summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/compressed/eboot.c4
-rw-r--r--arch/x86/entry/entry_64_compat.S3
-rw-r--r--arch/x86/include/asm/desc.h15
-rw-r--r--arch/x86/include/asm/kvm_host.h43
-rw-r--r--arch/x86/include/asm/mmu.h3
-rw-r--r--arch/x86/include/asm/mmu_context.h54
-rw-r--r--arch/x86/include/asm/mshyperv.h5
-rw-r--r--arch/x86/include/asm/sigcontext.h6
-rw-r--r--arch/x86/include/asm/switch_to.h12
-rw-r--r--arch/x86/include/asm/vmx.h47
-rw-r--r--arch/x86/include/uapi/asm/hyperv.h2
-rw-r--r--arch/x86/include/uapi/asm/sigcontext.h21
-rw-r--r--arch/x86/include/uapi/asm/vmx.h2
-rw-r--r--arch/x86/kernel/apic/apic.c14
-rw-r--r--arch/x86/kernel/apic/io_apic.c2
-rw-r--r--arch/x86/kernel/apic/vector.c2
-rw-r--r--arch/x86/kernel/cpu/common.c4
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c47
-rw-r--r--arch/x86/kernel/cpu/perf_event.c12
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c23
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_cqm.c8
-rw-r--r--arch/x86/kernel/fpu/core.c2
-rw-r--r--arch/x86/kernel/fpu/init.c7
-rw-r--r--arch/x86/kernel/ldt.c262
-rw-r--r--arch/x86/kernel/process.c2
-rw-r--r--arch/x86/kernel/process_64.c4
-rw-r--r--arch/x86/kernel/signal.c26
-rw-r--r--arch/x86/kernel/step.c8
-rw-r--r--arch/x86/kvm/Makefile4
-rw-r--r--arch/x86/kvm/hyperv.c377
-rw-r--r--arch/x86/kvm/hyperv.h32
-rw-r--r--arch/x86/kvm/i8259.c15
-rw-r--r--arch/x86/kvm/irq.h8
-rw-r--r--arch/x86/kvm/lapic.c5
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--arch/x86/kvm/mmu.c285
-rw-r--r--arch/x86/kvm/mmu.h4
-rw-r--r--arch/x86/kvm/mtrr.c8
-rw-r--r--arch/x86/kvm/paging_tmpl.h13
-rw-r--r--arch/x86/kvm/pmu_amd.c2
-rw-r--r--arch/x86/kvm/svm.c16
-rw-r--r--arch/x86/kvm/vmx.c181
-rw-r--r--arch/x86/kvm/x86.c330
-rw-r--r--arch/x86/kvm/x86.h5
-rw-r--r--arch/x86/math-emu/fpu_entry.c3
-rw-r--r--arch/x86/math-emu/fpu_system.h21
-rw-r--r--arch/x86/math-emu/get_address.c3
-rw-r--r--arch/x86/net/bpf_jit_comp.c8
-rw-r--r--arch/x86/platform/efi/efi.c5
-rw-r--r--arch/x86/power/cpu.c3
-rw-r--r--arch/x86/xen/Kconfig4
-rw-r--r--arch/x86/xen/Makefile4
-rw-r--r--arch/x86/xen/enlighten.c40
-rw-r--r--arch/x86/xen/xen-ops.h6
54 files changed, 1219 insertions, 805 deletions
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 2c82bd1..7d69afd 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1193,6 +1193,10 @@ static efi_status_t setup_e820(struct boot_params *params,
unsigned int e820_type = 0;
unsigned long m = efi->efi_memmap;
+#ifdef CONFIG_X86_64
+ m |= (u64)efi->efi_memmap_hi << 32;
+#endif
+
d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
switch (d->type) {
case EFI_RESERVED_TYPE:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 5a18447..a7e257d 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -140,6 +140,7 @@ sysexit_from_sys_call:
*/
andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
movl RIP(%rsp), %ecx /* User %eip */
+ movq RAX(%rsp), %rax
RESTORE_RSI_RDI
xorl %edx, %edx /* Do not leak kernel information */
xorq %r8, %r8
@@ -219,7 +220,6 @@ sysexit_from_sys_call:
1: setbe %al /* 1 if error, 0 if not */
movzbl %al, %edi /* zero-extend that into %edi */
call __audit_syscall_exit
- movq RAX(%rsp), %rax /* reload syscall return value */
movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
@@ -368,6 +368,7 @@ sysretl_from_sys_call:
RESTORE_RSI_RDI_RDX
movl RIP(%rsp), %ecx
movl EFLAGS(%rsp), %r11d
+ movq RAX(%rsp), %rax
xorq %r10, %r10
xorq %r9, %r9
xorq %r8, %r8
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a0bf89f..4e10d73 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)
set_ldt(NULL, 0);
}
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
- set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
- preempt_disable();
- load_LDT_nolock(pc);
- preempt_enable();
-}
-
static inline unsigned long get_desc_base(const struct desc_struct *desc)
{
return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 49ec903..c12e845 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -252,6 +252,11 @@ struct kvm_pio_request {
int size;
};
+struct rsvd_bits_validate {
+ u64 rsvd_bits_mask[2][4];
+ u64 bad_mt_xwr;
+};
+
/*
* x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
* 32-bit). The kvm_mmu structure abstracts the details of the current mmu
@@ -289,8 +294,15 @@ struct kvm_mmu {
u64 *pae_root;
u64 *lm_root;
- u64 rsvd_bits_mask[2][4];
- u64 bad_mt_xwr;
+
+ /*
+ * check zero bits on shadow page table entries, these
+ * bits include not only hardware reserved bits but also
+ * the bits spte never used.
+ */
+ struct rsvd_bits_validate shadow_zero_check;
+
+ struct rsvd_bits_validate guest_rsvd_check;
/*
* Bitmap: bit set = last pte in walk
@@ -358,6 +370,11 @@ struct kvm_mtrr {
struct list_head head;
};
+/* Hyper-V per vcpu emulation context */
+struct kvm_vcpu_hv {
+ u64 hv_vapic;
+};
+
struct kvm_vcpu_arch {
/*
* rip and regs accesses must go through
@@ -514,8 +531,7 @@ struct kvm_vcpu_arch {
/* used for guest single stepping over the given code position */
unsigned long singlestep_rip;
- /* fields used by HYPER-V emulation */
- u64 hv_vapic;
+ struct kvm_vcpu_hv hyperv;
cpumask_var_t wbinvd_dirty_mask;
@@ -586,6 +602,17 @@ struct kvm_apic_map {
struct kvm_lapic *logical_map[16][16];
};
+/* Hyper-V emulation context */
+struct kvm_hv {
+ u64 hv_guest_os_id;
+ u64 hv_hypercall;
+ u64 hv_tsc_page;
+
+ /* Hyper-v based guest crash (NT kernel bugcheck) parameters */
+ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
+ u64 hv_crash_ctl;
+};
+
struct kvm_arch {
unsigned int n_used_mmu_pages;
unsigned int n_requested_mmu_pages;
@@ -645,16 +672,14 @@ struct kvm_arch {
/* reads protected by irq_srcu, writes by irq_lock */
struct hlist_head mask_notifier_list;
- /* fields used by HYPER-V emulation */
- u64 hv_guest_os_id;
- u64 hv_hypercall;
- u64 hv_tsc_page;
+ struct kvm_hv hyperv;
#ifdef CONFIG_KVM_MMU_AUDIT
int audit_point;
#endif
bool boot_vcpu_runs_old_kvmclock;
+ u32 bsp_vcpu_id;
u64 disabled_quirks;
};
@@ -1203,5 +1228,7 @@ int __x86_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem);
int x86_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem);
+bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 09b9620..364d274 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
* we put the segment information here.
