diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2011-10-30 15:36:45 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-10-30 15:36:45 -0700 |
commit | 1bc87b00556e8f7ba30a1010471951c5b8f71114 (patch) | |
tree | e73c2d187e2dff0df97ed82e32b45e362b923117 /arch/x86 | |
parent | acff987d94cbdb4049f3706bed1f1792f8ef6837 (diff) | |
parent | f1c1da2bde712812a3e0f9a7a7ebe7a916a4b5f4 (diff) |
Merge branch 'kvm-updates/3.2' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm
* 'kvm-updates/3.2' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (75 commits)
KVM: SVM: Keep intercepting task switching with NPT enabled
KVM: s390: implement sigp external call
KVM: s390: fix register setting
KVM: s390: fix return value of kvm_arch_init_vm
KVM: s390: check cpu_id prior to using it
KVM: emulate lapic tsc deadline timer for guest
x86: TSC deadline definitions
KVM: Fix simultaneous NMIs
KVM: x86 emulator: convert push %sreg/pop %sreg to direct decode
KVM: x86 emulator: switch lds/les/lss/lfs/lgs to direct decode
KVM: x86 emulator: streamline decode of segment registers
KVM: x86 emulator: simplify OpMem64 decode
KVM: x86 emulator: switch src decode to decode_operand()
KVM: x86 emulator: qualify OpReg inhibit_byte_regs hack
KVM: x86 emulator: switch OpImmUByte decode to decode_imm()
KVM: x86 emulator: free up some flag bits near src, dst
KVM: x86 emulator: switch src2 to generic decode_operand()
KVM: x86 emulator: expand decode flags to 64 bits
KVM: x86 emulator: split dst decode to a generic decode_operand()
KVM: x86 emulator: move memop, memopp into emulation context
...
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/include/asm/apicdef.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/cpufeature.h | 1 | ||||
-rw-r--r-- | arch/x86/include/asm/kvm_emulate.h | 4 | ||||
-rw-r--r-- | arch/x86/include/asm/kvm_host.h | 14 | ||||
-rw-r--r-- | arch/x86/include/asm/msr-index.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/vmx.h | 12 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 867 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.c | 6 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 123 | ||||
-rw-r--r-- | arch/x86/kvm/irq.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_cache_regs.h | 7 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_timer.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 167 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 5 | ||||
-rw-r--r-- | arch/x86/kvm/mmu_audit.c | 6 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 24 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 93 | ||||
-rw-r--r-- | arch/x86/kvm/trace.h | 118 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 131 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 274 |
21 files changed, 1095 insertions, 771 deletions
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 34595d5e103..3925d800786 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -100,7 +100,9 @@ #define APIC_TIMER_BASE_CLKIN 0x0 #define APIC_TIMER_BASE_TMBASE 0x1 #define APIC_TIMER_BASE_DIV 0x2 +#define APIC_LVT_TIMER_ONESHOT (0 << 17) #define APIC_LVT_TIMER_PERIODIC (1 << 17) +#define APIC_LVT_TIMER_TSCDEADLINE (2 << 17) #define APIC_LVT_MASKED (1 << 16) #define APIC_LVT_LEVEL_TRIGGER (1 << 15) #define APIC_LVT_REMOTE_IRR (1 << 14) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index aa6a488cd07..2f84a433b6a 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -121,6 +121,7 @@ #define X86_FEATURE_X2APIC (4*32+21) /* x2APIC */ #define X86_FEATURE_MOVBE (4*32+22) /* MOVBE instruction */ #define X86_FEATURE_POPCNT (4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER (4*32+24) /* Tsc deadline timer */ #define X86_FEATURE_AES (4*32+25) /* AES instructions */ #define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 6040d115ef5..a026507893e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -262,7 +262,7 @@ struct x86_emulate_ctxt { struct operand dst; bool has_seg_override; u8 seg_override; - unsigned int d; + u64 d; int (*execute)(struct x86_emulate_ctxt *ctxt); int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* modrm */ @@ -275,6 +275,8 @@ struct x86_emulate_ctxt { unsigned long _eip; /* Fields above regs are cleared together. */ unsigned long regs[NR_VCPU_REGS]; + struct operand memop; + struct operand *memopp; struct fetch_cache fetch; struct read_cache io_read; struct read_cache mem_read; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd51c83aa5d..b4973f4dab9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -26,7 +26,8 @@ #include <asm/mtrr.h> #include <asm/msr-index.h> -#define KVM_MAX_VCPUS 64 +#define KVM_MAX_VCPUS 254 +#define KVM_SOFT_MAX_VCPUS 64 #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 @@ -264,6 +265,7 @@ struct kvm_mmu { void (*new_cr3)(struct kvm_vcpu *vcpu); void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); + u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, @@ -411,8 +413,9 @@ struct kvm_vcpu_arch { u32 tsc_catchup_mult; s8 tsc_catchup_shift; - bool nmi_pending; - bool nmi_injected; + atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ + unsigned nmi_pending; /* NMI queued after currently running handler */ + bool nmi_injected; /* Trying to inject an NMI this entry */ struct mtrr_state_type mtrr_state; u32 pat; @@ -628,14 +631,13 @@ struct kvm_x86_ops { void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); + u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage); - - const struct trace_print_flags *exit_reasons_str; }; struct kvm_arch_async_pf { @@ -672,6 +674,8 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); extern bool tdp_enabled; +u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); + /* control of guest tsc rate supported? */ extern bool kvm_has_tsc_control; /* minimum supported tsc_khz for guests */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d52609aeeab..a6962d9161a 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -229,6 +229,8 @@ #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define MSR_IA32_TSCDEADLINE 0x000006e0 + #define MSR_IA32_UCODE_WRITE 0x00000079 #define MSR_IA32_UCODE_REV 0x0000008b diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2caf290e989..31f180c21ce 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -350,6 +350,18 @@ enum vmcs_field { #define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */ +/* + * Exit Qualifications for APIC-Access + */ +#define APIC_ACCESS_OFFSET 0xfff /* 11:0, offset within the APIC page */ +#define APIC_ACCESS_TYPE 0xf000 /* 15:12, access type */ +#define TYPE_LINEAR_APIC_INST_READ (0 << 12) +#define TYPE_LINEAR_APIC_INST_WRITE (1 << 12) +#define TYPE_LINEAR_APIC_INST_FETCH (2 << 12) +#define TYPE_LINEAR_APIC_EVENT (3 << 12) +#define TYPE_PHYSICAL_APIC_EVENT (10 << 12) +#define TYPE_PHYSICAL_APIC_INST (15 << 12) + /* segment AR */ #define SEGMENT_AR_L_MASK (1 << 13) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8b4cc5f067d..f1e3be18a08 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -29,6 +29,39 @@ #include "tss.h" /* + * Operand types + */ +#define OpNone 0ull +#define OpImplicit 1ull /* No generic decode */ +#define OpReg 2ull /* Register */ +#define OpMem 3ull /* Memory */ +#define OpAcc 4ull /* Accumulator: AL/AX/EAX/RAX */ +#define OpDI 5ull /* ES:DI/EDI/RDI */ +#define OpMem64 6ull /* Memory, 64-bit */ +#define OpImmUByte 7ull /* Zero-extended 8-bit immediate */ +#define OpDX 8ull /* DX register */ +#define OpCL 9ull /* CL register (for shifts) */ +#define OpImmByte 10ull /* 8-bit sign extended immediate */ +#define OpOne 11ull /* Implied 1 */ +#define OpImm 12ull /* Sign extended immediate */ +#define OpMem16 13ull /* Memory operand (16-bit). */ +#define OpMem32 14ull /* Memory operand (32-bit). */ +#define OpImmU 15ull /* Immediate operand, zero extended */ +#define OpSI 16ull /* SI/ESI/RSI */ +#define OpImmFAddr 17ull /* Immediate far address */ +#define OpMemFAddr 18ull /* Far address in memory */ +#define OpImmU16 19ull /* Immediate operand, 16 bits, zero extended */ +#define OpES 20ull /* ES */ +#define OpCS 21ull /* CS */ +#define OpSS 22ull /* SS */ +#define OpDS 23ull /* DS */ +#define OpFS 24ull /* FS */ +#define OpGS 25ull /* GS */ + +#define OpBits 5 /* Width of operand field */ +#define OpMask ((1ull << OpBits) - 1) + +/* * Opcode effective-address decode tables. * Note that we only emulate instructions that have at least one memory * operand (excluding implicit stack references). We assume that stack @@ -40,37 +73,35 @@ /* Operand sizes: 8-bit operands or specified/overridden size. */ #define ByteOp (1<<0) /* 8-bit operands. */ /* Destination operand type. */ -#define ImplicitOps (1<<1) /* Implicit in opcode. No generic decode. */ -#define DstReg (2<<1) /* Register operand. */ -#define DstMem (3<<1) /* Memory operand. */ -#define DstAcc (4<<1) /* Destination Accumulator */ -#define DstDI (5<<1) /* Destination is in ES:(E)DI */ -#define DstMem64 (6<<1) /* 64bit memory operand */ -#define DstImmUByte (7<<1) /* 8-bit unsigned immediate operand */ -#define DstDX (8<<1) /* Destination is in DX register */ -#define DstMask (0xf<<1) +#define DstShift 1 +#define ImplicitOps (OpImplicit << DstShift) +#define DstReg (OpReg << DstShift) +#define DstMem (OpMem << DstShift) +#define DstAcc (OpAcc << DstShift) +#define DstDI (OpDI << DstShift) +#define DstMem64 (OpMem64 << DstShift) +#define DstImmUByte (OpImmUByte << DstShift) +#define DstDX (OpDX << DstShift) +#define DstMask (OpMask << DstShift) /* Source operand type. */ -#define SrcNone (0<<5) /* No source operand. */ -#define SrcReg (1<<5) /* Register operand. */ -#define SrcMem (2<<5) /* Memory operand. */ -#define SrcMem16 (3<<5) /* Memory operand (16-bit). */ -#define SrcMem32 (4<<5) /* Memory operand (32-bit). */ -#define SrcImm (5<<5) /* Immediate operand. */ -#define SrcImmByte (6<<5) /* 8-bit sign-extended immediate operand. */ -#define SrcOne (7<<5) /* Implied '1' */ -#define SrcImmUByte (8<<5) /* 8-bit unsigned immediate operand. */ -#define SrcImmU (9<<5) /* Immediate operand, unsigned */ -#define SrcSI (0xa<<5) /* Source is in the DS:RSI */ -#define SrcImmFAddr (0xb<<5) /* Source is immediate far address */ -#define SrcMemFAddr (0xc<<5) /* Source is far address in memory */ -#define SrcAcc (0xd<<5) /* Source Accumulator */ -#define SrcImmU16 (0xe<<5) /* Immediate operand, unsigned, 16 bits */ -#define SrcDX (0xf<<5) /* Source is in DX register */ -#define SrcMask (0xf<<5) -/* Generic ModRM decode. */ -#define