "lapic.h" +#include "mmu.h" +#include "trace.h" + +void kvm_update_cpuid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + struct kvm_lapic *apic = vcpu->arch.apic; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + if (!best) + return; + + /* Update OSXSAVE bit */ + if (cpu_has_xsave && best->function == 0x1) { + best->ecx &= ~(bit(X86_FEATURE_OSXSAVE)); + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) + best->ecx |= bit(X86_FEATURE_OSXSAVE); + } + + if (apic) { + if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER)) + apic->lapic_timer.timer_mode_mask = 3 << 17; + else + apic->lapic_timer.timer_mode_mask = 1 << 17; + } +} + +static int is_efer_nx(void) +{ + unsigned long long efer = 0; + + rdmsrl_safe(MSR_EFER, &efer); + return efer & EFER_NX; +} + +static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_cpuid_entry2 *e, *entry; + + entry = NULL; + for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + e = &vcpu->arch.cpuid_entries[i]; + if (e->function == 0x80000001) { + entry = e; + break; + } + } + if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) { + entry->edx &= ~(1 << 20); + printk(KERN_INFO "kvm: guest NX capability removed\n"); + } +} + +/* when an old userspace process fills a new kernel module */ +int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid *cpuid, + struct kvm_cpuid_entry __user *entries) +{ + int r, i; + struct kvm_cpuid_entry *cpuid_entries; + + r = -E2BIG; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + goto out; + r = -ENOMEM; + cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent); + if (!cpuid_entries) + goto out; + r = -EFAULT; + if (copy_from_user(cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry))) + goto out_free; + for (i = 0; i < cpuid->nent; i++) { + vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; + vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; + vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx; + vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx; + vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx; + vcpu->arch.cpuid_entries[i].index = 0; + vcpu->arch.cpuid_entries[i].flags = 0; + vcpu->arch.cpuid_entries[i].padding[0] = 0; + vcpu->arch.cpuid_entries[i].padding[1] = 0; + vcpu->arch.cpuid_entries[i].padding[2] = 0; + } + vcpu->arch.cpuid_nent = cpuid->nent; + cpuid_fix_nx_cap(vcpu); + r = 0; + kvm_apic_set_version(vcpu); + kvm_x86_ops->cpuid_update(vcpu); + kvm_update_cpuid(vcpu); + +out_free: + vfree(cpuid_entries); +out: + return r; +} + +int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + int r; + + r = -E2BIG; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + goto out; + r = -EFAULT; + if (copy_from_user(&vcpu->arch.cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry2))) + goto out; + vcpu->arch.cpuid_nent = cpuid->nent; + kvm_apic_set_version(vcpu); + kvm_x86_ops->cpuid_update(vcpu); + kvm_update_cpuid(vcpu); + return 0; + +out: + return r; +} + +int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + int r; + + r = -E2BIG; + if (cpuid->nent < vcpu->arch.cpuid_nent) + goto out; + r = -EFAULT; + if (copy_to_user(entries, &vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) + goto out; + return 0; + +out: + cpuid->nent = vcpu->arch.cpuid_nent; + return r; +} + +static void cpuid_mask(u32 *word, int wordnum) +{ + *word &= boot_cpu_data.x86_capability[wordnum]; +} + +static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index) +{ + entry->function = function; + entry->index = index; + cpuid_count(entry->function, entry->index, + &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); + entry->flags = 0; +} + +static bool supported_xcr0_bit(unsigned bit) +{ + u64 mask = ((u64)1 << bit); + + return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0; +} + +#define F(x) bit(X86_FEATURE_##x) + +static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index, int *nent, int maxnent) +{ + unsigned f_nx = is_efer_nx() ? F(NX) : 0; +#ifdef CONFIG_X86_64 + unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL) + ? F(GBPAGES) : 0; + unsigned f_lm = F(LM); +#else + unsigned f_gbpages = 0; + unsigned f_lm = 0; +#endif + unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; + + /* cpuid 1.edx */ + const u32 kvm_supported_word0_x86_features = + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) | + 0 /* Reserved, DS, ACPI */ | F(MMX) | + F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | + 0 /* HTT, TM, Reserved, PBE */; + /* cpuid 0x80000001.edx */ + const u32 kvm_supported_word1_x86_features = + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* Reserved */ | + f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp | + 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); + /* cpuid 1.ecx */ + const u32 kvm_supported_word4_x86_features = + F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | + 0 /* DS-CPL, VMX, SMX, EST */ | + 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | + 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ | + 0 /* Reserved, DCA */ | F(XMM4_1) | + F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | + 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | + F(F16C) | F(RDRAND); + /* cpuid 0x80000001.ecx */ + const u32 kvm_supported_word6_x86_features = + F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | + F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | + F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + + /* cpuid 0xC0000001.edx */ + const u32 kvm_supported_word5_x86_features = + F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | + F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | + F(PMM) | F(PMM_EN); + + /* cpuid 7.0.ebx */ + const u32 kvm_supported_word9_x86_features = + F(SMEP) | F(FSGSBASE) | F(ERMS); + + /* all calls to cpuid_count() should be made on the same cpu */ + get_cpu(); + do_cpuid_1_ent(entry, function, index); + ++*nent; + + switch (function) { + case 0: + entry->eax = min(entry->eax, (u32)0xd); + break; + case 1: + entry->edx &= kvm_supported_word0_x86_features; + cpuid_mask(&entry->edx, 0); + entry->ecx &= kvm_supported_word4_x86_features; + cpuid_mask(&entry->ecx, 4); + /* we support x2apic emulation even if host does not support + * it since we emulate x2apic in software */ + entry->ecx |= F(X2APIC); + break; + /* function 2 entries are STATEFUL. That is, repeated cpuid commands + * may return different values. This forces us to get_cpu() before + * issuing the first command, and also to emulate this annoying behavior + * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ + case 2: { + int t, times = entry->eax & 0xff; + + entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + for (t = 1; t < times && *nent < maxnent; ++t) { + do_cpuid_1_ent(&entry[t], function, 0); + entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + ++*nent; + } + break; + } + /* function 4 has additional index. */ + case 4: { + int i, cache_type; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* read more entries until cache_type is zero */ + for (i = 1; *nent < maxnent; ++i) { + cache_type = entry[i - 1].eax & 0x1f; + if (!cache_type) + break; + do_cpuid_1_ent(&entry[i], function, i); + entry[i].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + } + break; + } + case 7: { + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* Mask ebx against host capbability word 9 */ + if (index == 0) { + entry->ebx &= kvm_supported_word9_x86_features; + cpuid_mask(&entry->ebx, 9); + } else + entry->ebx = 0; + entry->eax = 0; + entry->ecx = 0; + entry->edx = 0; + break; + } + case 9: + break; + /* function 0xb has additional index. */ + case 0xb: { + int i, level_type; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* read more entries until level_type is zero */ + for (i = 1; *nent < maxnent; ++i) { + level_type = entry[i - 1].ecx & 0xff00; + if (!level_type) + break; + do_cpuid_1_ent(&entry[i], function, i); + entry[i].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + } + break; + } + case 0xd: { + int idx, i; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + for (idx = 1, i = 1; *nent < maxnent && idx < 64; ++idx) { + do_cpuid_1_ent(&entry[i], function, idx); + if (entry[i].eax == 0 || !supported_xcr0_bit(idx)) + continue; + entry[i].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + ++i; + } + break; + } + case KVM_CPUID_SIGNATURE: { + char signature[12] = "KVMKVMKVM\0\0"; + u32 *sigptr = (u32 *)signature; + entry->eax = 0; + entry->ebx = sigptr[0]; + entry->ecx = sigptr[1]; + entry->edx = sigptr[2]; + break; + } + case KVM_CPUID_FEATURES: + entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | + (1 << KVM_FEATURE_NOP_IO_DELAY) | + (1 << KVM_FEATURE_CLOCKSOURCE2) | + (1 << KVM_FEATURE_ASYNC_PF) | + (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); + + if (sched_info_on()) + entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); + + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; + case 0x80000000: + entry->eax = min(entry->eax, 0x8000001a); + break; + case 0x80000001: + entry->edx &= kvm_supported_word1_x86_features; + cpuid_mask(&entry->edx, 1); + entry->ecx &= kvm_supported_word6_x86_features; + cpuid_mask(&entry->ecx, 6); + break; + case 0x80000008: { + unsigned g_phys_as = (entry->eax >> 16) & 0xff; + unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned phys_as = entry->eax & 0xff; + + if (!g_phys_as) + g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); + entry->ebx = entry->edx = 0; + break; + } + case 0x80000019: + entry->ecx = entry->edx = 0; + break; + case 0x8000001a: + break; + case 0x8000001d: + break; + /*Add support for Centaur's CPUID instruction*/ + case 0xC0000000: + /*Just support up to 0xC0000004 now*/ + entry->eax = min(entry->eax, 0xC0000004); + break; + case 0xC0000001: + entry->edx &= kvm_supported_word5_x86_features; + cpuid_mask(&entry->edx, 5); + break; + case 3: /* Processor serial number */ + case 5: /* MONITOR/MWAIT */ + case 6: /* Thermal management */ + case 0xA: /* Architectural Performance Monitoring */ + case 0x80000007: /* Advanced power management */ + case 0xC0000002: + case 0xC0000003: + case 0xC0000004: + default: + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + + kvm_x86_ops->set_supported_cpuid(function, entry); + + put_cpu(); +} + +#undef F + +int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + struct kvm_cpuid_entry2 *cpuid_entries; + int limit, nent = 0, r = -E2BIG; + u32 func; + + if (cpuid->nent < 1) + goto out; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + cpuid->nent = KVM_MAX_CPUID_ENTRIES; + r = -ENOMEM; + cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); + if (!cpuid_entries) + goto out; + + do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent); + limit = cpuid_entries[0].eax; + for (func = 1; func <= limit && nent < cpuid->nent; ++func) + do_cpuid_ent(&cpuid_entries[nent], func, 0, + &nent, cpuid->nent); + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent); + limit = cpuid_entries[nent - 1].eax; + for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) + do_cpuid_ent(&cpuid_entries[nent], func, 0, + &nent, cpuid->nent); + + + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + /* Add support for Centaur's CPUID instruction. */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) { + do_cpuid_ent(&cpuid_entries[nent], 0xC0000000, 0, + &nent, cpuid->nent); + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + limit = cpuid_entries[nent - 1].eax; + for (func = 0xC0000001; + func <= limit && nent < cpuid->nent; ++func) + do_cpuid_ent(&cpuid_entries[nent], func, 0, + &nent, cpuid->nent); + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + } + + do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent, + cpuid->nent); + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent, + cpuid->nent); + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + r = -EFAULT; + if (copy_to_user(entries, cpuid_entries, + nent * sizeof(struct kvm_cpuid_entry2))) + goto out_free; + cpuid->nent = nent; + r = 0; + +out_free: + vfree(cpuid_entries); +out: + return r; +} + +static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) +{ + struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; + int j, nent = vcpu->arch.cpuid_nent; + + e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; + /* when no next entry is found, the current entry[i] is reselected */ + for (j = i + 1; ; j = (j + 1) % nent) { + struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; + if (ej->function == e->function) { + ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + return j; + } + } + return 0; /* silence gcc, even though control never reaches here */ +} + +/* find an entry with matching function, matching index (if needed), and that + * should be read next (if it's stateful) */ +static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, + u32 function, u32 index) +{ + if (e->function != function) + return 0; + if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) + return 0; + if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && + !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) + return 0; + return 1; +} + +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + int i; + struct kvm_cpuid_entry2 *best = NULL; + + for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + struct kvm_cpuid_entry2 *e; + + e = &vcpu->arch.cpuid_entries[i]; + if (is_matching_cpuid_entry(e, function, index)) { + if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) + move_to_next_stateful_cpuid_entry(vcpu, i); + best = e; + break; + } + } + return best; +} +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); + +int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best) + return best->eax & 0xff; +not_found: + return 36; +} + +/* + * If no match is found, check whether we exceed the vCPU's limit + * and return the content of the highest valid _standard_ leaf instead. + * This is to satisfy the CPUID specification. + */ +static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + struct kvm_cpuid_entry2 *maxlevel; + + maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + if (!maxlevel || maxlevel->eax >= function) + return NULL; + if (function & 0x80000000) { + maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); + if (!maxlevel) + return NULL; + } + return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); +} + +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + u32 function, index; + struct kvm_cpuid_entry2 *best; + + function = kvm_register_read(vcpu, VCPU_REGS_RAX); + index = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_register_write(vcpu, VCPU_REGS_RAX, 0); + kvm_register_write(vcpu, VCPU_REGS_RBX, 0); + kvm_register_write(vcpu, VCPU_REGS_RCX, 0); + kvm_register_write(vcpu, VCPU_REGS_RDX, 0); + best = kvm_find_cpuid_entry(vcpu, function, index); + + if (!best) + best = check_cpuid_limit(vcpu, function, index); + + if (best) { + kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); + kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); + kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx); + kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); + } + kvm_x86_ops->skip_emulated_instruction(vcpu); + trace_kvm_cpuid(function, + kvm_register_read(vcpu, VCPU_REGS_RAX), + kvm_register_read(vcpu, VCPU_REGS_RBX), + kvm_register_read(vcpu, VCPU_REGS_RCX), + kvm_register_read(vcpu, VCPU_REGS_RDX)); +} +EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h new file mode 100644 index 000000000000..5b97e1797a6d --- /dev/null +++ b/arch/x86/kvm/cpuid.h @@ -0,0 +1,46 @@ +#ifndef ARCH_X86_KVM_CPUID_H +#define ARCH_X86_KVM_CPUID_H + +#include "x86.h" + +void kvm_update_cpuid(struct kvm_vcpu *vcpu); +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index); +int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); +int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid *cpuid, + struct kvm_cpuid_entry __user *entries); +int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); +int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); + + +static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->ecx & bit(X86_FEATURE_XSAVE)); +} + +static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_SMEP)); +} + +static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); +} + +#endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 54abb40199d6..a7f3e655cd3e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -38,6 +38,7 @@ #include "irq.h" #include "trace.h" #include "x86.h" +#include "cpuid.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8f19d91ec3e7..4ceced2669ef 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -18,6 +18,7 @@ #include "irq.h" #include "mmu.h" +#include "cpuid.h" #include #include diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b6776c613e6d..4e533d24c513 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -26,6 +26,7 @@ #include "tss.h" #include "kvm_cache_regs.h" #include "x86.h" +#include "cpuid.h" #include #include @@ -82,8 +83,6 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU static void update_cr8_intercept(struct kvm_vcpu *vcpu); -static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; @@ -574,54 +573,6 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 1, 0); - return best && (best->ecx & bit(X86_FEATURE_XSAVE)); -} - -static bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->ebx & bit(X86_FEATURE_SMEP)); -} - -static bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); -} - -static void update_cpuid(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - struct kvm_lapic *apic = vcpu->arch.apic; - - best = kvm_find_cpuid_entry(vcpu, 1, 0); - if (!best) - return; - - /* Update OSXSAVE bit */ - if (cpu_has_xsave && best->function == 0x1) { - best->ecx &= ~(bit(X86_FEATURE_OSXSAVE)); - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) - best->ecx |= bit(X86_FEATURE_OSXSAVE); - } - - if (apic) { - if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER)) - apic->lapic_timer.timer_mode_mask = 3 << 17; - else - apic->lapic_timer.timer_mode_mask = 1 << 17; - } -} - int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); @@ -655,7 +606,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_mmu_reset_context(vcpu); if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) - update_cpuid(vcpu); + kvm_update_cpuid(vcpu); return 0; } @@ -2265,466 +2216,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); } -static int is_efer_nx(void) -{ - unsigned long long efer = 0; - - rdmsrl_safe(MSR_EFER, &efer); - return efer & EFER_NX; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_cpuid_entry2 *e, *entry; - - entry = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) { - entry->edx &= ~(1 << 20); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - -/* when an old userspace process fills a new kernel module */ -static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, - struct kvm_cpuid *cpuid, - struct kvm_cpuid_entry __user *entries) -{ - int r, i; - struct kvm_cpuid_entry *cpuid_entries; - - r = -E2BIG; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - goto out; - r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent); - if (!cpuid_entries) - goto out; - r = -EFAULT; - if (copy_from_user(cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry))) - goto out_free; - for (i = 0; i < cpuid->nent; i++) { - vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; - vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; - vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx; - vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx; - vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx; - vcpu->arch.cpuid_entries[i].index = 0; - vcpu->arch.cpuid_entries[i].flags = 0; - vcpu->arch.cpuid_entries[i].padding[0] = 0; - vcpu->arch.cpuid_entries[i].padding[1] = 0; - vcpu->arch.cpuid_entries[i].padding[2] = 0; - } - vcpu->arch.cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); - r = 0; - kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); - update_cpuid(vcpu); - -out_free: - vfree(cpuid_entries); -out: - return r; -} - -static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) -{ - int r; - - r = -E2BIG; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - goto out; - r = -EFAULT; - if (copy_from_user(&vcpu->arch.cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry2))) - goto out; - vcpu->arch.cpuid_nent = cpuid->nent; - kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); - update_cpuid(vcpu); - return 0; - -out: - return r; -} - -static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) -{ - int r; - - r = -E2BIG; - if (cpuid->nent < vcpu->arch.cpuid_nent) - goto out; - r = -EFAULT; - if (copy_to_user(entries, &vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) - goto out; - return 0; - -out: - cpuid->nent = vcpu->arch.cpuid_nent; - return r; -} - -static void cpuid_mask(u32 *word, int wordnum) -{ - *word &= boot_cpu_data.x86_capability[wordnum]; -} - -static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index) -{ - entry->function = function; - entry->index = index; - cpuid_count(entry->function, entry->index, - &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; -} - -static bool supported_xcr0_bit(unsigned bit) -{ - u64 mask = ((u64)1 << bit); - - return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0; -} - -#define F(x) bit(X86_FEATURE_##x) - -static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) -{ - unsigned f_nx = is_efer_nx() ? F(NX) : 0; -#ifdef CONFIG_X86_64 - unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL) - ? F(GBPAGES) : 0; - unsigned f_lm = F(LM); -#else - unsigned f_gbpages = 0; - unsigned f_lm = 0; -#endif - unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; - - /* cpuid 1.edx */ - const u32 kvm_supported_word0_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) | - 0 /* Reserved, DS, ACPI */ | F(MMX) | - F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | - 0 /* HTT, TM, Reserved, PBE */; - /* cpuid 0x80000001.edx */ - const u32 kvm_supported_word1_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | - F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp | - 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); - /* cpuid 1.ecx */ - const u32 kvm_supported_word4_x86_features = - F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | - 0 /* DS-CPL, VMX, SMX, EST */ | - 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ | - 0 /* Reserved, DCA */ | F(XMM4_1) | - F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | - F(F16C) | F(RDRAND); - /* cpuid 0x80000001.ecx */ - const u32 kvm_supported_word6_x86_features = - F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | - F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); - - /* cpuid 0xC0000001.edx */ - const u32 kvm_supported_word5_x86_features = - F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | - F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | - F(PMM) | F(PMM_EN); - - /* cpuid 7.0.ebx */ - const u32 kvm_supported_word9_x86_features = - F(SMEP) | F(FSGSBASE) | F(ERMS); - - /* all calls to cpuid_count() should be made on the same cpu */ - get_cpu(); - do_cpuid_1_ent(entry, function, index); - ++*nent; - - switch (function) { - case 0: - entry->eax = min(entry->eax, (u32)0xd); - break; - case 1: - entry->edx &= kvm_supported_word0_x86_features; - cpuid_mask(&entry->edx, 0); - entry->ecx &= kvm_supported_word4_x86_features; - cpuid_mask(&entry->ecx, 4); - /* we support x2apic emulation even if host does not support - * it since we emulate x2apic in software */ - entry->ecx |= F(X2APIC); - break; - /* function 2 entries are STATEFUL. That is, repeated cpuid commands - * may return different values. This forces us to get_cpu() before - * issuing the first command, and also to emulate this annoying behavior - * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ - case 2: { - int t, times = entry->eax & 0xff; - - entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - for (t = 1; t < times && *nent < maxnent; ++t) { - do_cpuid_1_ent(&entry[t], function, 0); - entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - ++*nent; - } - break; - } - /* function 4 has additional index. */ - case 4: { - int i, cache_type; - - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* read more entries until cache_type is zero */ - for (i = 1; *nent < maxnent; ++i) { - cache_type = entry[i - 1].eax & 0x1f; - if (!cache_type) - break; - do_cpuid_1_ent(&entry[i], function, i); - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; - } - break; - } - case 7: { - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* Mask ebx against host capbability word 9 */ - if (index == 0) { - entry->ebx &= kvm_supported_word9_x86_features; - cpuid_mask(&entry->ebx, 9); - } else - entry->ebx = 0; - entry->eax = 0; - entry->ecx = 0; - entry->edx = 0; - break; - } - case 9: - break; - /* function 0xb has additional index. */ - case 0xb: { - int i, level_type; - - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* read more entries until level_type is zero */ - for (i = 1; *nent < maxnent; ++i) { - level_type = entry[i - 1].ecx & 0xff00; - if (!level_type) - break; - do_cpuid_1_ent(&entry[i], function, i); - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; - } - break; - } - case 0xd: { - int idx, i; - - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - for (idx = 1, i = 1; *nent < maxnent && idx < 64; ++idx) { - do_cpuid_1_ent(&entry[i], function, idx); - if (entry[i].eax == 0 || !supported_xcr0_bit(idx)) - continue; - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; - ++i; - } - break; - } - case KVM_CPUID_SIGNATURE: { - char signature[12] = "KVMKVMKVM\0\0"; - u32 *sigptr = (u32 *)signature; - entry->eax = 0; - entry->ebx = sigptr[0]; - entry->ecx = sigptr[1]; - entry->edx = sigptr[2]; - break; - } - case KVM_CPUID_FEATURES: - entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | - (1 << KVM_FEATURE_NOP_IO_DELAY) | - (1 << KVM_FEATURE_CLOCKSOURCE2) | - (1 << KVM_FEATURE_ASYNC_PF) | - (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); - - if (sched_info_on()) - entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); - - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - break; - case 0x80000000: - entry->eax = min(entry->eax, 0x8000001a); - break; - case 0x80000001: - entry->edx &= kvm_supported_word1_x86_features; - cpuid_mask(&entry->edx, 1); - entry->ecx &= kvm_supported_word6_x86_features; - cpuid_mask(&entry->ecx, 6); - break; - case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; - - if (!g_phys_as) - g_phys_as = phys_as; - entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; - break; - } - case 0x80000019: - entry->ecx = entry->edx = 0; - break; - case 0x8000001a: - break; - case 0x8000001d: - break; - /*Add support for Centaur's CPUID instruction*/ - case 0xC0000000: - /*Just support up to 0xC0000004 now*/ - entry->eax = min(entry->eax, 0xC0000004); - break; - case 0xC0000001: - entry->edx &= kvm_supported_word5_x86_features; - cpuid_mask(&entry->edx, 5); - break; - case 3: /* Processor serial number */ - case 5: /* MONITOR/MWAIT */ - case 6: /* Thermal management */ - case 0xA: /* Architectural Performance Monitoring */ - case 0x80000007: /* Advanced power management */ - case 0xC0000002: - case 0xC0000003: - case 0xC0000004: - default: - entry->eax = entry->ebx = entry->ecx = entry->edx = 0; - break; - } - - kvm_x86_ops->set_supported_cpuid(function, entry); - - put_cpu(); -} - -#undef F - -static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) -{ - struct kvm_cpuid_entry2 *cpuid_entries; - int limit, nent = 0, r = -E2BIG; - u32 func; - - if (cpuid->nent < 1) - goto out; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - cpuid->nent = KVM_MAX_CPUID_ENTRIES; - r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); - if (!cpuid_entries) - goto out; - - do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent); - limit = cpuid_entries[0].eax; - for (func = 1; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent); - limit = cpuid_entries[nent - 1].eax; - for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - - - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - /* Add support for Centaur's CPUID instruction. */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) { - do_cpuid_ent(&cpuid_entries[nent], 0xC0000000, 0, - &nent, cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - limit = cpuid_entries[nent - 1].eax; - for (func = 0xC0000001; - func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - } - - do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent, - cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent, - cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - r = -EFAULT; - if (copy_to_user(entries, cpuid_entries, - nent * sizeof(struct kvm_cpuid_entry2))) - goto out_free; - cpuid->nent = nent; - r = 0; - -out_free: - vfree(cpuid_entries); -out: - return r; -} - static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { @@ -5438,125 +4929,6 @@ int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) -{ - struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - int j, nent = vcpu->arch.cpuid_nent; - - e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; - /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; ; j = (j + 1) % nent) { - struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; - if (ej->function == e->function) { - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - return j; - } - } - return 0; /* silence gcc, even though control never reaches here */ -} - -/* find an entry with matching function, matching index (if needed), and that - * should be read next (if it's stateful) */ -static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, - u32 function, u32 index) -{ - if (e->function != function) - return 0; - if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) - return 0; - if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && - !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) - return 0; - return 1; -} - -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index) -{ - int i; - struct kvm_cpuid_entry2 *best = NULL; - - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - struct kvm_cpuid_entry2 *e; - - e = &vcpu->arch.cpuid_entries[i]; - if (is_matching_cpuid_entry(e, function, index)) { - if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) - move_to_next_stateful_cpuid_entry(vcpu, i); - best = e; - break; - } - } - return best; -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); - -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); - if (!best || best->eax < 0x80000008) - goto not_found; - best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best) - return best->eax & 0xff; -not_found: - return 36; -} - -/* - * If no match is found, check whether we exceed the vCPU's limit - * and return the content of the highest valid _standard_ leaf instead. - * This is to satisfy the CPUID specification. - */ -static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, - u32 function, u32 index) -{ - struct kvm_cpuid_entry2 *maxlevel; - - maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - if (!maxlevel || maxlevel->eax >= function) - return NULL; - if (function & 0x80000000) { - maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); - if (!maxlevel) - return NULL; - } - return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); -} - -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) -{ - u32 function, index; - struct kvm_cpuid_entry2 *best; - - function = kvm_register_read(vcpu, VCPU_REGS_RAX); - index = kvm_register_read(vcpu, VCPU_REGS_RCX); - kvm_register_write(vcpu, VCPU_REGS_RAX, 0); - kvm_register_write(vcpu, VCPU_REGS_RBX, 0); - kvm_register_write(vcpu, VCPU_REGS_RCX, 0); - kvm_register_write(vcpu, VCPU_REGS_RDX, 0); - best = kvm_find_cpuid_entry(vcpu, function, index); - - if (!best) - best = check_cpuid_limit(vcpu, function, index); - - if (best) { - kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); - kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); - kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx); - kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); - } - kvm_x86_ops->skip_emulated_instruction(vcpu); - trace_kvm_cpuid(function, - kvm_register_read(vcpu, VCPU_REGS_RAX), - kvm_register_read(vcpu, VCPU_REGS_RBX), - kvm_register_read(vcpu, VCPU_REGS_RCX), - kvm_register_read(vcpu, VCPU_REGS_RDX)); -} -EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); - /* * Check if userspace requested an interrupt window, and that the * interrupt window is open. @@ -6222,7 +5594,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); if (sregs->cr4 & X86_CR4_OSXSAVE) - update_cpuid(vcpu); + kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); if (!is_long_mode(vcpu) && is_pae(vcpu)) { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index d36fe237c665..cb80c293cdd8 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -33,9 +33,6 @@ static inline bool kvm_exception_is_soft(unsigned int nr) return (nr == BP_VECTOR) || (nr == OF_VECTOR); } -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index); - static inline bool is_protmode(struct kvm_vcpu *vcpu) { return kvm_read_cr0_bits(vcpu, X86_CR0_PE); @@ -125,4 +122,6 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +extern u64 host_xcr0; + #endif -- cgit v1.2.3 From fb215366b3c7320ac25dca766a0152df16534932 Mon Sep 17 00:00:00 2001 From: "Liu, Jinsong" Date: Mon, 28 Nov 2011 03:55:19 -0800 Subject: KVM: expose latest Intel cpu new features (BMI1/BMI2/FMA/AVX2) to guest Intel latest cpu add 6 new features, refer http://software.intel.com/file/36945 The new feature cpuid listed as below: 1. FMA CPUID.EAX=01H:ECX.FMA[bit 12] 2. MOVBE CPUID.EAX=01H:ECX.MOVBE[bit 22] 3. BMI1 CPUID.EAX=07H,ECX=0H:EBX.BMI1[bit 3] 4. AVX2 CPUID.EAX=07H,ECX=0H:EBX.AVX2[bit 5] 5. BMI2 CPUID.EAX=07H,ECX=0H:EBX.BMI2[bit 8] 6. LZCNT CPUID.EAX=80000001H:ECX.LZCNT[bit 5] This patch expose these features to guest. Among them, FMA/MOVBE/LZCNT has already been defined, MOVBE/LZCNT has already been exposed. This patch defines BMI1/AVX2/BMI2, and exposes FMA/BMI1/AVX2/BMI2 to guest. Signed-off-by: Liu, Jinsong Signed-off-by: Avi Kivity --- arch/x86/include/asm/cpufeature.h | 3 +++ arch/x86/kvm/cpuid.c | 4 ++-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index f3444f700f36..17c5d4bdee5e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -197,7 +197,10 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ #define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ +#define X86_FEATURE_BMI1 (9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */ #define X86_FEATURE_SMEP (9*32+ 7) /* Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 (9*32+ 8) /* 2nd group bit manipulation extensions */ #define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0a332ec5203c..47be763e1b60 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -222,7 +222,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ | + F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | @@ -242,7 +242,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ebx */ const u32 kvm_supported_word9_x86_features = - F(SMEP) | F(FSGSBASE) | F(ERMS); + F(FSGSBASE) | F(BMI1) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); -- cgit v1.2.3 From 831bf664e9c1fc08fc6b3984d00d275cac82f5e9 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 28 Nov 2011 11:20:29 +0200 Subject: KVM: Refactor and simplify kvm_dev_ioctl_get_supported_cpuid This patch cleans and simplifies kvm_dev_ioctl_get_supported_cpuid by using a table instead of duplicating code as Avi suggested. This patch also fixes a bug where kvm_dev_ioctl_get_supported_cpuid would return -E2BIG when amount of entries passed was just right. Signed-off-by: Sasha Levin Signed-off-by: Avi Kivity --- arch/x86/kvm/cpuid.c | 113 ++++++++++++++++++++++++++++----------------------- 1 file changed, 63 insertions(+), 50 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 47be763e1b60..52593e8e1ae8 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -183,9 +183,10 @@ static bool supported_xcr0_bit(unsigned bit) #define F(x) bit(X86_FEATURE_##x) -static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, +static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, u32 index, int *nent, int maxnent) { + int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; #ifdef CONFIG_X86_64 unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL) @@ -246,6 +247,12 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); + + r = -E2BIG; + + if (*nent >= maxnent) + goto out; + do_cpuid_1_ent(entry, function, index); ++*nent; @@ -271,7 +278,10 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - for (t = 1; t < times && *nent < maxnent; ++t) { + for (t = 1; t < times; ++t) { + if (*nent >= maxnent) + goto out; + do_cpuid_1_ent(&entry[t], function, 0); entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; ++*nent; @@ -284,7 +294,10 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* read more entries until cache_type is zero */ - for (i = 1; *nent < maxnent; ++i) { + for (i = 1; ; ++i) { + if (*nent >= maxnent) + goto out; + cache_type = entry[i - 1].eax & 0x1f; if (!cache_type) break; @@ -316,7 +329,10 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* read more entries until level_type is zero */ - for (i = 1; *nent < maxnent; ++i) { + for (i = 1; ; ++i) { + if (*nent >= maxnent) + goto out; + level_type = entry[i - 1].ecx & 0xff00; if (!level_type) break; @@ -331,7 +347,10 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, int idx, i; entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - for (idx = 1, i = 1; *nent < maxnent && idx < 64; ++idx) { + for (idx = 1, i = 1; idx < 64; ++idx) { + if (*nent >= maxnent) + goto out; + do_cpuid_1_ent(&entry[i], function, idx); if (entry[i].eax == 0 || !supported_xcr0_bit(idx)) continue; @@ -416,17 +435,41 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, kvm_x86_ops->set_supported_cpuid(function, entry); + r = 0; + +out: put_cpu(); + + return r; } #undef F +struct kvm_cpuid_param { + u32 func; + u32 idx; + bool has_leaf_count; + bool (*qualifier)(struct kvm_cpuid_param *param); +}; + +static bool is_centaur_cpu(struct kvm_cpuid_param *param) +{ + return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; +} + int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { struct kvm_cpuid_entry2 *cpuid_entries; - int limit, nent = 0, r = -E2BIG; + int limit, nent = 0, r = -E2BIG, i; u32 func; + static struct kvm_cpuid_param param[] = { + { .func = 0, .has_leaf_count = true }, + { .func = 0x80000000, .has_leaf_count = true }, + { .func = 0xC0000000, .qualifier = is_centaur_cpu, .has_leaf_count = true }, + { .func = KVM_CPUID_SIGNATURE }, + { .func = KVM_CPUID_FEATURES }, + }; if (cpuid->nent < 1) goto out; @@ -437,61 +480,31 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, if (!cpuid_entries) goto out; - do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent); - limit = cpuid_entries[0].eax; - for (func = 1; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent); - limit = cpuid_entries[nent - 1].eax; - for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - - + r = 0; + for (i = 0; i < ARRAY_SIZE(param); i++) { + struct kvm_cpuid_param *ent = ¶m[i]; - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; + if (ent->qualifier && !ent->qualifier(ent)) + continue; - /* Add support for Centaur's CPUID instruction. */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) { - do_cpuid_ent(&cpuid_entries[nent], 0xC0000000, 0, + r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, &nent, cpuid->nent); - r = -E2BIG; - if (nent >= cpuid->nent) + if (r) goto out_free; + if (!ent->has_leaf_count) + continue; + limit = cpuid_entries[nent - 1].eax; - for (func = 0xC0000001; - func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); + for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) + r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, + &nent, cpuid->nent); - r = -E2BIG; - if (nent >= cpuid->nent) + if (r) goto out_free; } - do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent, - cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent, - cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - r = -EFAULT; if (copy_to_user(entries, cpuid_entries, nent * sizeof(struct kvm_cpuid_entry2))) -- cgit v1.2.3 From a65cf5181aa608addcb2873c8ed90413a9f539cb Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 28 Nov 2011 20:39:59 +0800 Subject: jump-label: export jump_label_inc/jump_label_dec Export these two symbols, they will be used by KVM mmu audit Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- kernel/jump_label.