*/
typedef struct {
- void *ldt;
- int size;
+ struct ldt_struct *ldt;
#ifdef CONFIG_X86_64
/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 804a3a6..984abfe 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -34,6 +34,50 @@ static inline void load_mm_cr4(struct mm_struct *mm) {}
#endif
/*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+ /*
+ * Xen requires page-aligned LDTs with special permissions. This is
+ * needed to prevent us from installing evil descriptors such as
+ * call gates. On native, we could merge the ldt_struct and LDT
+ * allocations, but it's not worth trying to optimize.
+ */
+ struct desc_struct *entries;
+ int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+ struct ldt_struct *ldt;
+
+ /* lockless_dereference synchronizes with smp_store_release */
+ ldt = lockless_dereference(mm->context.ldt);
+
+ /*
+ * Any change to mm->context.ldt is followed by an IPI to all
+ * CPUs with the mm active. The LDT will not be freed until
+ * after the IPI is handled by all such CPUs. This means that,
+ * if the ldt_struct changes before we return, the values we see
+ * will be safe, and the new values will be loaded before we run
+ * any user code.
+ *
+ * NB: don't try to convert this to use RCU without extreme care.
+ * We would still need IRQs off, because we don't want to change
+ * the local LDT after an IPI loaded a newer value than the one
+ * that we can see.
+ */
+
+ if (unlikely(ldt))
+ set_ldt(ldt->entries, ldt->size);
+ else
+ clear_LDT();
+
+ DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
* Used for LDT copy/destruction.
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -78,12 +122,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
* was called and then modify_ldt changed
* prev->context.ldt but suppressed an IPI to this CPU.
* In this case, prev->context.ldt != NULL, because we
- * never free an LDT while the mm still exists. That
- * means that next->context.ldt != prev->context.ldt,
- * because mms never share an LDT.
+ * never set context.ldt to NULL while the mm still
+ * exists. That means that next->context.ldt !=
+ * prev->context.ldt, because mms never share an LDT.
*/
if (unlikely(prev->context.ldt != next->context.ldt))
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
}
#ifdef CONFIG_SMP
else {
@@ -106,7 +150,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
load_cr3(next->pgd);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
load_mm_cr4(next);
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
}
}
#endif
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index c163215..aaf59b7 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -7,6 +7,7 @@
struct ms_hyperv_info {
u32 features;
+ u32 misc_features;
u32 hints;
};
@@ -20,4 +21,8 @@ void hyperv_vector_handler(struct pt_regs *regs);
void hv_setup_vmbus_irq(void (*handler)(void));
void hv_remove_vmbus_irq(void);
+void hv_setup_kexec_handler(void (*handler)(void));
+void hv_remove_kexec_handler(void);
+void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
+void hv_remove_crash_handler(void);
#endif
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 6fe6b18..9dfce4e 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -57,9 +57,9 @@ struct sigcontext {
unsigned long ip;
unsigned long flags;
unsigned short cs;
- unsigned short __pad2; /* Was called gs, but was always zero. */
- unsigned short __pad1; /* Was called fs, but was always zero. */
- unsigned short ss;
+ unsigned short gs;
+ unsigned short fs;
+ unsigned short __pad0;
unsigned long err;
unsigned long trapno;
unsigned long oldmask;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b..d7f3b3b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -79,12 +79,12 @@ do { \
#else /* CONFIG_X86_32 */
/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
+#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
#define __EXTRA_CLOBBER \
, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
- "r12", "r13", "r14", "r15", "flags"
+ "r12", "r13", "r14", "r15"
#ifdef CONFIG_CC_STACKPROTECTOR
#define __switch_canary \
@@ -100,11 +100,7 @@ do { \
#define __switch_canary_iparam
#endif /* CC_STACKPROTECTOR */
-/*
- * There is no need to save or restore flags, because flags are always
- * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL
- * has no effect.
- */
+/* Save restore flags to clear handle leaking NT */
#define switch_to(prev, next, last) \
asm volatile(SAVE_CONTEXT \
"movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index da772ed..448b7ca 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -47,6 +47,7 @@
#define CPU_BASED_MOV_DR_EXITING 0x00800000
#define CPU_BASED_UNCOND_IO_EXITING 0x01000000
#define CPU_BASED_USE_IO_BITMAPS 0x02000000
+#define CPU_BASED_MONITOR_TRAP_FLAG 0x08000000
#define CPU_BASED_USE_MSR_BITMAPS 0x10000000
#define CPU_BASED_MONITOR_EXITING 0x20000000
#define CPU_BASED_PAUSE_EXITING 0x40000000
@@ -367,29 +368,29 @@ enum vmcs_field {
#define TYPE_PHYSICAL_APIC_EVENT (10 << 12)
#define TYPE_PHYSICAL_APIC_INST (15 << 12)
-/* segment AR */
-#define SEGMENT_AR_L_MASK (1 << 13)
-
-#define AR_TYPE_ACCESSES_MASK 1
-#define AR_TYPE_READABLE_MASK (1 << 1)
-#define AR_TYPE_WRITEABLE_MASK (1 << 2)
-#define AR_TYPE_CODE_MASK (1 << 3)
-#define AR_TYPE_MASK 0x0f
-#define AR_TYPE_BUSY_64_TSS 11
-#define AR_TYPE_BUSY_32_TSS 11
-#define AR_TYPE_BUSY_16_TSS 3
-#define AR_TYPE_LDT 2
-
-#define AR_UNUSABLE_MASK (1 << 16)
-#define AR_S_MASK (1 << 4)
-#define AR_P_MASK (1 << 7)
-#define AR_L_MASK (1 << 13)
-#define AR_DB_MASK (1 << 14)
-#define AR_G_MASK (1 << 15)
-#define AR_DPL_SHIFT 5
-#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3)
-
-#define AR_RESERVD_MASK 0xfffe0f00
+/* segment AR in VMCS -- these are different from what LAR reports */
+#define VMX_SEGMENT_AR_L_MASK (1 << 13)
+
+#define VMX_AR_TYPE_ACCESSES_MASK 1
+#define VMX_AR_TYPE_READABLE_MASK (1 << 1)
+#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2)
+#define VMX_AR_TYPE_CODE_MASK (1 << 3)
+#define VMX_AR_TYPE_MASK 0x0f
+#define VMX_AR_TYPE_BUSY_64_TSS 11
+#define VMX_AR_TYPE_BUSY_32_TSS 11
+#define VMX_AR_TYPE_BUSY_16_TSS 3
+#define VMX_AR_TYPE_LDT 2
+
+#define VMX_AR_UNUSABLE_MASK (1 << 16)
+#define VMX_AR_S_MASK (1 << 4)
+#define VMX_AR_P_MASK (1 << 7)
+#define VMX_AR_L_MASK (1 << 13)
+#define VMX_AR_DB_MASK (1 << 14)
+#define VMX_AR_G_MASK (1 << 15)
+#define VMX_AR_DPL_SHIFT 5
+#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3)
+
+#define VMX_AR_RESERVD_MASK 0xfffe0f00
#define TSS_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 0)
#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 1)
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index f36d56b..f0412c5 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -27,6 +27,8 @@
#define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0)
/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1)
+/* Partition reference TSC MSR is available */
+#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE (1 << 9)
/* A partition's reference time stamp counter (TSC) page */
#define HV_X64_MSR_REFERENCE_TSC 0x40000021
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 0e8a973..40836a9 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -177,24 +177,9 @@ struct sigcontext {
__u64 rip;
__u64 eflags; /* RFLAGS */
__u16 cs;
-
- /*
- * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
- * Linux saved and restored fs and gs in these slots. This
- * was counterproductive, as fsbase and gsbase were never
- * saved, so arch_prctl was presumably unreliable.