ModRM (1<<9) -/* Destination is only written; never read. */ -#define Mov (1<<10) +#define SrcShift 6 +#define SrcNone (OpNone << SrcShift) +#define SrcReg (OpReg << SrcShift) +#define SrcMem (OpMem << SrcShift) +#define SrcMem16 (OpMem16 << SrcShift) +#define SrcMem32 (OpMem32 << SrcShift) +#define SrcImm (OpImm << SrcShift) +#define SrcImmByte (OpImmByte << SrcShift) +#define SrcOne (OpOne << SrcShift) +#define SrcImmUByte (OpImmUByte << SrcShift) +#define SrcImmU (OpImmU << SrcShift) +#define SrcSI (OpSI << SrcShift) +#define SrcImmFAddr (OpImmFAddr << SrcShift) +#define SrcMemFAddr (OpMemFAddr << SrcShift) +#define SrcAcc (OpAcc << SrcShift) +#define SrcImmU16 (OpImmU16 << SrcShift) +#define SrcDX (OpDX << SrcShift) +#define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) #define MemAbs (1<<12) /* Memory operand is absolute displacement */ #define String (1<<13) /* String instruction (rep capable) */ @@ -81,6 +112,10 @@ #define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */ #define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */ #define Sse (1<<18) /* SSE Vector instruction */ +/* Generic ModRM decode. */ +#define ModRM (1<<19) +/* Destination is only written; never read. */ +#define Mov (1<<20) /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define VendorSpecific (1<<22) /* Vendor specific instruction */ @@ -91,12 +126,19 @@ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) /* Source 2 operand type */ -#define Src2None (0<<29) -#define Src2CL (1<<29) -#define Src2ImmByte (2<<29) -#define Src2One (3<<29) -#define Src2Imm (4<<29) -#define Src2Mask (7<<29) +#define Src2Shift (29) +#define Src2None (OpNone << Src2Shift) +#define Src2CL (OpCL << Src2Shift) +#define Src2ImmByte (OpImmByte << Src2Shift) +#define Src2One (OpOne << Src2Shift) +#define Src2Imm (OpImm << Src2Shift) +#define Src2ES (OpES << Src2Shift) +#define Src2CS (OpCS << Src2Shift) +#define Src2SS (OpSS << Src2Shift) +#define Src2DS (OpDS << Src2Shift) +#define Src2FS (OpFS << Src2Shift) +#define Src2GS (OpGS << Src2Shift) +#define Src2Mask (OpMask << Src2Shift) #define X2(x...) x, x #define X3(x...) X2(x), x @@ -108,8 +150,8 @@ #define X16(x...) X8(x), X8(x) struct opcode { - u32 flags; - u8 intercept; + u64 flags : 56; + u64 intercept : 8; union { int (*execute)(struct x86_emulate_ctxt *ctxt); struct opcode *group; @@ -205,105 +247,100 @@ struct gprefix { #define ON64(x) #endif -#define ____emulate_2op(_op, _src, _dst, _eflags, _x, _y, _suffix, _dsttype) \ +#define ____emulate_2op(ctxt, _op, _x, _y, _suffix, _dsttype) \ do { \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "4", "2") \ _op _suffix " %"_x"3,%1; " \ _POST_EFLAGS("0", "4", "2") \ - : "=m" (_eflags), "+q" (*(_dsttype*)&(_dst).val),\ + : "=m" ((ctxt)->eflags), \ + "+q" (*(_dsttype*)&(ctxt)->dst.val), \ "=&r" (_tmp) \ - : _y ((_src).val), "i" (EFLAGS_MASK)); \ + : _y ((ctxt)->src.val), "i" (EFLAGS_MASK)); \ } while (0) /* Raw emulation: instruction has two explicit operands. */ -#define __emulate_2op_nobyte(_op,_src,_dst,_eflags,_wx,_wy,_lx,_ly,_qx,_qy) \ +#define __emulate_2op_nobyte(ctxt,_op,_wx,_wy,_lx,_ly,_qx,_qy) \ do { \ unsigned long _tmp; \ \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 2: \ - ____emulate_2op(_op,_src,_dst,_eflags,_wx,_wy,"w",u16);\ + ____emulate_2op(ctxt,_op,_wx,_wy,"w",u16); \ break; \ case 4: \ - ____emulate_2op(_op,_src,_dst,_eflags,_lx,_ly,"l",u32);\ + ____emulate_2op(ctxt,_op,_lx,_ly,"l",u32); \ break; \ case 8: \ - ON64(____emulate_2op(_op,_src,_dst,_eflags,_qx,_qy,"q",u64)); \ + ON64(____emulate_2op(ctxt,_op,_qx,_qy,"q",u64)); \ break; \ } \ } while (0) -#define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ +#define __emulate_2op(ctxt,_op,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ do { \ unsigned long _tmp; \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 1: \ - ____emulate_2op(_op,_src,_dst,_eflags,_bx,_by,"b",u8); \ + ____emulate_2op(ctxt,_op,_bx,_by,"b",u8); \ break; \ default: \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ + __emulate_2op_nobyte(ctxt, _op, \ _wx, _wy, _lx, _ly, _qx, _qy); \ break; \ } \ } while (0) /* Source operand is byte-sized and may be restricted to just %cl. */ -#define emulate_2op_SrcB(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "c", "b", "c", "b", "c", "b", "c") +#define emulate_2op_SrcB(ctxt, _op) \ + __emulate_2op(ctxt, _op, "b", "c", "b", "c", "b", "c", "b", "c") /* Source operand is byte, word, long or quad sized. */ -#define emulate_2op_SrcV(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "q", "w", "r", _LO32, "r", "", "r") +#define emulate_2op_SrcV(ctxt, _op) \ + __emulate_2op(ctxt, _op, "b", "q", "w", "r", _LO32, "r", "", "r") /* Source operand is word, long or quad sized. */ -#define emulate_2op_SrcV_nobyte(_op, _src, _dst, _eflags) \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ - "w", "r", _LO32, "r", "", "r") +#define emulate_2op_SrcV_nobyte(ctxt, _op) \ + __emulate_2op_nobyte(ctxt, _op, "w", "r", _LO32, "r", "", "r") /* Instruction has three operands and one operand is stored in ECX register */ -#define __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, _suffix, _type) \ +#define __emulate_2op_cl(ctxt, _op, _suffix, _type) \ do { \ unsigned long _tmp; \ - _type _clv = (_cl).val; \ - _type _srcv = (_src).val; \ - _type _dstv = (_dst).val; \ + _type _clv = (ctxt)->src2.val; \ + _type _srcv = (ctxt)->src.val; \ + _type _dstv = (ctxt)->dst.val; \ \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "5", "2") \ _op _suffix " %4,%1 \n" \ _POST_EFLAGS("0", "5", "2") \ - : "=m" (_eflags), "+r" (_dstv), "=&r" (_tmp) \ + : "=m" ((ctxt)->eflags), "+r" (_dstv), "=&r" (_tmp) \ : "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK) \ ); \ \ - (_cl).val = (unsigned long) _clv; \ - (_src).val = (unsigned long) _srcv; \ - (_dst).val = (unsigned long) _dstv; \ + (ctxt)->src2.val = (unsigned long) _clv; \ + (ctxt)->src2.val = (unsigned long) _srcv; \ + (ctxt)->dst.val = (unsigned long) _dstv; \ } while (0) -#define emulate_2op_cl(_op, _cl, _src, _dst, _eflags) \ +#define emulate_2op_cl(ctxt, _op) \ do { \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 2: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "w", unsigned short); \ + __emulate_2op_cl(ctxt, _op, "w", u16); \ break; \ case 4: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "l", unsigned int); \ + __emulate_2op_cl(ctxt, _op, "l", u32); \ break; \ case 8: \ - ON64(__emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "q", unsigned long)); \ + ON64(__emulate_2op_cl(ctxt, _op, "q", ulong)); \ break; \ } \ } while (0) -#define __emulate_1op(_op, _dst, _eflags, _suffix) \ +#define __emulate_1op(ctxt, _op, _suffix) \ do { \ unsigned long _tmp; \ \ @@ -311,39 +348,27 @@ struct gprefix { _PRE_EFLAGS("0", "3", "2") \ _op _suffix " %1; " \ _POST_EFLAGS("0", "3", "2") \ - : "=m" (_eflags), "+m" ((_dst).val), \ + : "=m" ((ctxt)->eflags), "+m" ((ctxt)->dst.val), \ "=&r" (_tmp) \ : "i" (EFLAGS_MASK)); \ } while (0) /* Instruction has only one explicit operand (no source operand). */ -#define emulate_1op(_op, _dst, _eflags) \ +#define emulate_1op(ctxt, _op) \ do { \ - switch ((_dst).bytes) { \ - case 1: __emulate_1op(_op, _dst, _eflags, "b"); break; \ - case 2: __emulate_1op(_op, _dst, _eflags, "w"); break; \ - case 4: __emulate_1op(_op, _dst, _eflags, "l"); break; \ - case 8: ON64(__emulate_1op(_op, _dst, _eflags, "q")); break; \ + switch ((ctxt)->dst.bytes) { \ + case 1: __emulate_1op(ctxt, _op, "b"); break; \ + case 2: __emulate_1op(ctxt, _op, "w"); break; \ + case 4: __emulate_1op(ctxt, _op, "l"); break; \ + case 8: ON64(__emulate_1op(ctxt, _op, "q")); break; \ } \ } while (0) -#define __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags, _suffix) \ - do { \ - unsigned long _tmp; \ - \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "4", "1") \ - _op _suffix " %5; " \ - _POST_EFLAGS("0", "4", "1") \ - : "=m" (_eflags), "=&r" (_tmp), \ - "+a" (_rax), "+d" (_rdx) \ - : "i" (EFLAGS_MASK), "m" ((_src).val), \ - "a" (_rax), "d" (_rdx)); \ - } while (0) - -#define __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, _eflags, _suffix, _ex) \ +#define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex) \ do { \ unsigned long _tmp; \ + ulong *rax = &(ctxt)->regs[VCPU_REGS_RAX]; \ + ulong *rdx = &(ctxt)->regs[VCPU_REGS_RDX]; \ \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "5", "1") \ @@ -356,53 +381,27 @@ struct gprefix { "jmp 2b \n\t" \ ".popsection \n\t" \ _ASM_EXTABLE(1b, 3b) \ - : "=m" (_eflags), "=&r" (_tmp), \ - "+a" (_rax), "+d" (_rdx), "+qm"(_ex) \ - : "i" (EFLAGS_MASK), "m" ((_src).val), \ - "a" (_rax), "d" (_rdx)); \ + : "=m" ((ctxt)->eflags), "=&r" (_tmp), \ + "+a" (*rax), "+d" (*rdx), "+qm"(_ex) \ + : "i" (EFLAGS_MASK), "m" ((ctxt)->src.val), \ + "a" (*rax), "d" (*rdx)); \ } while (0) /* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */ -#define emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags) \ +#define emulate_1op_rax_rdx(ctxt, _op, _ex) \ do { \ - switch((_src).bytes) { \ + switch((ctxt)->src.bytes) { \ case 1: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "b"); \ + __emulate_1op_rax_rdx(ctxt, _op, "b", _ex); \ break; \ case 2: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "w"); \ + __emulate_1op_rax_rdx(ctxt, _op, "w", _ex); \ break; \ case 4: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "l"); \ - break; \ - case 8: \ - ON64(__emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "q")); \ - break; \ - } \ - } while (0) - -#define emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, _eflags, _ex) \ - do { \ - switch((_src).bytes) { \ - case 1: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "b", _ex); \ - break; \ - case 2: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "w", _ex); \ - break; \ - case 4: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "l", _ex); \ + __emulate_1op_rax_rdx(ctxt, _op, "l", _ex); \ break; \ case 8: ON64( \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "q", _ex)); \ + __emulate_1op_rax_rdx(ctxt, _op, "q", _ex)); \ break; \ } \ } while (0) @@ -651,41 +650,50 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt, return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception); } -static int do_insn_fetch_byte(struct x86_emulate_ctxt *ctxt, - unsigned long eip, u8 *dest) +/* + * Fetch the next byte of the instruction being emulated which is pointed to + * by ctxt->_eip, then increment ctxt->_eip. + * + * Also