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 66ff7109f697..2af9027106a8 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -71,6 +71,7 @@ void jump_label_inc(struct jump_label_key *key) atomic_inc(&key->enabled); jump_label_unlock(); } +EXPORT_SYMBOL_GPL(jump_label_inc); void jump_label_dec(struct jump_label_key *key) { @@ -80,6 +81,7 @@ void jump_label_dec(struct jump_label_key *key) jump_label_update(key, JUMP_LABEL_DISABLE); jump_label_unlock(); } +EXPORT_SYMBOL_GPL(jump_label_dec); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { -- cgit v1.2.3 From 0375f7fad904b59502341ccecfc8faea70b34c91 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 28 Nov 2011 20:41:00 +0800 Subject: KVM: MMU: audit: replace mmu audit tracepoint with jump-label The tracepoint is only used to audit mmu code, it should not be exposed to user, let us replace it with jump-label. Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 16 +++++++++++----- arch/x86/kvm/mmu_audit.c | 28 +++++++++++++--------------- arch/x86/kvm/mmutrace.h | 19 ------------------- arch/x86/kvm/paging_tmpl.h | 4 ++-- 4 files changed, 26 insertions(+), 41 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d737443cdfdb..62f69dbf6b52 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -68,6 +68,12 @@ char *audit_point_name[] = { "post sync" }; +#ifdef CONFIG_KVM_MMU_AUDIT +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point); +#else +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } +#endif + #undef MMU_DEBUG #ifdef MMU_DEBUG @@ -2852,12 +2858,12 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) return; vcpu_clear_mmio_info(vcpu, ~0ul); - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); + kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; sp = page_header(root); mmu_sync_children(vcpu, sp); - trace_kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); return; } for (i = 0; i < 4; ++i) { @@ -2869,7 +2875,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) mmu_sync_children(vcpu, sp); } } - trace_kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); } void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) @@ -3667,7 +3673,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, spin_lock(&vcpu->kvm->mmu_lock); ++vcpu->kvm->stat.mmu_pte_write; - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); + kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { @@ -3700,7 +3706,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, } mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush); kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - trace_kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); + kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); spin_unlock(&vcpu->kvm->mmu_lock); } diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 746ec259d024..5df6736a5afb 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -224,30 +224,29 @@ static void audit_vcpu_spte(struct kvm_vcpu *vcpu) mmu_spte_walk(vcpu, audit_spte); } -static void kvm_mmu_audit(void *ignore, struct kvm_vcpu *vcpu, int point) +static bool mmu_audit; +static struct jump_label_key mmu_audit_key; + +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); - if (!__ratelimit(&ratelimit_state)) - return; + if (static_branch((&mmu_audit_key))) { + if (!__ratelimit(&ratelimit_state)) + return; - vcpu->kvm->arch.audit_point = point; - audit_all_active_sps(vcpu->kvm); - audit_vcpu_spte(vcpu); + vcpu->kvm->arch.audit_point = point; + audit_all_active_sps(vcpu->kvm); + audit_vcpu_spte(vcpu); + } } -static bool mmu_audit; - static void mmu_audit_enable(void) { - int ret; - if (mmu_audit) return; - ret = register_trace_kvm_mmu_audit(kvm_mmu_audit, NULL); - WARN_ON(ret); - + jump_label_inc(&mmu_audit_key); mmu_audit = true; } @@ -256,8 +255,7 @@ static void mmu_audit_disable(void) if (!mmu_audit) return; - unregister_trace_kvm_mmu_audit(kvm_mmu_audit, NULL); - tracepoint_synchronize_unregister(); + jump_label_dec(&mmu_audit_key); mmu_audit = false; } diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index eed67f34146d..89fb0e81322a 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -243,25 +243,6 @@ TRACE_EVENT( TP_printk("addr:%llx gfn %llx access %x", __entry->addr, __entry->gfn, __entry->access) ); - -TRACE_EVENT( - kvm_mmu_audit, - TP_PROTO(struct kvm_vcpu *vcpu, int audit_point), - TP_ARGS(vcpu, audit_point), - - TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) - __field(int, audit_point) - ), - - TP_fast_assign( - __entry->vcpu = vcpu; - __entry->audit_point = audit_point; - ), - - TP_printk("vcpu:%d %s", __entry->vcpu->cpu, - audit_point_name[__entry->audit_point]) -); #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 52e9d58cec2b..15610285ebb6 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -632,7 +632,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); + kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); kvm_mmu_free_some_pages(vcpu); if (!force_pt_level) transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); @@ -643,7 +643,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, sptep, *sptep, emulate); ++vcpu->stat.pf_fixed; - trace_kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); + kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); spin_unlock(&vcpu->kvm->mmu_lock); return emulate; -- cgit v1.2.3 From 9edb17d55f3ea4943f9654f2aad7a99b4c55840a Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 28 Nov 2011 20:41:38 +0800 Subject: KVM: x86: remove the dead code of KVM_EXIT_HYPERCALL KVM_EXIT_HYPERCALL is not used anymore, so remove the code Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4e533d24c513..465053151a2d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5389,10 +5389,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (r <= 0) goto out; - if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) - kvm_register_write(vcpu, VCPU_REGS_RAX, - kvm_run->hypercall.ret); - r = __vcpu_run(vcpu); out: -- cgit v1.2.3 From e459e3228dc57f7160e564ce0f09edb5bee656d3 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 28 Nov 2011 20:42:16 +0800 Subject: KVM: MMU: move the relevant mmu code to mmu.c Move the mmu code in kvm_arch_vcpu_init() to kvm_mmu_create() Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 6 ++++++ arch/x86/kvm/mmu.c | 6 +++++- arch/x86/kvm/x86.c | 11 +---------- 3 files changed, 12 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1769f3dde611..020413afb285 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -752,6 +752,7 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, @@ -773,6 +774,11 @@ void kvm_disable_tdp(void); int complete_pio(struct kvm_vcpu *vcpu); bool kvm_check_iopl(struct kvm_vcpu *vcpu); +static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) +{ + return gpa; +} + static inline struct kvm_mmu_page *page_header(hpa_t shadow_page) { struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 62f69dbf6b52..262a3af1f0ec 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3839,7 +3839,11 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) int kvm_mmu_create(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + vcpu->arch.walk_mmu = &vcpu->arch.mmu; + vcpu->arch.mmu.root_hpa = INVALID_PAGE; + vcpu->arch.mmu.translate_gpa = translate_gpa; + vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; return alloc_mmu_pages(vcpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 465053151a2d..d99976e4451e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3430,12 +3430,7 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, kvm_x86_ops->get_segment(vcpu, var, seg); } -static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) -{ - return gpa; -} - -static gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) { gpa_t t_gpa; struct x86_exception exception; @@ -5915,10 +5910,6 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm = vcpu->kvm; vcpu->arch.emulate_ctxt.ops = &emulate_ops; - vcpu->arch.walk_mmu = &vcpu->arch.mmu; - vcpu->arch.mmu.root_hpa = INVALID_PAGE; - vcpu->arch.mmu.translate_gpa = translate_gpa; - vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else -- cgit v1.2.3 From d750ea28865dbff6a73444358d189dd811c68c50 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 28 Nov 2011 20:43:18 +0800 Subject: KVM: MMU: remove oos_shadow parameter The unsync code should be stable now, maybe it is the time to remove this parameter to cleanup the code a little bit Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- Documentation/kernel-parameters.txt | 3 --- arch/x86/kvm/mmu.c | 5 ----- 2 files changed, 8 deletions(-) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 81c287fad79d..6e7cce096e6b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1178,9 +1178,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. Default is 0 (don't ignore, but inject #GP) - kvm.oos_shadow= [KVM] Disable out-of-sync shadow paging. - Default is 1 (enabled) - kvm.mmu_audit= [KVM] This is a R/W parameter which allows audit KVM MMU at runtime. Default is 0 (off) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 262a3af1f0ec..b1178d1bb8f5 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -93,9 +93,6 @@ static int dbg = 0; module_param(dbg, bool, 0644); #endif -static int oos_shadow = 1; -module_param(oos_shadow, bool, 0644); - #ifndef MMU_DEBUG #define ASSERT(x) do { } while (0) #else @@ -2196,8 +2193,6 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 1; if (!need_unsync && !s->unsync) { - if (!oos_shadow) - return 1; need_unsync = true; } } -- cgit v1.2.3 From e37fa7853c276403da2fea8792c579e8bfd75042 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 30 Nov 2011 17:43:24 +0800 Subject: KVM: MMU: audit: inline audit function inline audit function and little cleanup Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 28 +++++++--------------------- arch/x86/kvm/mmu_audit.c | 29 +++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 29 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b1178d1bb8f5..7a8e99c6dc81 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -59,21 +59,6 @@ enum { AUDIT_POST_SYNC }; -char *audit_point_name[] = { - "pre page fault", - "post page fault", - "pre pte write", - "post pte write", - "pre sync", - "post sync" -}; - -#ifdef CONFIG_KVM_MMU_AUDIT -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point); -#else -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } -#endif - #undef MMU_DEBUG #ifdef MMU_DEBUG @@ -1539,6 +1524,13 @@ static int kvm_sync_page_transient(struct kvm_vcpu *vcpu, return ret; } +#ifdef CONFIG_KVM_MMU_AUDIT +#include "mmu_audit.c" +#else +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } +static void mmu_audit_disable(void) { } +#endif + static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -4035,12 +4027,6 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) mmu_free_memory_caches(vcpu); } -#ifdef CONFIG_KVM_MMU_AUDIT -#include "mmu_audit.c" -#else -static void mmu_audit_disable(void) { } -#endif - void kvm_mmu_module_exit(void) { mmu_destroy_caches(); diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 5df6736a5afb..fe15dcc07a6b 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -19,6 +19,15 @@ #include +char const *audit_point_name[] = { + "pre page fault", + "post page fault", + "pre pte write", + "post pte write", + "pre sync", + "post sync" +}; + #define audit_printk(kvm, fmt, args...) \ printk(KERN_ERR "audit: (%s) error: " \ fmt, audit_point_name[kvm->arch.audit_point], ##args) @@ -227,18 +236,22 @@ static void audit_vcpu_spte(struct kvm_vcpu *vcpu) static bool mmu_audit; static struct jump_label_key mmu_audit_key; -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) +static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); - if (static_branch((&mmu_audit_key))) { - if (!__ratelimit(&ratelimit_state)) - return; + if (!