- *
- * If these slots are ever needed for any other purpose, there
- * is some risk that very old 64-bit binaries could get
- * confused. I doubt that many such binaries still work,
- * though, since the same patch in 2.5.64 also removed the
- * 64-bit set_thread_area syscall, so it appears that there is
- * no TLS API that works in both pre- and post-2.5.64 kernels.
- */
- __u16 __pad2; /* Was gs. */
- __u16 __pad1; /* Was fs. */
-
- __u16 ss;
+ __u16 gs;
+ __u16 fs;
+ __u16 __pad0;
__u64 err;
__u64 trapno;
__u64 oldmask;
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 1fe9218..37fee27 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -58,6 +58,7 @@
#define EXIT_REASON_INVALID_STATE 33
#define EXIT_REASON_MSR_LOAD_FAIL 34
#define EXIT_REASON_MWAIT_INSTRUCTION 36
+#define EXIT_REASON_MONITOR_TRAP_FLAG 37
#define EXIT_REASON_MONITOR_INSTRUCTION 39
#define EXIT_REASON_PAUSE_INSTRUCTION 40
#define EXIT_REASON_MCE_DURING_VMENTRY 41
@@ -106,6 +107,7 @@
{ EXIT_REASON_MSR_READ, "MSR_READ" }, \
{ EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \
{ EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \
+ { EXIT_REASON_MONITOR_TRAP_FLAG, "MONITOR_TRAP_FLAG" }, \
{ EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \
{ EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index dcb5285..cde732c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1424,7 +1424,7 @@ static inline void __x2apic_disable(void)
{
u64 msr;
- if (cpu_has_apic)
+ if (!cpu_has_apic)
return;
rdmsrl(MSR_IA32_APICBASE, msr);
@@ -1483,10 +1483,13 @@ void x2apic_setup(void)
static __init void x2apic_disable(void)
{
- u32 x2apic_id;
+ u32 x2apic_id, state = x2apic_state;
- if (x2apic_state != X2APIC_ON)
- goto out;
+ x2apic_mode = 0;
+ x2apic_state = X2APIC_DISABLED;
+
+ if (state != X2APIC_ON)
+ return;
x2apic_id = read_apic_id();
if (x2apic_id >= 255)
@@ -1494,9 +1497,6 @@ static __init void x2apic_disable(void)
__x2apic_disable();
register_lapic_address(mp_lapic_addr);
-out:
- x2apic_state = X2APIC_DISABLED;
- x2apic_mode = 0;
}
static __init void x2apic_enable(void)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 845dc0d..206052e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -943,7 +943,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
*/
if (irq < nr_legacy_irqs() && data->count == 1) {
if (info->ioapic_trigger != data->trigger)
- mp_register_handler(irq, data->trigger);
+ mp_register_handler(irq, info->ioapic_trigger);
data->entry.trigger = data->trigger = info->ioapic_trigger;
data->entry.polarity = data->polarity = info->ioapic_polarity;
}
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index f813261..2683f36 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -322,7 +322,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
irq_data->chip = &lapic_controller;
irq_data->chip_data = data;
irq_data->hwirq = virq + i;
- err = assign_irq_vector_policy(virq, irq_data->node, data,
+ err = assign_irq_vector_policy(virq + i, irq_data->node, data,
info);
if (err)
goto error;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 922c5e0..cb9e5df 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1410,7 +1410,7 @@ void cpu_init(void)
load_sp0(t, &current->thread);
set_tss_desc(cpu, t);
load_TR_desc();
- load_LDT(&init_mm.context);
+ load_mm_ldt(&init_mm);
clear_all_debug_regs();
dbg_restore_debug_regs();
@@ -1459,7 +1459,7 @@ void cpu_init(void)
load_sp0(t, thread);
set_tss_desc(cpu, t);
load_TR_desc();
- load_LDT(&init_mm.context);
+ load_mm_ldt(&init_mm);
t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index aad4bd8..f794bfa 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -18,6 +18,7 @@
#include <linux/efi.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
+#include <linux/kexec.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
#include <asm/hyperv.h>
@@ -28,10 +29,14 @@
#include <asm/i8259.h>
#include <asm/apic.h>
#include <asm/timer.h>
+#include <asm/reboot.h>
struct ms_hyperv_info ms_hyperv;
EXPORT_SYMBOL_GPL(ms_hyperv);
+static void (*hv_kexec_handler)(void);
+static void (*hv_crash_handler)(struct pt_regs *regs);
+
#if IS_ENABLED(CONFIG_HYPERV)
static void (*vmbus_handler)(void);
@@ -67,8 +72,47 @@ void hv_remove_vmbus_irq(void)
}
EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
+
+void hv_setup_kexec_handler(void (*handler)(void))
+{
+ hv_kexec_handler = handler;
+}
+EXPORT_SYMBOL_GPL(hv_setup_kexec_handler);
+
+void hv_remove_kexec_handler(void)
+{
+ hv_kexec_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_remove_kexec_handler);
+
+void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs))
+{
+ hv_crash_handler = handler;
+}
+EXPORT_SYMBOL_GPL(hv_setup_crash_handler);
+
+void hv_remove_crash_handler(void)
+{
+ hv_crash_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
#endif
+static void hv_machine_shutdown(void)
+{
+ if (kexec_in_progress && hv_kexec_handler)
+ hv_kexec_handler();
+ native_machine_shutdown();
+}
+
+static void hv_machine_crash_shutdown(struct pt_regs *regs)
+{
+ if (hv_crash_handler)
+ hv_crash_handler(regs);
+ native_machine_crash_shutdown(regs);
+}
+
+
static uint32_t __init ms_hyperv_platform(void)
{
u32 eax;
@@ -114,6 +158,7 @@ static void __init ms_hyperv_init_platform(void)
* Extract the features and hints
*/
ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
+ ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
@@ -141,6 +186,8 @@ static void __init ms_hyperv_init_platform(void)
no_timer_check = 1;
#endif
+ machine_ops.shutdown = hv_machine_shutdown;
+ machine_ops.crash_shutdown = hv_machine_crash_shutdown;
}
const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3658de4..9469dfa 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2179,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment)
int idx = segment >> 3;
if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+ struct ldt_struct *ldt;
+
if (idx > LDT_ENTRIES)
return 0;
- if (idx > current->active_mm->context.size)
+ /* IRQs are off, so this synchronizes with smp_store_release */
+ ldt = lockless_dereference(current->active_mm->context.ldt);
+ if (!ldt || idx > ldt->size)
return 0;
- desc = current->active_mm->context.ldt;
+ desc = &ldt->entries[idx];
} else {
if (idx > GDT_ENTRIES)
return 0;
- desc = raw_cpu_ptr(gdt_page.gdt);
+ desc = raw_cpu_ptr(gdt_page.gdt) + idx;
}
- return get_desc_base(desc + idx);
+ return get_desc_base(desc);
}
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b9826a9..6326ae2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2534,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu)
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
if (!cpuc->shared_regs)
- return NOTIFY_BAD;
+ goto err;
}
if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
@@ -2542,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu)
cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
if (!cpuc->constraint_list)
- return NOTIFY_BAD;
+ goto err_shared_regs;
cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
- if (!cpuc->excl_cntrs) {
- kfree(cpuc->constraint_list);
- kfree(cpuc->shared_regs);
- return NOTIFY_BAD;
- }
+ if (!cpuc->excl_cntrs)
+ goto err_constraint_list;
+
cpuc->excl_thread_id = 0;
}
return NOTIFY_OK;
+
+err_constraint_list:
+ kfree(cpuc->constraint_list);
+ cpuc->constraint_list = NULL;
+
+err_shared_regs:
+ kfree(cpuc->shared_regs);
+ cpuc->shared_regs = NULL;
+
+err:
+ return NOTIFY_BAD;
}
