summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-10-04 16:30:33 (GMT)
committerLinus Torvalds <torvalds@linux-foundation.org>2012-10-04 16:30:33 (GMT)
commitecefbd94b834fa32559d854646d777c56749ef1c (patch)
treeca8958900ad9e208a8e5fb7704f1b66dc76131b4 /arch/x86/include
parentce57e981f2b996aaca2031003b3f866368307766 (diff)
parent3d11df7abbff013b811d5615320580cd5d9d7d31 (diff)
downloadlinux-fsl-qoriq-ecefbd94b834fa32559d854646d777c56749ef1c.tar.xz
Merge tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Avi Kivity: "Highlights of the changes for this release include support for vfio level triggered interrupts, improved big real mode support on older Intels, a streamlines guest page table walker, guest APIC speedups, PIO optimizations, better overcommit handling, and read-only memory." * tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits) KVM: s390: Fix vcpu_load handling in interrupt code KVM: x86: Fix guest debug across vcpu INIT reset KVM: Add resampling irqfds for level triggered interrupts KVM: optimize apic interrupt delivery KVM: MMU: Eliminate pointless temporary 'ac' KVM: MMU: Avoid access/dirty update loop if all is well KVM: MMU: Eliminate eperm temporary KVM: MMU: Optimize is_last_gpte() KVM: MMU: Simplify walk_addr_generic() loop KVM: MMU: Optimize pte permission checks KVM: MMU: Update accessed and dirty bits after guest pagetable walk KVM: MMU: Move gpte_access() out of paging_tmpl.h KVM: MMU: Optimize gpte_access() slightly KVM: MMU: Push clean gpte write protection out of gpte_access() KVM: clarify kvmclock documentation KVM: make processes waiting on vcpu mutex killable KVM: SVM: Make use of asm.h KVM: VMX: Make use of asm.h KVM: VMX: Make lto-friendly KVM: x86: lapic: Clean up find_highest_vector() and count_vectors() ... Conflicts: arch/s390/include/asm/processor.h arch/x86/kvm/i8259.c
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/kvm.h1
-rw-r--r--arch/x86/include/asm/kvm_emulate.h48
-rw-r--r--arch/x86/include/asm/kvm_host.h36
-rw-r--r--arch/x86/include/asm/kvm_para.h6
4 files changed, 70 insertions, 21 deletions
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 41e08cb..a65ec29 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -41,6 +41,7 @@
#define __KVM_HAVE_DEBUGREGS
#define __KVM_HAVE_XSAVE
#define __KVM_HAVE_XCRS
+#define __KVM_HAVE_READONLY_MEM
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index c764f43..15f960c 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -86,6 +86,19 @@ struct x86_instruction_info {
struct x86_emulate_ops {
/*
+ * read_gpr: read a general purpose register (rax - r15)
+ *
+ * @reg: gpr number.
+ */
+ ulong (*read_gpr)(struct x86_emulate_ctxt *ctxt, unsigned reg);
+ /*
+ * write_gpr: write a general purpose register (rax - r15)
+ *
+ * @reg: gpr number.
+ * @val: value to write.
+ */
+ void (*write_gpr)(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val);
+ /*
* read_std: Read bytes of standard (non-emulated/special) memory.
* Used for descriptor reading.
* @addr: [IN ] Linear address from which to read.
@@ -200,8 +213,9 @@ typedef u32 __attribute__((vector_size(16))) sse128_t;
/* Type, address-of, and value of an instruction's operand. */
struct operand {
- enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
+ enum { OP_REG, OP_MEM, OP_MEM_STR, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
unsigned int bytes;
+ unsigned int count;
union {
unsigned long orig_val;
u64 orig_val64;
@@ -221,6 +235,7 @@ struct operand {
char valptr[sizeof(unsigned long) + 2];
sse128_t vec_val;
u64 mm_val;
+ void *data;
};
};
@@ -236,14 +251,23 @@ struct read_cache {
unsigned long end;
};
+/* Execution mode, passed to the emulator. */
+enum x86emul_mode {
+ X86EMUL_MODE_REAL, /* Real mode. */
+ X86EMUL_MODE_VM86, /* Virtual 8086 mode. */
+ X86EMUL_MODE_PROT16, /* 16-bit protected mode. */
+ X86EMUL_MODE_PROT32, /* 32-bit protected mode. */
+ X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */
+};
+
struct x86_emulate_ctxt {
- struct x86_emulate_ops *ops;
+ const struct x86_emulate_ops *ops;
/* Register state before/after emulation. */
unsigned long eflags;
unsigned long eip; /* eip before instruction emulation */
/* Emulated execution mode, represented by an X86EMUL_MODE value. */
- int mode;
+ enum x86emul_mode mode;
/* interruptibility state, as a result of execution of STI or MOV SS */
int interruptibility;
@@ -281,8 +305,10 @@ struct x86_emulate_ctxt {
bool rip_relative;
unsigned long _eip;
struct operand memop;
+ u32 regs_valid; /* bitmaps of registers in _regs[] that can be read */
+ u32 regs_dirty; /* bitmaps of registers in _regs[] that have been written */