__ratelimit(&ratelimit_state)) + return; - vcpu->kvm->arch.audit_point = point; - audit_all_active_sps(vcpu->kvm); - audit_vcpu_spte(vcpu); - } + vcpu->kvm->arch.audit_point = point; + audit_all_active_sps(vcpu->kvm); + audit_vcpu_spte(vcpu); +} + +static inline void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) +{ + if (static_branch((&mmu_audit_key))) + __kvm_mmu_audit(vcpu, point); } static void mmu_audit_enable(void) -- cgit v1.2.3 From 086c9855019935854311b477b33498a6ea357ef6 Mon Sep 17 00:00:00 2001 From: "Alex,Shi" Date: Thu, 20 Oct 2011 15:34:01 +0800 Subject: KVM: use this_cpu_xxx replace percpu_xxx funcs percpu_xxx funcs are duplicated with this_cpu_xxx funcs, so replace them for further code clean up. And in preempt safe scenario, __this_cpu_xxx funcs has a bit better performance since __this_cpu_xxx has no redundant preempt_disable() Signed-off-by: Alex Shi Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d99976e4451e..d55a94f1155a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4664,15 +4664,15 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); static int kvm_is_in_guest(void) { - return percpu_read(current_vcpu) != NULL; + return __this_cpu_read(current_vcpu) != NULL; } static int kvm_is_user_mode(void) { int user_mode = 3; - if (percpu_read(current_vcpu)) - user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu)); + if (__this_cpu_read(current_vcpu)) + user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu)); return user_mode != 0; } @@ -4681,8 +4681,8 @@ static unsigned long kvm_get_guest_ip(void) { unsigned long ip = 0; - if (percpu_read(current_vcpu)) - ip = kvm_rip_read(percpu_read(current_vcpu)); + if (__this_cpu_read(current_vcpu)) + ip = kvm_rip_read(__this_cpu_read(current_vcpu)); return ip; } @@ -4695,13 +4695,13 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { void kvm_before_handle_nmi(struct kvm_vcpu *vcpu) { - percpu_write(current_vcpu, vcpu); + __this_cpu_write(current_vcpu, vcpu); } EXPORT_SYMBOL_GPL(kvm_before_handle_nmi); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) { - percpu_write(current_vcpu, NULL); + __this_cpu_write(current_vcpu, NULL); } EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); -- cgit v1.2.3 From 3d56cbdf359c953f8bfcab68aa5cf766e4480799 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 2 Dec 2011 18:35:24 +0100 Subject: KVM: MMU: Drop unused return value of kvm_mmu_remove_some_alloc_mmu_pages freed_pages is never evaluated, so remove it as well as the return code kvm_mmu_remove_some_alloc_mmu_pages so far delivered to its only user. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7a8e99c6dc81..2a2a9b40db19 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3890,14 +3890,14 @@ restart: spin_unlock(&kvm->mmu_lock); } -static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, - struct list_head *invalid_list) +static void kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, + struct list_head *invalid_list) { struct kvm_mmu_page *page; page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); - return kvm_mmu_prepare_zap_page(kvm, page, invalid_list); + kvm_mmu_prepare_zap_page(kvm, page, invalid_list); } static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) @@ -3912,15 +3912,15 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) raw_spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - int idx, freed_pages; + int idx; LIST_HEAD(invalid_list); idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); if (!kvm_freed && nr_to_scan > 0 && kvm->arch.n_used_mmu_pages > 0) { - freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm, - &invalid_list); + kvm_mmu_remove_some_alloc_mmu_pages(kvm, + &invalid_list); kvm_freed = kvm; } nr_to_scan--; -- cgit v1.2.3 From 234b639206a7d9d5ca362cff64ceddd4f27e4a46 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 2 Dec 2011 18:26:28 +0100 Subject: KVM: x86 emulator: Remove set-but-unused cr4 from check_cr_write This was probably copy&pasted from the cr0 case, but it's unneeded here. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ac8e5ed78834..f641201c7b31 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3028,9 +3028,6 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) break; } case 4: { - u64 cr4; - - cr4 = ctxt->ops->get_cr(ctxt, 4); ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if ((efer & EFER_LMA) && !(new_val & X86_CR4_PAE)) -- cgit v1.2.3 From 3f745f1e224e05e845a15760a55f3fd323f7a753 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 7 Dec 2011 12:42:47 +0200 Subject: KVM: Document KVM_NMI Signed-off-by: Avi Kivity --- Documentation/virtual/kvm/api.txt | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index e2a4b5287361..e1d94bf4056e 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1466,6 +1466,31 @@ is supported; 2 if the processor requires all virtual machines to have an RMA, or 1 if the processor can use an RMA but doesn't require it, because it supports the Virtual RMA (VRMA) facility. +4.64 KVM_NMI + +Capability: KVM_CAP_USER_NMI +Architectures: x86 +Type: vcpu ioctl +Parameters: none +Returns: 0 on success, -1 on error + +Queues an NMI on the thread's vcpu. Note this is well defined only +when KVM_CREATE_IRQCHIP has not been called, since this is an interface +between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP +has been called, this interface is completely emulated within the kernel. + +To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the +following algorithm: + + - pause the vpcu + - read the local APIC's state (KVM_GET_LAPIC) + - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1) + - if so, issue KVM_NMI + - resume the vcpu + +Some guests configure the LINT1 NMI input to cause a panic, aiding in +debugging. + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by -- cgit v1.2.3 From cdfca7b346e6dbab1ba33260c28ccb8333485a5b Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sun, 4 Dec 2011 19:36:28 +0200 Subject: KVM: Use kmemdup() instead of kmalloc/memcpy Switch to kmemdup() in two places to shorten the code and avoid possible bugs. Signed-off-by: Sasha Levin Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 4 ++-- virt/kvm/kvm_main.c | 7 +++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d55a94f1155a..03042d60a8fc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3031,10 +3031,10 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, memset(dirty_bitmap_head, 0, n); r = -ENOMEM; - slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + slots = kmemdup(kvm->memslots, sizeof(*kvm->memslots), GFP_KERNEL); if (!slots) goto out; - memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + memslot = id_to_memslot(slots, log->slot); memslot->nr_dirty_pages = 0; memslot->dirty_bitmap = dirty_bitmap_head; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e289486edc6d..a6e612fced73 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2591,13 +2591,12 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, int i, r; struct kvm_io_bus *new_bus, *bus; - new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); + bus = kvm->buses[bus_idx]; + + new_bus = kmemdup(bus, sizeof(*bus), GFP_KERNEL); if (!new_bus) return -ENOMEM; - bus = kvm->buses[bus_idx]; - memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); - r = -ENOENT; for (i = 0; i < new_bus->dev_count; i++) if (new_bus->range[i].dev == dev) { -- cgit v1.2.3 From ff5c2c0316ff0e3e2dba3ca14167d994453df093 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sun, 4 Dec 2011 19:36:29 +0200 Subject: KVM: Use memdup_user instead of kmalloc/copy_from_user Switch to using memdup_user when possible. This makes code more smaller and compact, and prevents errors. Signed-off-by: Sasha Levin Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 82 +++++++++++++++++++++++------------------------------ virt/kvm/kvm_main.c | 29 ++++++++----------- 2 files changed, 47 insertions(+), 64 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 03042d60a8fc..0a646e2b57c5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1309,12 +1309,11 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) if (page_num >= blob_size) goto out; r = -ENOMEM; - page = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!page) + page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE); + if (IS_ERR(page)) { + r = PTR_ERR(page); goto out; - r = -EFAULT; - if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE)) - goto out_free; + } if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) goto out_free; r = 0; @@ -1988,15 +1987,12 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, if (msrs.nmsrs >= MAX_IO_MSRS) goto out; - r = -ENOMEM; size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; - entries = kmalloc(size, GFP_KERNEL); - if (!entries) + entries = memdup_user(user_msrs->entries, size); + if (IS_ERR(entries)) { + r = PTR_ERR(entries); goto out; - - r = -EFAULT; - if (copy_from_user(entries, user_msrs->entries, size)) - goto out_free; + } r = n = __msr_io(vcpu, &msrs, entries, do_msr); if (r < 0) @@ -2533,13 +2529,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; if (!vcpu->arch.apic) goto out; - u.lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); - r = -ENOMEM; - if (!u.lapic) - goto out; - r = -EFAULT; - if (copy_from_user(u.lapic, argp, sizeof(struct kvm_lapic_state))) + u.lapic = memdup_user(argp, sizeof(*u.lapic)); + if (IS_ERR(u.lapic)) { + r = PTR_ERR(u.lapic); goto out; + } + r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); if (r) goto out; @@ -2718,14 +2713,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_XSAVE: { - u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); - r = -ENOMEM; - if (!u.xsave) - break; - - r = -EFAULT; - if (copy_from_user(u.xsave, argp, sizeof(struct kvm_xsave))) - break; + u.xsave = memdup_user(argp, sizeof(*u.xsave)); + if (IS_ERR(u.xsave)) { + r = PTR_ERR(u.xsave); + goto out; + } r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; @@ -2746,15 +2738,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_XCRS: { - u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); - r = -ENOMEM; - if (!u.xcrs) - break; - - r = -EFAULT; - if (copy_from_user(u.xcrs, argp, - sizeof(struct kvm_xcrs))) - break; + u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); + if (IS_ERR(u.xcrs)) { + r = PTR_ERR(u.xcrs); + goto out; + } r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; @@ -3190,14 +3178,14 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_GET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL); + struct kvm_irqchip *chip; - r = -ENOMEM; - if (!chip) + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); goto out; - r = -EFAULT; - if (copy_from_user(chip, argp, sizeof *chip)) - goto get_irqchip_out; + } + r = -ENXIO; if (!irqchip_in_kernel(kvm)) goto get_irqchip_out; @@ -3216,14 +3204,14 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_SET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL); + struct kvm_irqchip *chip; - r = -ENOMEM; - if (!chip) + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); goto out; - r = -EFAULT; - if (copy_from_user(chip, argp, sizeof *chip)) - goto set_irqchip_out; + } + r = -ENXIO; if (!irqchip_in_kernel(kvm)) goto set_irqchip_out; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a6e612fced73..d8bac0751666 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1821,12 +1821,11 @@ out_free1: struct kvm_regs *kvm_regs; r = -ENOMEM; - kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); - if (!kvm_regs) + kvm_regs = memdup_user(argp, sizeof(*kvm_regs)); + if (IS_ERR(kvm_regs)) { + r = PTR_ERR(kvm_regs); goto out; - r = -EFAULT; - if (copy_from_user(kvm_regs, argp, sizeof(struct kvm_regs))) - goto out_free2; + } r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs); if (r) goto out_free2; @@ -1850,13 +1849,11 @@ out_free2: break; } case KVM_SET_SREGS: { - kvm_sregs = kmalloc(sizeof(struct kvm_sregs), GFP_KERNEL); - r = -ENOMEM; - if (!kvm_sregs) - goto out; - r = -EFAULT; - if (copy_from_user(kvm_sregs, argp, sizeof(struct kvm_sregs))) + kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs)); + if (IS_ERR(kvm_sregs)) { + r = PTR_ERR(kvm_sregs); goto out; + } r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs); if (r) goto out; @@ -1952,13 +1949,11 @@ out_free2: break; } case KVM_SET_FPU: { - fpu = kmalloc(sizeof(struct kvm_fpu), GFP_KERNEL); - r = -ENOMEM; - if (!fpu) - goto out; - r = -EFAULT; - if (copy_from_user(fpu, argp, sizeof(struct kvm_fpu))) + fpu = memdup_user(argp, sizeof(*fpu)); + if (IS_ERR(fpu)) { + r = PTR_ERR(fpu); goto out; + } r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); if (r) goto out; -- cgit v1.2.3 From 43771ebfc9d34ab1f74095d052d225a82ae0898c Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 14 Dec 2011 12:27:47 +0200 Subject: KVM: Make KVM_INTEL depend on CPU_SUP_INTEL PMU virtualization needs to talk to Intel-specific bits of perf; these are only available when CPU_SUP_INTEL=y. Fixes arch/x86/built-in.o: In function `atomic_switch_perf_msrs': vmx.c:(.text+0x6b1d4): undefined reference to `perf_guest_get_msrs' Reported-by: Ingo Molnar Reported-by: Randy Dunlap Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/Kconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ff5790d8e990..ca4d49ed9a6c 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -52,6 +52,8 @@ config KVM config KVM_INTEL tristate "KVM for Intel processors support" depends on KVM + # for perf_guest_get_msrs(): + depends on CPU_SUP_INTEL ---help--- Provides support for KVM on Intel processors equipped with the VT extensions. -- cgit v1.2.3 From bb5a798ad58996e4d666ead1016705854d5ca616 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Wed, 14 Dec 2011 17:58:18 +0100 Subject: KVM: x86: Do not rely on implicit inclusions Works so far by change, but it is not guaranteed to stay like this. Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/cpuid.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 52593e8e1ae8..ca63032bf03d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -14,6 +14,8 @@ #include #include +#include +#include #include #include #include "cpuid.h" -- cgit v1.2.3 From a647795efbedeedf8a1dc6deded26defa23562bd Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Wed, 14 Dec 2011 19:25:33 +0100 Subject: KVM: x86: Consolidate PIT legacy test Move the test for KVM_PIT_FLAGS_HPET_LEGACY into create_pit_timer instead of replicating it on the caller site. Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/i8254.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 405f2620392f..d68f99df690c 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -344,7 +344,7 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) struct kvm_timer *pt = &ps->pit_timer; s64 interval; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) return; interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); @@ -397,15 +397,11 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) case 1: /* FIXME: enhance mode 4 precision */ case 4: - if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) { - create_pit_timer(kvm, val, 0); - } + create_pit_timer(kvm, val, 0); break; case 2: case 3: - if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){ - create_pit_timer(kvm, val, 1); - } + create_pit_timer(kvm, val, 1); break; default: destroy_pit_timer(kvm->arch.vpit); -- cgit v1.2.3 From d546cb406ea0d83e2d39ec14221957a24f88a622 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 15 Dec 2011 12:38:40 +0200 Subject: KVM: drop bsp_vcpu pointer from kvm struct Drop bsp_vcpu pointer from kvm struct since its only use is incorrect anyway. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/i8259.c | 24 ++++++++++++++++-------- include/linux/kvm_host.h | 1 - virt/kvm/ioapic.c | 2 +- virt/kvm/kvm_main.c | 4 ---- 4 files changed, 17 insertions(+), 14 deletions(-) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index cac4746d7ffb..b6a73537e1ef 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -262,9 +262,10 @@ int kvm_pic_read_irq(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq; - struct kvm_vcpu *vcpu0 = s->pics_state->kvm->bsp_vcpu; + int irq, i; + struct kvm_vcpu *vcpu; u8 irr = s->irr, isr = s->imr; + bool found = false; s->last_irr = 0; s->irr = 0; @@ -281,12 +282,19 @@ void kvm_pic_reset(struct kvm_kpic_state *s) s->special_fully_nested_mode = 0; s->init4 = 0; - for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { - if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) - if (irr & (1 << irq) || isr & (1 << irq)) { - pic_clear_isr(s, irq); - } - } + kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm) + if (kvm_apic_accept_pic_intr(vcpu)) { + found = true; + break; + } + + + if (!found) + return; + + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) + if (irr & (1 << irq) || isr & (1 << irq)) + pic_clear_isr(s, irq); } static void pic_ioport_write(void *opaque, u32 addr, u32 val) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8c5c30361b0d..7a080383935f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -251,7 +251,6 @@ struct kvm { struct srcu_struct srcu; #ifdef CONFIG_KVM_APIC_ARCHITECTURE u32 bsp_vcpu_id; - struct kvm_vcpu *bsp_vcpu; #endif struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; atomic_t online_vcpus; diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 71e2253edee7..dcaf272c26c0 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -185,7 +185,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) irqe.dest_mode = 0; /* Physical mode. */ /* need to read apic_id from apic regiest since * it can be rewritten */ - irqe.dest_id = ioapic->kvm->bsp_vcpu->vcpu_id; + irqe.dest_id = ioapic->kvm->bsp_vcpu_id; } #endif return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d8bac0751666..0835c4b90d2f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1743,10 +1743,6 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) smp_wmb(); atomic_inc(&kvm->online_vcpus); -#ifdef CONFIG_KVM_APIC_ARCHITECTURE - if (kvm->bsp_vcpu_id == id) - kvm->bsp_vcpu = vcpu; -#endif mutex_unlock(&kvm->lock); return r; -- cgit v1.2.3 From 4f69b6805c4f818cf7f4126978cc4a54c489119f Mon Sep 17 00:00:00 2001 From: Hamo Date: Thu, 15 Dec 2011 14:23:16 +0800 Subject: KVM: ensure that debugfs entries have been created by checking the return value from kvm_init_debug, we can ensure that the entries under debugfs for KVM have been created correctly. Signed-off-by: Yang Bai Signed-off-by: Marcelo Tosatti --- virt/kvm/kvm_main.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0835c4b90d2f..7287bf5d1c9e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2654,15 +2654,29 @@ static const struct file_operations *stat_fops[] = { [KVM_STAT_VM] = &vm_stat_fops, }; -static void kvm_init_debug(void) +static int kvm_init_debug(void) { + int r = -EFAULT; struct kvm_stats_debugfs_item *p; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); - for (p = debugfs_entries; p->name; ++p) + if (kvm_debugfs_dir == NULL) + goto out; + + for (p = debugfs_entries; p->name; ++p) { p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir, (void *)(long)p->offset, stat_fops[p->kind]); + if (p->dentry == NULL) + goto out_dir; + } + + return 0; + +out_dir: + debugfs_remove_recursive(kvm_debugfs_dir); +out: + return r; } static void kvm_exit_debug(void) @@ -2806,10 +2820,16 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; - kvm_init_debug(); + r = kvm_init_debug(); + if (r) { + printk(KERN_ERR "kvm: create debugfs files failed\n"); + goto out_undebugfs; + } return 0; +out_undebugfs: + unregister_syscore_ops(&kvm_syscore_ops); out_unreg: kvm_async_pf_deinit(); out_free: -- cgit v1.2.3 From c15af35f54631b9e9b7ad1981016cc6e73cec794 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 6 Dec 2011 18:06:02 +0900 Subject: KVM: x86 emulator: Use opcode::execute for Group 1A instruction Group 1A: 8F Register em_pop() directly and remove em_grp1a(). Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f641201c7b31..cd49774f2d0e 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1675,11 +1675,6 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_grp1a(struct x86_emulate_ctxt *ctxt) -{ - return emulate_pop(ctxt, &ctxt->dst.val, ctxt->dst.bytes); -} - static int em_grp2(struct x86_emulate_ctxt *ctxt) { switch (ctxt->modrm_reg) { @@ -3203,7 +3198,7 @@ static struct opcode group1[] = { }; static struct opcode group1A[] = { - D(DstMem | SrcNone | ModRM | Mov | Stack), N, N, N, N, N, N, N, + I(DstMem | SrcNone | ModRM | Mov | Stack, em_pop), N, N, N, N, N, N, N, }; static struct opcode group3[] = { @@ -4031,9 +4026,6 @@ special_insn: case 0x8d: /* lea r16/r32, m */ ctxt->dst.val = ctxt->src.addr.mem.ea; break; - case 0x8f: /* pop (sole member of Grp1a) */ - rc = em_grp1a(ctxt); - break; case 0x90 ... 0x97: /* nop / xchg reg, rax */ if (ctxt->dst.addr.reg == &ctxt->regs[VCPU_REGS_RAX]) break; -- cgit v1.2.3 From c04ec8393f3815e0f60dde1d6b29040bf1875d52 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 6 Dec 2011 18:06:44 +0900 Subject: KVM: x86 emulator: Use opcode::execute for Group 4/5 instructions Group 4: FE Group 5: FF Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index cd49774f2d0e..5b78785de41b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3213,16 +3213,19 @@ static struct opcode group3[] = { }; static struct opcode group4[] = { - D(ByteOp | DstMem | SrcNone | ModRM | Lock), D(ByteOp | DstMem | SrcNone | ModRM | Lock), + I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45), + I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45), N, N, N, N, N, N, }; static struct opcode group5[] = { - D(DstMem | SrcNone | ModRM | Lock), D(DstMem | SrcNone | ModRM | Lock), - D(SrcMem | ModRM | Stack), + I(DstMem | SrcNone | ModRM | Lock, em_grp45), + I(DstMem | SrcNone | ModRM | Lock, em_grp45), + I(SrcMem | ModRM | Stack, em_grp45), I(SrcMemFAddr | ModRM | ImplicitOps | Stack, em_call_far), - D(SrcMem | ModRM | Stack), D(SrcMemFAddr | ModRM | ImplicitOps), - D(SrcMem | ModRM | Stack), N, + I(SrcMem | ModRM | Stack, em_grp45), + I(SrcMemFAddr | ModRM | ImplicitOps, em_grp45), + I(SrcMem | ModRM | Stack, em_grp45), N, }; static struct opcode group6[] = { @@ -4082,12 +4085,6 @@ special_insn: case 0xfd: /* std */ ctxt->eflags |= EFLG_DF; break; - case 0xfe: /* Grp4 */ - rc = em_grp45(ctxt); - break; - case 0xff: /* Grp5 */ - rc = em_grp45(ctxt); - break; default: goto cannot_emulate; } -- cgit v1.2.3 From e0dac408d08c2a5e1bed2a6a9da7f3af3f7a9827 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 6 Dec 2011 18:07:27 +0900 Subject: KVM: x86 emulator: Use opcode::execute for Group 9 instruction Group 9: 0F C7 Rename em_grp9() to em_cmpxchg8b() and register it. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5b78785de41b..de7be77820d5 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1784,7 +1784,7 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) return rc; } -static int em_grp9(struct x86_emulate_ctxt *ctxt) +static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) { u64 old = ctxt->dst.orig_val64; @@ -3261,7 +3261,7 @@ static struct opcode group8[] = { }; static struct group_dual group9 = { { - N, D(DstMem64 | ModRM | Lock | PageTable), N, N, N, N, N, N, + N, I(DstMem64 | ModRM | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { N, N, N, N, N, N, N, N, } }; @@ -4202,9 +4202,6 @@ twobyte_insn: ctxt->dst.val = (ctxt->op_bytes == 4) ? (u32) ctxt->src.val : (u64) ctxt->src.val; break; - case 0xc7: /* Grp9 (cmpxchg8b) */ - rc = em_grp9(ctxt); - break; default: goto cannot_emulate; } -- cgit v1.2.3 From 893420822192f717af6fde927c9e78c9b82f8327 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 10 Nov 2011 14:57:21 +0200 Subject: KVM: Expose kvm_lapic_local_deliver() Needed to deliver performance monitoring interrupts. Signed-off-by: Avi Kivity Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/lapic.c | 2 +- arch/x86/kvm/lapic.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index a7f3e655cd3e..cfdc6e0ef002 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1121,7 +1121,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu) return 0; } -static int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) +int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = apic_get_reg(apic, lvt_type); int vector, mode, trig_mode; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 138e8cc6fea6..6f4ce2575d09 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -34,6 +34,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu); int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq); +int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); -- cgit v1.2.3 From f5132b01386b5a67f1ff673bb2b96a507a3f7e41 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 10 Nov 2011 14:57:22 +0200 Subject: KVM: Expose a version 2 architectural PMU to a guests Use perf_events to emulate an architectural PMU, version 2. Based on PMU version 1 emulation by Avi Kivity. [avi: adjust for cpuid.c] [jan: fix anonymous field initialization for older gcc] Signed-off-by: Gleb Natapov Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 48 ++++ arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/Makefile | 2 +- arch/x86/kvm/cpuid.c | 2 + arch/x86/kvm/pmu.c | 533 ++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 22 +- include/linux/kvm_host.h | 2 + 7 files changed, 600 insertions(+), 10 deletions(-) create mode 100644 arch/x86/kvm/pmu.c diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 020413afb285..fb60ffdb4e43 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -16,10 +16,12 @@ #include #include #include +#include #include #include #include +#include #include #include @@ -291,6 +293,37 @@ struct kvm_mmu { u64 pdptrs[4]; /* pae */ }; +enum pmc_type { + KVM_PMC_GP = 0, + KVM_PMC_FIXED, +}; + +struct kvm_pmc { + enum pmc_type type; + u8 idx; + u64 counter; + u64 eventsel; + struct perf_event *perf_event; + struct kvm_vcpu *vcpu; +}; + +struct kvm_pmu { + unsigned nr_arch_gp_counters; + unsigned nr_arch_fixed_counters; + unsigned available_event_types; + u64 fixed_ctr_ctrl; + u64 global_ctrl; + u64 global_status; + u64 global_ovf_ctrl; + u64 counter_bitmask[2]; + u64 global_ctrl_mask; + u8 version; + struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC]; + struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED]; + struct irq_work irq_work; + u64 reprogram_pmi; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -424,6 +457,8 @@ struct kvm_vcpu_arch { unsigned access; gfn_t mmio_gfn; + struct kvm_pmu pmu; + /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; @@ -891,4 +926,17 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); +int kvm_is_in_guest(void); + +void kvm_pmu_init(struct kvm_vcpu *vcpu); +void kvm_pmu_destroy(struct kvm_vcpu *vcpu); +void kvm_pmu_reset(struct kvm_vcpu *vcpu); +void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu); +bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr); +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); +void kvm_handle_pmu_event(struct kvm_vcpu *vcpu); +void kvm_deliver_pmi(struct kvm_vcpu *vcpu); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ca4d49ed9a6c..1a7fe868f375 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -35,6 +35,7 @@ config KVM select KVM_MMIO select TASKSTATS select TASK_DELAY_ACCT + select PERF_EVENTS ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 161b76ae87c4..4f579e8dcacf 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o timer.o cpuid.o + i8254.o timer.o cpuid.o pmu.o kvm-intel-y += vmx.o kvm-amd-y += svm.