static void intel_pmu_cpu_starting(int cpu)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 63eb68b..377e8f8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -1255,7 +1255,7 @@ static inline void cqm_pick_event_reader(int cpu)
cpumask_set_cpu(cpu, &cqm_cpumask);
}
-static void intel_cqm_cpu_prepare(unsigned int cpu)
+static void intel_cqm_cpu_starting(unsigned int cpu)
{
struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1296,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb,
unsigned int cpu = (unsigned long)hcpu;
switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- intel_cqm_cpu_prepare(cpu);
- break;
case CPU_DOWN_PREPARE:
intel_cqm_cpu_exit(cpu);
break;
case CPU_STARTING:
+ intel_cqm_cpu_starting(cpu);
cqm_pick_event_reader(cpu);
break;
}
@@ -1373,7 +1371,7 @@ static int __init intel_cqm_init(void)
goto out;
for_each_online_cpu(i) {
- intel_cqm_cpu_prepare(i);
+ intel_cqm_cpu_starting(i);
cqm_pick_event_reader(i);
}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 79de954..d25097c 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -270,7 +270,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
dst_fpu->fpregs_active = 0;
dst_fpu->last_cpu = -1;
- if (src_fpu->fpstate_active)
+ if (src_fpu->fpstate_active && cpu_has_fpu)
fpu_copy(dst_fpu, src_fpu);
return 0;
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 1e173f6..d14e9ac 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -40,7 +40,12 @@ static void fpu__init_cpu_generic(void)
write_cr0(cr0);
/* Flush out any pending x87 state: */
- asm volatile ("fninit");
+#ifdef CONFIG_MATH_EMULATION
+ if (!cpu_has_fpu)
+ fpstate_init_soft(&current->thread.fpu.state.soft);
+ else
+#endif
+ asm volatile ("fninit");
}
/*
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d..2bcc052 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/smp.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
@@ -20,82 +21,82 @@
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
static void flush_ldt(void *current_mm)
{
- if (current->active_mm == current_mm)
- load_LDT(&current->active_mm->context);
+ mm_context_t *pc;
+
+ if (current->active_mm != current_mm)
+ return;
+
+ pc = &current->active_mm->context;
+ set_ldt(pc->ldt->entries, pc->ldt->size);
}
-#endif
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
{
- void *oldldt, *newldt;
- int oldsize;
-
- if (mincount <= pc->size)
- return 0;
- oldsize = pc->size;
- mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
- (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
- if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
- newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+ struct ldt_struct *new_ldt;
+ int alloc_size;
+
+ if (size > LDT_ENTRIES)
+ return NULL;
+
+ new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+ if (!new_ldt)
+ return NULL;
+
+ BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+ alloc_size = size * LDT_ENTRY_SIZE;
+
+ /*
+ * Xen is very picky: it requires a page-aligned LDT that has no
+ * trailing nonzero bytes in any page that contains LDT descriptors.
+ * Keep it simple: zero the whole allocation and never allocate less
+ * than PAGE_SIZE.
+ */
+ if (alloc_size > PAGE_SIZE)
+ new_ldt->entries = vzalloc(alloc_size);
else
- newldt = (void *)__get_free_page(GFP_KERNEL);
-
- if (!newldt)
- return -ENOMEM;
+ new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
- if (oldsize)
- memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
- oldldt = pc->ldt;
- memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
- (mincount - oldsize) * LDT_ENTRY_SIZE);
+ if (!new_ldt->entries) {
+ kfree(new_ldt);
+ return NULL;
+ }
- paravirt_alloc_ldt(newldt, mincount);
+ new_ldt->size = size;
+ return new_ldt;
+}
-#ifdef CONFIG_X86_64
- /* CHECKME: Do we really need this ? */
- wmb();
-#endif
- pc->ldt = newldt;
- wmb();
- pc->size = mincount;
- wmb();
-
- if (reload) {
-#ifdef CONFIG_SMP
- preempt_disable();
- load_LDT(pc);
- if (!cpumask_equal(mm_cpumask(current->mm),
- cpumask_of(smp_processor_id())))
- smp_call_function(flush_ldt, current->mm, 1);
- preempt_enable();
-#else
- load_LDT(pc);
-#endif
- }
- if (oldsize) {
- paravirt_free_ldt(oldldt, oldsize);
- if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
- vfree(oldldt);
- else
- put_page(virt_to_page(oldldt));
- }
- return 0;
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
+{
+ paravirt_alloc_ldt(ldt->entries, ldt->size);
}
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+ struct ldt_struct *ldt)
{
- int err = alloc_ldt(new, old->size, 0);
- int i;
+ /* Synchronizes with lockless_dereference in load_mm_ldt. */
+ smp_store_release(&current_mm->context.ldt, ldt);
+
+ /* Activate the LDT for all CPUs using current_mm. */
+ on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
- if (err < 0)
- return err;
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+ if (likely(!ldt))
+ return;
- for (i = 0; i < old->size; i++)
- write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
- return 0;
+ paravirt_free_ldt(ldt->entries, ldt->size);
+ if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(ldt->entries);
+ else
+ kfree(ldt->entries);
+ kfree(ldt);
}
/*
@@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
+ struct ldt_struct *new_ldt;
struct mm_struct *old_mm;
int retval = 0;
mutex_init(&mm->context.lock);
- mm->context.size = 0;
old_mm = current->mm;
- if (old_mm && old_mm->context.size > 0) {
- mutex_lock(&old_mm->context.lock);
- retval = copy_ldt(&mm->context, &old_mm->context);
- mutex_unlock(&old_mm->context.lock);
+ if (!old_mm) {
+ mm->context.ldt = NULL;
+ return 0;
}
+
+ mutex_lock(&old_mm->context.lock);
+ if (!old_mm->context.ldt) {
+ mm->context.ldt = NULL;
+ goto out_unlock;
+ }
+
+ new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+ if (!new_ldt) {
+ retval = -ENOMEM;
+ goto out_unlock;
+ }
+
+ memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+ new_ldt->size * LDT_ENTRY_SIZE);
+ finalize_ldt_struct(new_ldt);
+
+ mm->context.ldt = new_ldt;
+
+out_unlock:
+ mutex_unlock(&old_mm->context.lock);
return retval;
}
@@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
*/
void destroy_context(struct mm_struct *mm)
{
- if (mm->context.size) {
-#ifdef CONFIG_X86_32
- /* CHECKME: Can this ever happen ? */
- if (mm == current->active_mm)
- clear_LDT();
-#endif
- paravirt_free_ldt(mm->context.ldt, mm->context.size);
- if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
- vfree(mm->context.ldt);
- else
- put_page(virt_to_page(mm->context.ldt));
- mm->context.size = 0;
- }
+ free_ldt_struct(mm->context.ldt);
+ mm->context.ldt = NULL;
}
static int read_ldt(void __user *ptr, unsigned long bytecount)
{
- int err;
+ int retval;
unsigned long size;
struct mm_struct *mm = current->mm;
- if (!mm->context.size)
- return 0;
+ mutex_lock(&mm->context.lock);
+
+ if (!mm->context.ldt) {
+ retval = 0;
+ goto out_unlock;
+ }
+
if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
- mutex_lock(&mm->context.lock);
- size = mm->context.size * LDT_ENTRY_SIZE;
+ size = mm->context.ldt->size * LDT_ENTRY_SIZE;
if (size > bytecount)
size = bytecount;
- err = 0;
- if (copy_to_user(ptr, mm->context.ldt, size))
- err = -EFAULT;
- mutex_unlock(&mm->context.lock);
- if (err < 0)
- goto error_return;
+ if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+ retval = -EFAULT;
+ goto out_unlock;
+ }
+
if (size != bytecount) {
- /* zero-fill the rest */
- if (clear_user(ptr + size, bytecount - size) != 0) {
- err = -EFAULT;
- goto error_return;
+ /* Zero-fill the rest and pretend we read bytecount bytes. */
+ if (clear_user(ptr + size, bytecount - size)) {