prefetch the remaining bytes of the instruction without crossing page + * boundary if they are not in fetch_cache yet. + */ +static int do_insn_fetch_byte(struct x86_emulate_ctxt *ctxt, u8 *dest) { struct fetch_cache *fc = &ctxt->fetch; int rc; int size, cur_size; - if (eip == fc->end) { + if (ctxt->_eip == fc->end) { unsigned long linear; - struct segmented_address addr = { .seg=VCPU_SREG_CS, .ea=eip}; + struct segmented_address addr = { .seg = VCPU_SREG_CS, + .ea = ctxt->_eip }; cur_size = fc->end - fc->start; - size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip)); + size = min(15UL - cur_size, + PAGE_SIZE - offset_in_page(ctxt->_eip)); rc = __linearize(ctxt, addr, size, false, true, &linear); - if (rc != X86EMUL_CONTINUE) + if (unlikely(rc != X86EMUL_CONTINUE)) return rc; rc = ctxt->ops->fetch(ctxt, linear, fc->data + cur_size, size, &ctxt->exception); - if (rc != X86EMUL_CONTINUE) + if (unlikely(rc != X86EMUL_CONTINUE)) return rc; fc->end += size; } - *dest = fc->data[eip - fc->start]; + *dest = fc->data[ctxt->_eip - fc->start]; + ctxt->_eip++; return X86EMUL_CONTINUE; } static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, - unsigned long eip, void *dest, unsigned size) + void *dest, unsigned size) { int rc; /* x86 instructions are limited to 15 bytes. */ - if (eip + size - ctxt->eip > 15) + if (unlikely(ctxt->_eip + size - ctxt->eip > 15)) return X86EMUL_UNHANDLEABLE; while (size--) { - rc = do_insn_fetch_byte(ctxt, eip++, dest++); + rc = do_insn_fetch_byte(ctxt, dest++); if (rc != X86EMUL_CONTINUE) return rc; } @@ -693,20 +701,18 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, } /* Fetch next part of the instruction being emulated. */ -#define insn_fetch(_type, _size, _eip) \ +#define insn_fetch(_type, _ctxt) \ ({ unsigned long _x; \ - rc = do_insn_fetch(ctxt, (_eip), &_x, (_size)); \ + rc = do_insn_fetch(_ctxt, &_x, sizeof(_type)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ - (_eip) += (_size); \ (_type)_x; \ }) -#define insn_fetch_arr(_arr, _size, _eip) \ -({ rc = do_insn_fetch(ctxt, (_eip), _arr, (_size)); \ +#define insn_fetch_arr(_arr, _size, _ctxt) \ +({ rc = do_insn_fetch(_ctxt, _arr, (_size)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ - (_eip) += (_size); \ }) /* @@ -894,7 +900,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_rm = base_reg = (ctxt->rex_prefix & 1) << 3; /* REG.B */ } - ctxt->modrm = insn_fetch(u8, 1, ctxt->_eip); + ctxt->modrm = insn_fetch(u8, ctxt); ctxt->modrm_mod |= (ctxt->modrm & 0xc0) >> 6; ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3; ctxt->modrm_rm |= (ctxt->modrm & 0x07); @@ -928,13 +934,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 6) - modrm_ea += insn_fetch(u16, 2, ctxt->_eip); + modrm_ea += insn_fetch(u16, ctxt); break; case 1: - modrm_ea += insn_fetch(s8, 1, ctxt->_eip); + modrm_ea += insn_fetch(s8, ctxt); break; case 2: - modrm_ea += insn_fetch(u16, 2, ctxt->_eip); + modrm_ea += insn_fetch(u16, ctxt); break; } switch (ctxt->modrm_rm) { @@ -971,13 +977,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, } else { /* 32/64-bit ModR/M decode. */ if ((ctxt->modrm_rm & 7) == 4) { - sib = insn_fetch(u8, 1, ctxt->_eip); + sib = insn_fetch(u8, ctxt); index_reg |= (sib >> 3) & 7; base_reg |= sib & 7; scale = sib >> 6; if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0) - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); else modrm_ea += ctxt->regs[base_reg]; if (index_reg != 4) @@ -990,13 +996,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 5) - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); break; case 1: - modrm_ea += insn_fetch(s8, 1, ctxt->_eip); + modrm_ea += insn_fetch(s8, ctxt); break; case 2: - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); break; } } @@ -1013,13 +1019,13 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt, op->type = OP_MEM; switch (ctxt->ad_bytes) { case 2: - op->addr.mem.ea = insn_fetch(u16, 2, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u16, ctxt); break; case 4: - op->addr.mem.ea = insn_fetch(u32, 4, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u32, ctxt); break; case 8: - op->addr.mem.ea = insn_fetch(u64, 8, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u64, ctxt); break; } done: @@ -1452,15 +1458,18 @@ static int em_popf(struct x86_emulate_ctxt *ctxt) return emulate_popf(ctxt, &ctxt->dst.val, ctxt->op_bytes); } -static int emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg) +static int em_push_sreg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; + ctxt->src.val = get_segment_selector(ctxt, seg); return em_push(ctxt); } -static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, int seg) +static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; unsigned long selector; int rc; @@ -1674,64 +1683,74 @@ static int em_grp2(struct x86_emulate_ctxt *ctxt) { switch (ctxt->modrm_reg) { case 0: /* rol */ - emulate_2op_SrcB("rol", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rol"); break; case 1: /* ror */ - emulate_2op_SrcB("ror", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "ror"); break; case 2: /* rcl */ - emulate_2op_SrcB("rcl", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rcl"); break; case 3: /* rcr */ - emulate_2op_SrcB("rcr", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rcr"); break; case 4: /* sal/shl */ case 6: /* sal/shl */ - emulate_2op_SrcB("sal", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "sal"); break; case 5: /* shr */ - emulate_2op_SrcB("shr", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "shr"); break; case 7: /* sar */ - emulate_2op_SrcB("sar", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "sar"); break; } return X86EMUL_CONTINUE; } -static int em_grp3(struct x86_emulate_ctxt *ctxt) +static int em_not(struct x86_emulate_ctxt *ctxt) +{ + ctxt->dst.val = ~ctxt->dst.val; + return X86EMUL_CONTINUE; +} + +static int em_neg(struct x86_emulate_ctxt *ctxt) +{ + emulate_1op(ctxt, "neg"); + return X86EMUL_CONTINUE; +} + +static int em_mul_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 ex = 0; + + emulate_1op_rax_rdx(ctxt, "mul", ex); + return X86EMUL_CONTINUE; +} + +static int em_imul_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 ex = 0; + + emulate_1op_rax_rdx(ctxt, "imul", ex); + return X86EMUL_CONTINUE; +} + +static int em_div_ex(struct x86_emulate_ctxt *ctxt) { - unsigned long *rax = &ctxt->regs[VCPU_REGS_RAX]; - unsigned long *rdx = &ctxt->regs[VCPU_REGS_RDX]; u8 de = 0; - switch (ctxt->modrm_reg) { - case 0 ... 1: /* test */ - emulate_2op_SrcV("test", ctxt->src, ctxt->dst, ctxt->eflags); - break; - case 2: /* not */ - ctxt->dst.val = ~ctxt->dst.val; - break; - case 3: /* neg */ - emulate_1op("neg", ctxt->dst, ctxt->eflags); - break; - case 4: /* mul */ - emulate_1op_rax_rdx("mul", ctxt->src, *rax, *rdx, ctxt->eflags); - break; - case 5: /* imul */ - emulate_1op_rax_rdx("imul", ctxt->src, *rax, *rdx, ctxt->eflags); - break; - case 6: /* div */ - emulate_1op_rax_rdx_ex |