/* Fields above regs are cleared together. */
- unsigned long regs[NR_VCPU_REGS];
+ unsigned long _regs[NR_VCPU_REGS];
struct operand *memopp;
struct fetch_cache fetch;
struct read_cache io_read;
@@ -293,17 +319,6 @@ struct x86_emulate_ctxt {
#define REPE_PREFIX 0xf3
#define REPNE_PREFIX 0xf2
-/* Execution mode, passed to the emulator. */
-#define X86EMUL_MODE_REAL 0 /* Real mode. */
-#define X86EMUL_MODE_VM86 1 /* Virtual 8086 mode. */
-#define X86EMUL_MODE_PROT16 2 /* 16-bit protected mode. */
-#define X86EMUL_MODE_PROT32 4 /* 32-bit protected mode. */
-#define X86EMUL_MODE_PROT64 8 /* 64-bit (long) mode. */
-
-/* any protected mode */
-#define X86EMUL_MODE_PROT (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
- X86EMUL_MODE_PROT64)
-
/* CPUID vendors */
#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
@@ -394,4 +409,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
u16 tss_selector, int idt_index, int reason,
bool has_error_code, u32 error_code);
int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
+void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt);
+void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt);
+
#endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1eaa6b0..b2e11f4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -271,10 +271,24 @@ struct kvm_mmu {
union kvm_mmu_page_role base_role;
bool direct_map;
+ /*
+ * Bitmap; bit set = permission fault
+ * Byte index: page fault error code [4:1]
+ * Bit index: pte permissions in ACC_* format
+ */
+ u8 permissions[16];
+
u64 *pae_root;
u64 *lm_root;
u64 rsvd_bits_mask[2][4];
+ /*
+ * Bitmap: bit set = last pte in walk
+ * index[0:1]: level (zero-based)
+ * index[2]: pte.ps
+ */
+ u8 last_pte_bitmap;
+
bool nx;
u64 pdptrs[4]; /* pae */
@@ -398,12 +412,15 @@ struct kvm_vcpu_arch {
struct x86_emulate_ctxt emulate_ctxt;
bool emulate_regs_need_sync_to_vcpu;
bool emulate_regs_need_sync_from_vcpu;
+ int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
gpa_t time;
struct pvclock_vcpu_time_info hv_clock;
unsigned int hw_tsc_khz;
unsigned int time_offset;
struct page *time_page;
+ /* set guest stopped flag in pvclock flags field */
+ bool pvclock_set_guest_stopped_request;
struct {
u64 msr_val;
@@ -438,6 +455,7 @@ struct kvm_vcpu_arch {
unsigned long dr6;
unsigned long dr7;
unsigned long eff_db[KVM_NR_DB_REGS];
+ unsigned long guest_debug_dr7;
u64 mcg_cap;
u64 mcg_status;
@@ -484,14 +502,24 @@ struct kvm_vcpu_arch {
};
struct kvm_lpage_info {
- unsigned long rmap_pde;
int write_count;
};
struct kvm_arch_memory_slot {
+ unsigned long *rmap[KVM_NR_PAGE_SIZES];
struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
};
+struct kvm_apic_map {
+ struct rcu_head rcu;
+ u8 ldr_bits;
+ /* fields bellow are used to decode ldr values in different modes */
+ u32 cid_shift, cid_mask, lid_mask;
+ struct kvm_lapic *phys_map[256];
+ /* first index is cluster id second is cpu id in a cluster */
+ struct kvm_lapic *logical_map[16][16];
+};
+
struct kvm_arch {
unsigned int n_used_mmu_pages;
unsigned int n_requested_mmu_pages;
@@ -509,6 +537,8 @@ struct kvm_arch {
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
int vapics_in_nmi_mode;
+ struct mutex apic_map_lock;
+ struct kvm_apic_map *apic_map;
unsigned int tss_addr;
struct page *apic_access_page;
@@ -602,8 +632,7 @@ struct kvm_x86_ops {
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
- void (*set_guest_debug)(struct kvm_vcpu *vcpu,
- struct kvm_guest_debug *dbg);
+ void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -941,6 +970,7 @@ extern bool kvm_rebooting;
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_age_hva(struct kvm *kvm, unsigned long hva);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 2f7712e..eb3e9d8 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -102,21 +102,21 @@ struct kvm_vcpu_pv_apf_data {
extern void kvmclock_init(void);
extern int kvm_register_clock(char *txt);
-#ifdef CONFIG_KVM_CLOCK
+#ifdef CONFIG_KVM_GUEST
bool kvm_check_and_clear_guest_paused(void);
#else
static inline bool kvm_check_and_clear_guest_paused(void)
{
return false;
}
-#endif /* CONFIG_KVMCLOCK */
+#endif /* CONFIG_KVM_GUEST */
/* This instruction is vmcall. On non-VT architectures, it will generate a
* trap that we will then rewrite to the appropriate instruction.
*/
#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
-/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun
+/* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
* instruction. The hypervisor may replace it with something else but only the
* instructions are guaranteed to be supported.
*