+ retval = -EFAULT;
+ goto out_unlock;
}
}
- return bytecount;
-error_return:
- return err;
+ retval = bytecount;
+
+out_unlock:
+ mutex_unlock(&mm->context.lock);
+ return retval;
}
static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
struct desc_struct ldt;
int error;
struct user_desc ldt_info;
+ int oldsize, newsize;
+ struct ldt_struct *new_ldt, *old_ldt;
error = -EINVAL;
if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
goto out;
}
- mutex_lock(&mm->context.lock);
- if (ldt_info.entry_number >= mm->context.size) {
- error = alloc_ldt(&current->mm->context,
- ldt_info.entry_number + 1, 1);
- if (error < 0)
- goto out_unlock;
- }
-
- /* Allow LDTs to be cleared by the user. */
- if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
- if (oldmode || LDT_empty(&ldt_info)) {
- memset(&ldt, 0, sizeof(ldt));
- goto install;
+ if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+ LDT_empty(&ldt_info)) {
+ /* The user wants to clear the entry. */
+ memset(&ldt, 0, sizeof(ldt));
+ } else {
+ if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+ error = -EINVAL;
+ goto out;
}
+
+ fill_ldt(&ldt, &ldt_info);
+ if (oldmode)
+ ldt.avl = 0;
}
- if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
- error = -EINVAL;
+ mutex_lock(&mm->context.lock);
+
+ old_ldt = mm->context.ldt;
+ oldsize = old_ldt ? old_ldt->size : 0;
+ newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+ error = -ENOMEM;
+ new_ldt = alloc_ldt_struct(newsize);
+ if (!new_ldt)
goto out_unlock;
- }
- fill_ldt(&ldt, &ldt_info);
- if (oldmode)
- ldt.avl = 0;
+ if (old_ldt)
+ memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+ new_ldt->entries[ldt_info.entry_number] = ldt;
+ finalize_ldt_struct(new_ldt);
- /* Install the new entry ... */
-install:
- write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+ install_ldt(mm, new_ldt);
+ free_ldt_struct(old_ldt);
error = 0;
out_unlock:
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 397688b..c27cad7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -408,6 +408,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
static void mwait_idle(void)
{
if (!current_set_polling_and_test()) {
+ trace_cpu_idle_rcuidle(1, smp_processor_id());
if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
smp_mb(); /* quirk */
clflush((void *)&current_thread_info()->flags);
@@ -419,6 +420,7 @@ static void mwait_idle(void)
__sti_mwait(0, 0);
else
local_irq_enable();
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
} else {
local_irq_enable();
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71d7849..f6b9163 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -121,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all)
void release_thread(struct task_struct *dead_task)
{
if (dead_task->mm) {
- if (dead_task->mm->context.size) {
+ if (dead_task->mm->context.ldt) {
pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
dead_task->comm,
dead_task->mm->context.ldt,
- dead_task->mm->context.size);
+ dead_task->mm->context.ldt->size);
BUG();
}
}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 206996c..71820c4 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
COPY(r15);
#endif /* CONFIG_X86_64 */
+#ifdef CONFIG_X86_32
COPY_SEG_CPL3(cs);
COPY_SEG_CPL3(ss);
+#else /* !CONFIG_X86_32 */
+ /* Kernel saves and restores only the CS segment register on signals,
+ * which is the bare minimum needed to allow mixed 32/64-bit code.
+ * App's signal handler can save/restore other segments if needed. */
+ COPY_SEG_CPL3(cs);
+#endif /* CONFIG_X86_32 */
get_user_ex(tmpflags, &sc->flags);
regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
#else /* !CONFIG_X86_32 */
put_user_ex(regs->flags, &sc->flags);
put_user_ex(regs->cs, &sc->cs);
- put_user_ex(0, &sc->__pad2);
- put_user_ex(0, &sc->__pad1);
- put_user_ex(regs->ss, &sc->ss);
+ put_user_ex(0, &sc->gs);
+ put_user_ex(0, &sc->fs);
#endif /* CONFIG_X86_32 */
put_user_ex(fpstate, &sc->fpstate);
@@ -451,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
regs->sp = (unsigned long)frame;
- /*
- * Set up the CS and SS registers to run signal handlers in
- * 64-bit mode, even if the handler happens to be interrupting
- * 32-bit or 16-bit code.
- *
- * SS is subtle. In 64-bit mode, we don't need any particular
- * SS descriptor, but we do need SS to be valid. It's possible
- * that the old SS is entirely bogus -- this can happen if the
- * signal we're trying to deliver is #GP or #SS caused by a bad
- * SS value.
- */
+ /* Set up the CS register to run signal handlers in 64-bit mode,
+ even if the handler happens to be interrupting 32-bit code. */
regs->cs = __USER_CS;
- regs->ss = __USER_DS;
return 0;
}
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d..0ccb53a 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
#include <linux/mm.h>
#include <linux/ptrace.h>
#include <asm/desc.h>
+#include <asm/mmu_context.h>
unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
{
@@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
struct desc_struct *desc;
unsigned long base;
- seg &= ~7UL;
+ seg >>= 3;
mutex_lock(&child->mm->context.lock);
- if (unlikely((seg >> 3) >= child->mm->context.size))
+ if (unlikely(!child->mm->context.ldt ||
+ seg >= child->mm->context.ldt->size))
addr = -1L; /* bogus selector, access would fault */
else {
- desc = child->mm->context.ldt + seg;
+ desc = &child->mm->context.ldt->entries[seg];
base = get_desc_base(desc);
/* 16-bit code segment? */
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 67d215c..a1ff508 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,7 +12,9 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
- i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o
+ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
+ hyperv.o
+
kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o
kvm-intel-y += vmx.o pmu_intel.o
kvm-amd-y += svm.o pmu_amd.o
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
new file mode 100644
index 0000000..a8160d2
--- /dev/null
+++ b/arch/x86/kvm/hyperv.c
@@ -0,0 +1,377 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ * Avi Kivity <avi@qumranet.com>
+ * Yaniv Kamay <yaniv@qumranet.com>
+ * Amit Shah <amit.shah@qumranet.com>
+ * Ben-Ami Yassour <benami@il.ibm.com>
+ * Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "x86.h"
+#include "lapic.h"
+#include "hyperv.h"
+
+#include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+ bool r = false;
+
+ switch (msr) {
+ case HV_X64_MSR_GUEST_OS_ID:
+ case HV_X64_MSR_HYPERCALL:
+ case HV_X64_MSR_REFERENCE_TSC:
+ case HV_X64_MSR_TIME_REF_COUNT:
+ case HV_X64_MSR_CRASH_CTL:
+ case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+ r = true;
+ break;
+ }
+
+ return r;
+}
+
+static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
+ u32 index, u64 *pdata)
+{
+ struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+ if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+ return -EINVAL;
+
+ *pdata = hv->hv_crash_param[index];
+ return 0;
+}
+
+static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata)
+{
+ struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+ *pdata = hv->hv_crash_ctl;
+ return 0;
+}
+
+static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host)
+{
+ struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+ if (host)
+ hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY;
+
+ if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) {
+
+ vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