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ca63032bf03d..e70be46f50fc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -45,6 +45,8 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu) else apic->lapic_timer.timer_mode_mask = 1 << 17; } + + kvm_pmu_cpuid_update(vcpu); } static int is_efer_nx(void) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c new file mode 100644 index 000000000000..7aad5446f393 --- /dev/null +++ b/arch/x86/kvm/pmu.c @@ -0,0 +1,533 @@ +/* + * Kernel-based Virtual Machine -- Performane Monitoring Unit support + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Avi Kivity + * Gleb Natapov + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include +#include +#include +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" + +static struct kvm_arch_event_perf_mapping { + u8 eventsel; + u8 unit_mask; + unsigned event_type; + bool inexact; +} arch_events[] = { + /* Index must match CPUID 0x0A.EBX bit vector */ + [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, + [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, + [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, + [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, +}; + +/* mapping between fixed pmc index and arch_events array */ +int fixed_pmc_events[] = {1, 0, 2}; + +static bool pmc_is_gp(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_GP; +} + +static inline u64 pmc_bitmask(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + + return pmu->counter_bitmask[pmc->type]; +} + +static inline bool pmc_enabled(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); +} + +static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, + u32 base) +{ + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) + return &pmu->gp_counters[msr - base]; + return NULL; +} + +static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) +{ + int base = MSR_CORE_PERF_FIXED_CTR0; + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) + return &pmu->fixed_counters[msr - base]; + return NULL; +} + +static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx) +{ + return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx); +} + +static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) +{ + if (idx < X86_PMC_IDX_FIXED) + return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0); + else + return get_fixed_pmc_idx(pmu, idx - X86_PMC_IDX_FIXED); +} + +void kvm_deliver_pmi(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.apic) + kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); +} + +static void trigger_pmi(struct irq_work *irq_work) +{ + struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, + irq_work); + struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu, + arch.pmu); + + kvm_deliver_pmi(vcpu); +} + +static void kvm_perf_overflow(struct perf_event *perf_event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); +} + +static void kvm_perf_overflow_intr(struct perf_event *perf_event, + struct perf_sample_data *data, struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + kvm_perf_overflow(perf_event, data, regs); + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + /* + * Inject PMI. If vcpu was in a guest mode during NMI PMI + * can be ejected on a guest mode re-entry. Otherwise we can't + * be sure that vcpu wasn't executing hlt instruction at the + * time of vmexit and is not going to re-enter guest mode until, + * woken up. So we should wake it, but this is impossible from + * NMI context. Do it from irq work instead. + */ + if (!kvm_is_in_guest()) + irq_work_queue(&pmc->vcpu->arch.pmu.irq_work); + else + kvm_make_request(KVM_REQ_PMI, pmc->vcpu); + } +} + +static u64 read_pmc(struct kvm_pmc *pmc) +{ + u64 counter, enabled, running; + + counter = pmc->counter; + + if (pmc->perf_event) + counter += perf_event_read_value(pmc->perf_event, + &enabled, &running); + + /* FIXME: Scaling needed? */ + + return counter & pmc_bitmask(pmc); +} + +static void stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = read_pmc(pmc); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static void reprogram_counter(struct kvm_pmc *pmc, u32 type, + unsigned config, bool exclude_user, bool exclude_kernel, + bool intr) +{ + struct perf_event *event; + struct perf_event_attr attr = { + .type = type, + .size = sizeof(attr), + .pinned = true, + .exclude_idle = true, + .exclude_host = 1, + .exclude_user = exclude_user, + .exclude_kernel = exclude_kernel, + .config = config, + }; + + attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc); + + event = perf_event_create_kernel_counter(&attr, -1, current, + intr ? kvm_perf_overflow_intr : + kvm_perf_overflow, pmc); + if (IS_ERR(event)) { + printk_once("kvm: pmu event creation failed %ld\n", + PTR_ERR(event)); + return; + } + + pmc->perf_event = event; + clear_bit(pmc->idx, (unsigned long*)&pmc->vcpu->arch.pmu.reprogram_pmi); +} + +static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select, + u8 unit_mask) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(arch_events); i++) + if (arch_events[i].eventsel == event_select + && arch_events[i].unit_mask == unit_mask + && (pmu->available_event_types & (1 << i))) + break; + + if (i == ARRAY_SIZE(arch_events)) + return PERF_COUNT_HW_MAX; + + return arch_events[i].event_type; +} + +static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) +{ + unsigned config, type = PERF_TYPE_RAW; + u8 event_select, unit_mask; + + pmc->eventsel = eventsel; + + stop_counter(pmc); + + if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc)) + return; + + event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; + unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; + + if (!(event_select & (ARCH_PERFMON_EVENTSEL_EDGE | + ARCH_PERFMON_EVENTSEL_INV | + ARCH_PERFMON_EVENTSEL_CMASK))) { + config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, + unit_mask); + if (config != PERF_COUNT_HW_MAX) + type = PERF_TYPE_HARDWARE; + } + + if (type == PERF_TYPE_RAW) + config = eventsel & X86_RAW_EVENT_MASK; + + reprogram_counter(pmc, type, config, + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT); +} + +static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) +{ + unsigned en = en_pmi & 0x3; + bool pmi = en_pmi & 0x8; + + stop_counter(pmc); + + if (!en || !pmc_enabled(pmc)) + return; + + reprogram_counter(pmc, PERF_TYPE_HARDWARE, + arch_events[fixed_pmc_events[idx]].event_type, + !(en & 0x2), /* exclude user */ + !(en & 0x1), /* exclude kernel */ + pmi); +} + +static inline u8 fixed_en_pmi(u64 ctrl, int idx) +{ + return (ctrl >> (idx * 4)) & 0xf; +} + +static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) +{ + int i; + + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { + u8 en_pmi = fixed_en_pmi(data, i); + struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i); + + if (fixed_en_pmi(pmu->fixed_ctr_ctrl, i) == en_pmi) + continue; + + reprogram_fixed_counter(pmc, en_pmi, i); + } + + pmu->fixed_ctr_ctrl = data; +} + +static void reprogram_idx(struct kvm_pmu *pmu, int idx) +{ + struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx); + + if (!pmc) + return; + + if (pmc_is_gp(pmc)) + reprogram_gp_counter(pmc, pmc->eventsel); + else { + int fidx = idx - X86_PMC_IDX_FIXED; + reprogram_fixed_counter(pmc, + fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx); + } +} + +static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +{ + int bit; + u64 diff = pmu->global_ctrl ^ data; + + pmu->global_ctrl = data; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + reprogram_idx(pmu, bit); +} + +bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + int ret; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + ret = pmu->version > 1; + break; + default: + ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) + || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) + || get_fixed_pmc(pmu, msr); + break; + } + return ret; +} + +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc; + + switch (index) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + *data = pmu->fixed_ctr_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_STATUS: + *data = pmu->global_status; + return 0; + case MSR_CORE_PERF_GLOBAL_CTRL: + *data = pmu->global_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + *data = pmu->global_ovf_ctrl; + return 0; + default: + if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, index))) { + *data = read_pmc(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { + *data = pmc->eventsel; + return 0; + } + } + return 1; +} + +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc; + + switch (index) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + if (pmu->fixed_ctr_ctrl == data) + return 0; + if (!(data & 0xfffffffffffff444)) { + reprogram_fixed_counters(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_STATUS: + break; /* RO MSR */ + case MSR_CORE_PERF_GLOBAL_CTRL: + if (pmu->global_ctrl == data) + return 0; + if (!(data & pmu->global_ctrl_mask)) { + global_ctrl_changed(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { + pmu->global_status &= ~data; + pmu->global_ovf_ctrl = data; + return 0; + } + break; + default: + if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, index))) { + data = (s64)(s32)data; + pmc->counter += data - read_pmc(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { + if (data == pmc->eventsel) + return 0; + if (!(data & 0xffffffff00200000ull)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + } + return 1; +} + +int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + bool fast_mode = pmc & (1u << 31); + bool fixed = pmc & (1u << 30); + struct kvm_pmc *counters; + u64 ctr; + + pmc &= (3u << 30) - 1; + if (!fixed && pmc >= pmu->nr_arch_gp_counters) + return 1; + if (fixed && pmc >= pmu->nr_arch_fixed_counters) + return 1; + counters = fixed ? pmu->fixed_counters : pmu->gp_counters; + ctr = read_pmc(&counters[pmc]); + if (fast_mode) + ctr = (u32)ctr; + *data = ctr; + + return 0; +} + +void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_cpuid_entry2 *entry; + unsigned bitmap_len; + + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->version = 0; + + entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + if (!entry) + return; + + pmu->version = entry->eax & 0xff; + if (!pmu->version) + return; + + pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff, + X86_PMC_MAX_GENERIC); + pmu->counter_bitmask[KVM_PMC_GP] = + ((u64)1 << ((entry->eax >> 16) & 0xff)) - 1; + bitmap_len = (entry->eax >> 24) & 0xff; + pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1); + + if (pmu->version == 1) { + pmu->global_ctrl = (1 << pmu->nr_arch_gp_counters) - 1; + return; + } + + pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f), + X86_PMC_MAX_FIXED); + pmu->counter_bitmask[KVM_PMC_FIXED] = + ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1; + pmu->global_ctrl_mask = ~(((1 << pmu->nr_arch_gp_counters) - 1) + | (((1ull << pmu->nr_arch_fixed_counters) - 1) + << X86_PMC_IDX_FIXED)); +} + +void kvm_pmu_init(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + + memset(pmu, 0, sizeof(*pmu)); + for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } + for (i = 0; i < X86_PMC_MAX_FIXED; i++) { + pmu->fixed_counters[i].type = KVM_PMC_FIXED; + pmu->fixed_counters[i].vcpu = vcpu; + pmu->fixed_counters[i].idx = i + X86_PMC_IDX_FIXED; + } + init_irq_work(&pmu->irq_work, trigger_pmi); + kvm_pmu_cpuid_update(vcpu); +} + +void kvm_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + int i; + + irq_work_sync(&pmu->irq_work); + for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } + + for (i = 0; i < X86_PMC_MAX_FIXED; i++) + stop_counter(&pmu->fixed_counters[i]); + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = + pmu->global_ovf_ctrl = 0; +} + +void kvm_pmu_destroy(struct kvm_vcpu *vcpu) +{ + kvm_pmu_reset(vcpu); +} + +void kvm_handle_pmu_event(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + u64 bitmask; + int bit; + + bitmask = pmu->reprogram_pmi; + + for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit); + + if (unlikely(!pmc || !pmc->perf_event)) { + clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + continue; + } + + reprogram_idx(pmu, bit); + } +} diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0a646e2b57c5..08ae951ecc5c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1602,8 +1602,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) * which we perfectly emulate ;-). Any other value should be at least * reported, some guests depend on them. */ - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: case MSR_K7_EVNTSEL0: case MSR_K7_EVNTSEL1: case MSR_K7_EVNTSEL2: @@ -1615,8 +1613,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* at least RHEL 4 unconditionally writes to the perfctr registers, * so we ignore writes to make it happy. */ - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: case MSR_K7_PERFCTR0: case MSR_K7_PERFCTR1: case MSR_K7_PERFCTR2: @@ -1653,6 +1649,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr, data); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); @@ -1815,10 +1813,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_K8_SYSCFG: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: case MSR_K7_EVNTSEL0: case MSR_K7_PERFCTR0: case MSR_K8_INT_PENDING_MSG: @@ -1929,6 +1923,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = 0xbe702111; break; default: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_get_msr(vcpu, msr, pdata); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); return 1; @@ -4650,7 +4646,7 @@ static void kvm_timer_init(void) static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); -static int kvm_is_in_guest(void) +int kvm_is_in_guest(void) { return __this_cpu_read(current_vcpu) != NULL; } @@ -5114,6 +5110,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) process_nmi(vcpu); req_immediate_exit = kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_handle_pmu_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_deliver_pmi(vcpu); } r = kvm_mmu_reload(vcpu); @@ -5850,6 +5850,8 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; + kvm_pmu_reset(vcpu); + return kvm_x86_ops->vcpu_reset(vcpu); } @@ -5934,6 +5936,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_mce_banks; kvm_async_pf_hash_reset(vcpu); + kvm_pmu_init(vcpu); return 0; fail_free_mce_banks: @@ -5952,6 +5955,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { int idx; + kvm_pmu_destroy(vcpu); kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7a080383935f..900c76337e8f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -52,6 +52,8 @@ #define KVM_REQ_STEAL_UPDATE 13 #define KVM_REQ_NMI 14 #define KVM_REQ_IMMEDIATE_EXIT 15 +#define KVM_REQ_PMU 16 +#define KVM_REQ_PMI 17 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 -- cgit v1.2.3 From 022cd0e84020eec8b589bc119699c935c7b29584 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 10 Nov 2011 14:57:23 +0200 Subject: KVM: Add generic RDPMC support Add a helper function that emulates the RDPMC instruction operation. Signed-off-by: Avi Kivity Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index fb60ffdb4e43..52d6640a5ca1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -760,6 +760,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); +bool kvm_rdpmc(struct kvm_vcpu *vcpu); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 08ae951ecc5c..27d18b7617f3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -760,6 +760,21 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) } EXPORT_SYMBOL_GPL(kvm_get_dr); +bool kvm_rdpmc(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + u64 data; + int err; + + err = kvm_pmu_read_pmc(vcpu, ecx, &data); + if (err) + return err; + kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); + kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32); + return err; +} +EXPORT_SYMBOL_GPL(kvm_rdpmc); + /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. -- cgit v1.2.3 From 332b56e4841ef62db4dbf1b4b92195575e1c7338 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 10 Nov 2011 14:57:24 +0200 Subject: KVM: SVM: Intercept RDPMC Intercept RDPMC and forward it to the PMU emulation code. Signed-off-by: Avi Kivity Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/svm.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e32243eac2f4..5fa553babe56 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1014,6 +1014,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_NMI); set_intercept(svm, INTERCEPT_SMI); set_intercept(svm, INTERCEPT_SELECTIVE_CR0); + set_intercept(svm, INTERCEPT_RDPMC); set_intercept(svm, INTERCEPT_CPUID); set_intercept(svm, INTERCEPT_INVD); set_intercept(svm, INTERCEPT_HLT); @@ -2770,6 +2771,19 @@ static int emulate_on_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } +static int rdpmc_interception(struct vcpu_svm *svm) +{ + int err; + + if (!static_cpu_has(X86_FEATURE_NRIPS)) + return emulate_on_interception(svm); + + err = kvm_rdpmc(&svm->vcpu); + kvm_complete_insn_gp(&svm->vcpu, err); + + return 1; +} + bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) { unsigned long cr0 = svm->vcpu.arch.cr0; @@ -3190,6 +3204,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_SMI] = nop_on_interception, [SVM_EXIT_INIT] = nop_on_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, + [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, -- cgit v1.2.3 From fee84b079d5ddee2247b5c1f53162c330c622902 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 10 Nov 2011 14:57:25 +0200 Subject: KVM: VMX: Intercept RDPMC Intercept RDPMC and forward it to the PMU emulation code. Signed-off-by: Avi Kivity Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4ceced2669ef..906a7e84200f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1956,6 +1956,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) #endif CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | + CPU_BASED_RDPMC_EXITING | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the @@ -2410,7 +2411,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) CPU_BASED_USE_TSC_OFFSETING | CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING | - CPU_BASED_INVLPG_EXITING; + CPU_BASED_INVLPG_EXITING | + CPU_BASED_RDPMC_EXITING; if (yield_on_hlt) min |= CPU_BASED_HLT_EXITING; @@ -4613,6 +4615,16 @@ static int handle_invlpg(struct kvm_vcpu *vcpu) return 1; } +static int handle_rdpmc(struct kvm_vcpu *vcpu) +{ + int err; + + err = kvm_rdpmc(vcpu); + kvm_complete_insn_gp(vcpu, err); + + return 1; +} + static int handle_wbinvd(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); @@ -5563,6 +5575,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_HLT] = handle_halt, [EXIT_REASON_INVD] = handle_invd, [EXIT_REASON_INVLPG] = handle_invlpg, + [EXIT_REASON_RDPMC] = handle_rdpmc, [EXIT_REASON_VMCALL] = handle_vmcall, [EXIT_REASON_VMCLEAR] = handle_vmclear, [EXIT_REASON_VMLAUNCH] = handle_vmlaunch, -- cgit v1.2.3 From a6c06ed1a60aff77b27ba558c315c3fed4e35565 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 10 Nov 2011 14:57:28 +0200 Subject: KVM: Expose the architectural performance monitoring CPUID leaf Provide a CPUID leaf that describes the emulated PMU. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/cpuid.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index e70be46f50fc..89b02bfaaca5 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -327,6 +327,35 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } case 9: break; + case 0xa: { /* Architectural Performance Monitoring */ + struct x86_pmu_capability cap; + union cpuid10_eax eax; + union cpuid10_edx edx; + + perf_get_x86_pmu_capability(&cap); + + /* + * Only support guest architectural pmu on a host + * with architectural pmu. + */ + if (!cap.version) + memset(&cap, 0, sizeof(cap)); + + eax.split.version_id = min(cap.version, 2); + eax.split.num_counters = cap.num_counters_gp; + eax.split.bit_width = cap.bit_width_gp; + eax.split.mask_length = cap.events_mask_len; + + edx.split.num_counters_fixed = cap.num_counters_fixed; + edx.split.bit_width_fixed = cap.bit_width_fixed; + edx.split.reserved = 0; + + entry->eax = eax.full; + entry->ebx = cap.events_mask; + entry->ecx = 0; + entry->edx = edx.full; + break; + } /* function 0xb has additional index. */ case 0xb: { int i, level_type; @@ -427,7 +456,6 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ case 6: /* Thermal management */ - case 0xA: /* Architectural Performance Monitoring */ case 0x80000007: /* Advanced power management */ case 0xC0000002: case 0xC0000003: -- cgit v1.2.3 From 80bdec64c05b645708b0dd97919783ad077fcdc8 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 10 Nov 2011 14:57:29 +0200 Subject: KVM: x86 emulator: fix RDPMC privilege check RDPMC is only privileged if CR4.PCE=0. check_rdpmc() already implements this, so all we need to do is drop the Priv flag. Signed-off-by: Avi Kivity Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index de7be77820d5..d270f1a817dc 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3411,7 +3411,7 @@ static struct opcode twobyte_table[256] = { II(ImplicitOps | Priv, em_wrmsr, wrmsr), IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), II(ImplicitOps | Priv, em_rdmsr, rdmsr), - DIP(ImplicitOps | Priv, rdpmc, check_rdpmc), + DIP(ImplicitOps, rdpmc, check_rdpmc), I(ImplicitOps | VendorSpecific, em_sysenter), I(ImplicitOps | Priv | VendorSpecific, em_sysexit), N, N, -- cgit v1.2.3 From 222d21aa070a4885ce3c7125a1b7ce07429ea4a1 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 10 Nov 2011 14:57:30 +0200 Subject: KVM: x86 emulator: implement RDPMC (0F 33) Signed-off-by: Avi Kivity Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_emulate.h | 1 + arch/x86/kvm/emulate.c | 13 ++++++++++++- arch/x86/kvm/x86.c | 7 +++++++ 3 files changed, 20 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 9a4acf41709c..ab4092e3214e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -181,6 +181,7 @@ struct x86_emulate_ops { int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); + int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata); void (*halt)(struct x86_emulate_ctxt *ctxt); void (*wbinvd)(struct x86_emulate_ctxt *ctxt); int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d270f1a817dc..05a562b85025 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2645,6 +2645,17 @@ static int em_rdtsc(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_rdpmc(struct x86_emulate_ctxt *ctxt) +{ + u64 pmc; + + if (ctxt->ops->read_pmc(ctxt, ctxt->regs[VCPU_REGS_RCX], &pmc)) + return emulate_gp(ctxt, 0); + ctxt->regs[VCPU_REGS_RAX] = (u32)pmc; + ctxt->regs[VCPU_REGS_RDX] = pmc >> 32; + return X86EMUL_CONTINUE; +} + static int em_mov(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = ctxt->src.val; @@ -3411,7 +3422,7 @@ static struct opcode twobyte_table[256] = { II(ImplicitOps | Priv, em_wrmsr, wrmsr), IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), II(ImplicitOps | Priv, em_rdmsr, rdmsr), - DIP(ImplicitOps, rdpmc, check_rdpmc), + IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc), I(ImplicitOps | VendorSpecific, em_sysenter), I(ImplicitOps | Priv | VendorSpecific, em_sysexit), N, N, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 27d18b7617f3..1171def5f96b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4146,6 +4146,12 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); } +static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, + u32 pmc, u64 *pdata) +{ + return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata); +} + static void emulator_halt(struct x86_emulate_ctxt *ctxt) { emul_to_vcpu(ctxt)->arch.halt_request = 1; @@ -4198,6 +4204,7 @@ static struct x86_emulate_ops emulate_ops = { .set_dr = emulator_set_dr, .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, + .read_pmc = emulator_read_pmc, .halt = emulator_halt, .wbinvd = emulator_wbinvd, .fix_hypercall = emulator_fix_hypercall, -- cgit v1.2.3 From 6c9b7c409ca2840ba589a869c48e641b40966e30 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Mon, 7 Nov 2011 13:29:56 +0000 Subject: KVM: PPC: annotate kvm_rma_init as __init kvm_rma_init() is only called at boot-time, by setup_arch, which is also __init. Signed-off-by: Nishanth Aravamudan Signed-off-by: Alexander Graf --- arch/powerpc/kvm/book3s_hv_builtin.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 286f13d601cf..a795a13f4a70 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -86,7 +86,7 @@ static inline int lpcr_rmls(unsigned long rma_size) * to allocate contiguous physical memory for the real memory * areas for guests. */ -void kvm_rma_init(void) +void __init kvm_rma_init(void) { unsigned long i; unsigned long j, npages; -- cgit v1.2.3 From 98362dec835218206fdb55212667040d23d3a440 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 19 Sep 2011 13:25:22 +0200 Subject: KVM: Fix whitespace in kvm_para.h When syncing KVM headers with QEMU I (or whoever applies the diff) end up automatically fixing whitespaces. One of them is in kvm_para.h. It's a lot more consistent for people who don't do the whitespace fixups automatically to already have fixed headers in Linux. So remove the sparse empty line at the end of kvm_para.h and everyone's happy. Reported-by: Blue Swirl Signed-off-by: Alexander Graf --- include/linux/kvm_para.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index 47a070b0520e..ff476ddaf310 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -35,4 +35,3 @@ static inline int kvm_para_has_feature(unsigned int feature) } #endif /* __KERNEL__ */ #endif /* __LINUX_KVM_PARA_H */ - -- cgit v1.2.3 From da69dee073a27ee2d4e50c9b19e9faf8776857eb Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 19 Sep 2011 13:24:10 +0200 Subject: KVM: PPC: Whitespace fix for kvm.h kvm.h had sparse whitespace at the end of the line. Clean it up so syncing with QEMU gets easier. Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index 0ad432bc81d6..f7727d91ac6b 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -170,8 +170,8 @@ struct kvm_sregs { } ppc64; struct { __u32 sr[16]; - __u64 ibat[8]; - __u64 dbat[8]; + __u64 ibat[8]; + __u64 dbat[8]; } ppc32; } s; struct { -- cgit v1.2.3