+ hv->hv_crash_param[0],
+ hv->hv_crash_param[1],
+ hv->hv_crash_param[2],
+ hv->hv_crash_param[3],
+ hv->hv_crash_param[4]);
+
+ /* Send notification about crash to user space */
+ kvm_make_request(KVM_REQ_HV_CRASH, vcpu);
+ }
+
+ return 0;
+}
+
+static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
+ u32 index, u64 data)
+{
+ struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+
+ if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+ return -EINVAL;
+
+ hv->hv_crash_param[index] = data;
+ return 0;
+}
+
+static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
+ bool host)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_hv *hv = &kvm->arch.hyperv;
+
+ switch (msr) {
+ case HV_X64_MSR_GUEST_OS_ID:
+ hv->hv_guest_os_id = data;
+ /* setting guest os id to zero disables hypercall page */
+ if (!hv->hv_guest_os_id)
+ hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+ break;
+ case HV_X64_MSR_HYPERCALL: {
+ u64 gfn;
+ unsigned long addr;
+ u8 instructions[4];
+
+ /* if guest os id is not set hypercall should remain disabled */
+ if (!hv->hv_guest_os_id)
+ break;
+ if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+ hv->hv_hypercall = data;
+ break;
+ }
+ gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+ addr = gfn_to_hva(kvm, gfn);
+ if (kvm_is_error_hva(addr))
+ return 1;
+ kvm_x86_ops->patch_hypercall(vcpu, instructions);
+ ((unsigned char *)instructions)[3] = 0xc3; /* ret */
+ if (__copy_to_user((void __user *)addr, instructions, 4))
+ return 1;
+ hv->hv_hypercall = data;
+ mark_page_dirty(kvm, gfn);
+ break;
+ }
+ case HV_X64_MSR_REFERENCE_TSC: {
+ u64 gfn;
+ HV_REFERENCE_TSC_PAGE tsc_ref;
+
+ memset(&tsc_ref, 0, sizeof(tsc_ref));
+ hv->hv_tsc_page = data;
+ if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+ break;
+ gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+ if (kvm_write_guest(
+ kvm,
+ gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
+ &tsc_ref, sizeof(tsc_ref)))
+ return 1;
+ mark_page_dirty(kvm, gfn);
+ break;
+ }
+ case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+ return kvm_hv_msr_set_crash_data(vcpu,
+ msr - HV_X64_MSR_CRASH_P0,
+ data);
+ case HV_X64_MSR_CRASH_CTL:
+ return kvm_hv_msr_set_crash_ctl(vcpu, data, host);
+ default:
+ vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+ msr, data);
+ return 1;
+ }
+ return 0;
+}
+
+static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+ switch (msr) {
+ case HV_X64_MSR_APIC_ASSIST_PAGE: {
+ u64 gfn;
+ unsigned long addr;
+
+ if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+ hv->hv_vapic = data;
+ if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+ return 1;
+ break;
+ }
+ gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
+ addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+ if (kvm_is_error_hva(addr))
+ return 1;
+ if (__clear_user((void __user *)addr, PAGE_SIZE))
+ return 1;
+ hv->hv_vapic = data;
+ kvm_vcpu_mark_page_dirty(vcpu, gfn);
+ if (kvm_lapic_enable_pv_eoi(vcpu,
+ gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+ return 1;
+ break;
+ }
+ case HV_X64_MSR_EOI:
+ return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+ case HV_X64_MSR_ICR:
+ return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
+ case HV_X64_MSR_TPR:
+ return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+ default:
+ vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+ msr, data);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+ u64 data = 0;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_hv *hv = &kvm->arch.hyperv;
+
+ switch (msr) {
+ case HV_X64_MSR_GUEST_OS_ID:
+ data = hv->hv_guest_os_id;
+ break;
+ case HV_X64_MSR_HYPERCALL:
+ data = hv->hv_hypercall;
+ break;
+ case HV_X64_MSR_TIME_REF_COUNT: {
+ data =
+ div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
+ break;
+ }
+ case HV_X64_MSR_REFERENCE_TSC:
+ data = hv->hv_tsc_page;
+ break;
+ case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+ return kvm_hv_msr_get_crash_data(vcpu,
+ msr - HV_X64_MSR_CRASH_P0,
+ pdata);
+ case HV_X64_MSR_CRASH_CTL:
+ return kvm_hv_msr_get_crash_ctl(vcpu, pdata);
+ default:
+ vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+ return 1;
+ }
+
+ *pdata = data;
+ return 0;
+}
+
+static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+ u64 data = 0;
+ struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+
+ switch (msr) {
+ case HV_X64_MSR_VP_INDEX: {
+ int r;
+ struct kvm_vcpu *v;
+
+ kvm_for_each_vcpu(r, v, vcpu->kvm) {
+ if (v == vcpu) {
+ data = r;
+ break;
+ }
+ }
+ break;
+ }
+ case HV_X64_MSR_EOI:
+ return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+ case HV_X64_MSR_ICR:
+ return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+ case HV_X64_MSR_TPR:
+ return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+ case HV_X64_MSR_APIC_ASSIST_PAGE:
+ data = hv->hv_vapic;
+ break;
+ default:
+ vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+ return 1;
+ }
+ *pdata = data;
+ return 0;
+}
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
+{
+ if (kvm_hv_msr_partition_wide(msr)) {
+ int r;
+
+ mutex_lock(&vcpu->kvm->lock);
+ r = kvm_hv_set_msr_pw(vcpu, msr, data, host);
+ mutex_unlock(&vcpu->kvm->lock);
+ return r;
+ } else
+ return kvm_hv_set_msr(vcpu, msr, data);
+}
+
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+ if (kvm_hv_msr_partition_wide(msr)) {
+ int r;
+
+ mutex_lock(&vcpu->kvm->lock);
+ r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
+ mutex_unlock(&vcpu->kvm->lock);
+ return r;
+ } else
+ return kvm_hv_get_msr(vcpu, msr, pdata);
+}
+
+bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+ return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+ u64 param, ingpa, outgpa, ret;
+ uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+ bool fast, longmode;
+
+ /*
+ * hypercall generates UD from non zero cpl and real mode
+ * per HYPER-V spec
+ */
+ if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 0;
+ }
+
+ longmode = is_64_bit_mode(vcpu);
+
+ if (!longmode) {
+ param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+ (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+ ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+ (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+ outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+ (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+ }
+#ifdef CONFIG_X86_64
+ else {
+ param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+ ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+ outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+ }
+#endif
+
+ code = param & 0xffff;
+ fast = (param >> 16) & 0x1;
+ rep_cnt = (param >> 32) & 0xfff;
+ rep_idx = (param >> 48) & 0xfff;
+
+ trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+ switch (code) {
+ case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+ kvm_vcpu_on_spin(vcpu);
+ break;
+ default:
+ res = HV_STATUS_INVALID_HYPERCALL_CODE;
+ break;
+ }
+
+ ret = res | (((u64)rep_done & 0xfff) << 32);
+ if (longmode) {
+ kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+ } else {
+ kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+ kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+ }
+
+ return 1;
+}
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
new file mode 100644
index 0000000..c7bce55
--- /dev/null
+++ b/arch/x86/kvm/hyperv.h
@@ -0,0 +1,32 @@
+/*
+ * KVM Microsoft Hyper-V emulation
+ *
+ * derived from arch/x86/kvm/x86.c
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright (C) 2008 Qumranet, Inc.
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * Authors:
+ * Avi Kivity <avi@qumranet.com>
+ * Yaniv Kamay <yaniv@qumranet.com>
+ * Amit Shah <amit.shah@qumranet.com>
+ * Ben-Ami Yassour <benami@il.ibm.com>
+ * Andrey Smetanin <asmetanin@virtuozzo.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef __ARCH_X86_KVM_HYPERV_H__
+#define __ARCH_X86_KVM_HYPERV_H__
+
+int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
+int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+bool kvm_hv_hypercall_enabled(struct kvm *kvm);
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index fef922f..7cc2360 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -651,15 +651,10 @@ fail_unlock:
return NULL;
}
-void kvm_destroy_pic(struct kvm *kvm)
+void kvm_destroy_pic(struct kvm_pic *vpic)
{
- struct kvm_pic *vpic = kvm->arch.vpic;
-
- if (vpic) {
- kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master);
- kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave);
- kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr);
- kvm->arch.vpic = NULL;
- kfree(vpic);
- }
+ kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
+ kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
+ kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
+ kfree(vpic);
}
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index ad68c73..3d782a2 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -74,7 +74,7 @@ struct kvm_pic {
};
struct kvm_pic *kvm_create_pic(struct kvm *kvm);
-void kvm_destroy_pic(struct kvm *kvm);
+void kvm_destroy_pic(struct kvm_pic *vpic);
int kvm_pic_read_irq(struct kvm *kvm);
void kvm_pic_update_irq(struct kvm_pic *s);
@@ -85,11 +85,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
static inline int irqchip_in_kernel(struct kvm *kvm)
{
- int ret;
+ struct kvm_pic *vpic = pic_irqchip(kvm);
- ret = (pic_irqchip(kvm) != NULL);
+ /* Read vpic before kvm->irq_routing. */
smp_rmb();
- return ret;
+ return vpic != NULL;
}
void kvm_pic_reset(struct kvm_kpic_state *s);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 2a5ca97..9a3e342 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1900,8 +1900,9 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
return;
- kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
- sizeof(u32));
+ if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+ sizeof(u32)))
+ return;
apic_set_tpr(vcpu->arch.apic, data & 0xff);
}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 7195274..7640379 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -91,7 +91,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
+ return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
}
int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4417146..fb16a8e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -357,12 +357,6 @@ static u64 __get_spte_lockless(u64 *sptep)
{
return ACCESS_ONCE(*sptep);
}
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
- /* It is valid if the spte is zapped. */
- return spte == 0ull;
-}
#else
union split_spte {
struct {
@@ -478,23 +472,6 @@ retry:
return spte.spte;
}
-
-static bool __check_direct_spte_mmio_pf(u64 spte)
-{
- union split_spte sspte = (union split_spte)spte;
- u32 high_mmio_mask = shadow_mmio_mask >> 32;
-
- /* It is valid if the spte is zapped. */
- if (spte == 0ull)
- return true;
-
- /* It is valid if the spte is being zapped. */
- if (sspte.spte_low == 0ull &&
- (sspte.spte_high & high_mmio_mask) == high_mmio_mask)
- return true;
-
- return false;
-}
#endif
static bool spte_is_locklessly_modifiable(u64 spte)
@@ -3291,54 +3268,89 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
}
-static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+static bool
+__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level)
{
- if (direct)
- return vcpu_match_mmio_gpa(vcpu, addr);
+ int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f;
- return vcpu_match_mmio_gva(vcpu, addr);
+ return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) |
+ ((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0);
}
+static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+ return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level);
+}
-/*
- * On direct hosts, the last spte is only allows two states
- * for mmio page fault:
- * - It is the mmio spte
- * - It is zapped or it is being zapped.
- *
- * This function completely checks the spte when the last spte
- * is not the mmio spte.
- */
-static bool check_direct_spte_mmio_pf(u64 spte)
+static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level)
{
- return __check_direct_spte_mmio_pf(spte);
+ return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
}
-static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
+static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+{
+ if (direct)
+ return vcpu_match_mmio_gpa(vcpu, addr);
+
+ return vcpu_match_mmio_gva(vcpu, addr);
+}
+
+/* return true if reserved bit is detected on spte. */
+static bool
+walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
{
struct kvm_shadow_walk_iterator iterator;
- u64 spte = 0ull;
+ u64 sptes[PT64_ROOT_LEVEL], spte = 0ull;
+ int root, leaf;
+ bool reserved = false;
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
- return spte;
+ goto exit;
walk_shadow_page_lockless_begin(vcpu);
- for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
+
+ for (shadow_walk_init(&iterator, vcpu, addr), root = iterator.level;
+ shadow_walk_okay(&iterator);
+ __shadow_walk_next(&iterator, spte)) {
+ leaf = iterator.level;
+ spte = mmu_spte_get_lockless(iterator.sptep);
+
+ sptes[leaf - 1] = spte;
+
if (!is_shadow_present_pte(spte))
break;
+
+ reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
+ leaf);
+ }
+
walk_shadow_page_lockless_end(vcpu);
- return spte;
+ if (reserved) {
+ pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
+ __func__, addr);
+ while (root >= leaf) {
+ pr_err("------ spte 0x%llx level %d.\n",
+ sptes[root - 1], root);
+ root--;
+ }
+ }
+exit:
+ *sptep = spte;
+ return reserved;
}
int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
u64 spte;
+ bool reserved;
if (quickly_check_mmio_pf(vcpu, addr, direct))
return RET_MMIO_PF_EMULATE;
- spte = walk_shadow_page_get_mmio_spte(vcpu, addr);
+ reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
+ if (unlikely(reserved))
+ return RET_MMIO_PF_BUG;
if (is_mmio_spte(spte)) {
gfn_t gfn = get_mmio_spte_gfn(spte);
@@ -3356,13 +3368,6 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
}
/*
- * It's ok if the gva is remapped by other cpus on shadow guest,
- * it's a BUG if the gfn is not a mmio page.
- */
- if (direct && !check_direct_spte_mmio_pf(spte))
- return RET_MMIO_PF_BUG;
-
- /*
* If the page table is zapped by other cpus, let CPU fault again on
* the address.
*/
@@ -3604,19 +3609,21 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp
#include "paging_tmpl.h"
#undef PTTYPE
-static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
- struct kvm_mmu *context)
+static void
+__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+ struct rsvd_bits_validate *rsvd_check,
+ int maxphyaddr, int level, bool nx, bool gbpages,
+ bool pse)
{
- int maxphyaddr = cpuid_maxphyaddr(vcpu);
u64 exb_bit_rsvd = 0;
u64 gbpages_bit_rsvd = 0;
u64 nonleaf_bit8_rsvd = 0;
- context->bad_mt_xwr = 0;
+ rsvd_check->bad_mt_xwr = 0;
- if (!context->nx)
+ if (!nx)
exb_bit_rsvd = rsvd_bits(63, 63);
- if (!guest_cpuid_has_gbpages(vcpu))
+ if (!gbpages)
gbpages_bit_rsvd = rsvd_bits(7, 7);
/*
@@ -3626,80 +3633,95 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
if (guest_cpuid_is_amd(vcpu))
nonleaf_bit8_rsvd = rsvd_bits(8, 8);
- switch (context->root_level) {
+ switch (level) {
case PT32_ROOT_LEVEL:
/* no rsvd bits for 2 level 4K page table entries */
- context->rsvd_bits_mask[0][1] = 0;
- context->rsvd_bits_mask[0][0] = 0;
- context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+ rsvd_check->rsvd_bits_mask[0][1] = 0;
+ rsvd_check->rsvd_bits_mask[0][0] = 0;
+ rsvd_check->rsvd_bits_mask[1][0] =
+ rsvd_check->rsvd_bits_mask[0][0];
- if (!is_pse(vcpu)) {
- context->rsvd_bits_mask[1][1] = 0;
+ if (!pse) {
+ rsvd_check->rsvd_bits_mask[1][1] = 0;
break;
}
if (is_cpuid_PSE36())
/* 36bits PSE 4MB page */
- context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
+ rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
else
/* 32 bits PSE 4MB page */
- context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
+ rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
break;
case PT32E_ROOT_LEVEL:
- context->rsvd_bits_mask[0][2] =
+ rsvd_check->rsvd_bits_mask[0][2] =
rsvd_bits(maxphyaddr, 63) |
rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */
- context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+ rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 62); /* PDE */
- context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+ rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 62); /* PTE */
- context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+ rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 62) |
rsvd_bits(13, 20); /* large page */
- context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+ rsvd_check->rsvd_bits_mask[1][0] =
+ rsvd_check->rsvd_bits_mask[0][0];
break;
case PT64_ROOT_LEVEL:
- context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
- nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51);
- context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
- nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
- context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+ rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
+ nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
+ rsvd_bits(maxphyaddr, 51);
+ rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
+ nonleaf_bit8_rsvd | gbpages_bit_rsvd |
rsvd_bits(maxphyaddr, 51);
- context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+ rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51);
- context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
- context->rsvd_bits_mask[1][2] = exb_bit_rsvd |
+ rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+ rsvd_bits(maxphyaddr, 51);
+ rsvd_check->rsvd_bits_mask[1][3] =
+ rsvd_check->rsvd_bits_mask[0][3];
+ rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd |
gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
rsvd_bits(13, 29);
- context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+ rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51) |
rsvd_bits(13, 20); /* large page */
- context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+ rsvd_check->rsvd_bits_mask[1][0] =
+ rsvd_check->rsvd_bits_mask[0][0];
break;
}
}
-static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
- struct kvm_mmu *context, bool execonly)
+static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
+{
+ __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
+ cpuid_maxphyaddr(vcpu), context->root_level,
+ context->nx, guest_cpuid_has_gbpages(vcpu),
+ is_pse(vcpu));
+}
+
+static void
+__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
+ int maxphyaddr, bool execonly)
{
- int maxphyaddr = cpuid_maxphyaddr(vcpu);
int pte;
- context->rsvd_bits_mask[0][3] =
+ rsvd_check->rsvd_bits_mask[0][3] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
- context->rsvd_bits_mask[0][2] =
+ rsvd_check->rsvd_bits_mask[0][2] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
- context->rsvd_bits_mask[0][1] =
+ rsvd_check->rsvd_bits_mask[0][1] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
- context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+ rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
/* large page */
- context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
- context->rsvd_bits_mask[1][2] =
+ rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
+ rsvd_check->rsvd_bits_mask[1][2] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
- context->rsvd_bits_mask[1][1] =
+ rsvd_check->rsvd_bits_mask[1][1] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
- context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
for (pte = 0; pte < 64; pte++) {
int rwx_bits = pte & 7;
@@ -3707,10 +3729,64 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
rwx_bits == 0x2 || rwx_bits == 0x6 ||
(rwx_bits == 0x4 && !execonly))
- context->bad_mt_xwr |= (1ull << pte);
+ rsvd_check->bad_mt_xwr |= (1ull << pte);
}
}
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context, bool execonly)
+{
+ __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check,
+ cpuid_maxphyaddr(vcpu), execonly);
+}
+
+/*
+ * the page table on host is the shadow page table for the page
+ * table in guest or amd nested guest, its mmu features completely
+ * follow the features in guest.
+ */
+void
+reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
+{
+ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+ boot_cpu_data.x86_phys_bits,
+ context->shadow_root_level, context->nx,
+ guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+}
+EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
+
+/*
+ * the direct page table on host, use as much mmu features as
+ * possible, however, kvm currently does not do execution-protection.
+ */
+static void
+reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
+{
+ if (guest_cpuid_is_amd(vcpu))
+ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+ boot_cpu_data.x86_phys_bits,
+ context->shadow_root_level, false,
+ cpu_has_gbpages, true);
+ else
+ __reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+ boot_cpu_data.x86_phys_bits,
+ false);
+
+}
+
+/*
+ * as the comments in reset_shadow_zero_bits_mask() except it
+ * is the shadow page table for intel nested guest.
+ */
+static void
+reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context, bool execonly)
+{
+ __reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+ boot_cpu_data.x86_phys_bits, execonly);
+}
+
static void update_permission_bitmask(struct kvm_vcpu *vcpu,
struct kvm_mmu *mmu, bool ept)
{
@@ -3889,6 +3965,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
update_permission_bitmask(vcpu, context, false);
update_last_pte_bitmap(vcpu, context);
+ reset_tdp_shadow_zero_bits_mask(vcpu, context);
}
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
@@ -3916,6 +3993,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
context->base_role.smap_andnot_wp
= smap && !is_write_protection(vcpu);
context->base_role.smm = is_smm(vcpu);
+ reset_shadow_zero_bits_mask(vcpu, context);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
@@ -3939,6 +4017,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly)
update_permission_bitmask(vcpu, context, true);
reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+ reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
@@ -4860,28 +4939,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
return nr_mmu_pages;
}
-int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
-{
- struct kvm_shadow_walk_iterator iterator;
- u64 spte;
- int nr_sptes = 0;
-
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
- return nr_sptes;
-
- walk_shadow_page_lockless_begin(vcpu);
- for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
- sptes[iterator.level-1] = spte;
- nr_sptes++;
- if (!is_shadow_present_pte(spte))
- break;
- }
- walk_shadow_page_lockless_end(vcpu);
-
- return nr_sptes;
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
-
void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
{
kvm_mmu_unload(vcpu);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 398d21c..e4202e4 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -50,9 +50,11 @@ static inline u64 rsvd_bits(int s, int e)
return ((1ULL << (e - s + 1)) - 1) << s;
}
-int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
+void
+reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+
/*
* Return values of handle_mmio_page_fault_common:
* RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index dc0a84a..9e8bf13 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -672,16 +672,16 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
if (iter.mtrr_disabled)
return mtrr_disabled_type();
+ /* not contained in any MTRRs. */
+ if (type == -1)
+ return mtrr_default_type(mtrr_state);
+
/*
* We just check one page, partially covered by MTRRs is
* impossible.
*/
WARN_ON(iter.partial_map);
- /* not contained in any MTRRs. */
- if (type == -1)
- return mtrr_default_type(mtrr_state);
-
return type;
}
EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 0f67d7e..736e6ab 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -128,14 +128,6 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
*access &= mask;
}
-static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
-{
- int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f;
-
- return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) |
- ((mmu->bad_mt_xwr & (1ull << low6)) != 0);
-}
-
static inline int FNAME(is_present_gpte)(unsigned long pte)
{
#if PTTYPE != PTTYPE_EPT
@@ -172,7 +164,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *spte,
u64 gpte)
{
- if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+ if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
goto no_present;
if (!FNAME(is_present_gpte)(gpte))
@@ -353,8 +345,7 @@ retry_walk:
if (unlikely(!FNAME(is_present_gpte)(pte)))
goto error;
- if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte,
- walker->level))) {
+ if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
goto error;
}
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 886aa25..39b9112 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -133,8 +133,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* MSR_K7_PERFCTRn */
pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0);
if (pmc) {
- if (!msr_info->host_initiated)
- data = (s64)data;
pmc->counter += data - pmc_read_counter(pmc);
return 0;
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 8e0c084..74d8257 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1173,6 +1173,10 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
return 0;
+ if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
+ kvm_read_cr0(vcpu) & X86_CR0_CD)
+ return _PAGE_NOCACHE;
+
mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
return mtrr2protval[mtrr];
}
@@ -1667,13 +1671,10 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if (!vcpu->fpu_active)
cr0 |= X86_CR0_TS;
- /*
- * re-enable caching here because the QEMU bios
- * does not do it - this results in some delay at
- * reboot
- */
- if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
- cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+
+ /* These are emulated via page tables. */
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+
svm->vmcb->save.cr0 = cr0;
mark_dirty(svm->vmcb, VMCB_CR);
update_cr0_intercept(svm);
@@ -2106,6 +2107,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr;
vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
vcpu->arch.mmu.shadow_root_level = get_npt_level();
+ reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 83b7b5c..da1590e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2443,10 +2443,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING |
#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_RDTSC_EXITING |
- CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW |
- CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+ CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG |
+ CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING |
+ CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING |
+ CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
/*
* We can allow some features even when not supported by the
* hardware. For example, L1 can specify an MSR bitmap - and we
@@ -3423,12 +3423,12 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
vmx_segment_cache_clear(to_vmx(vcpu));
guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
- if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
+ if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) {
pr_debug_ratelimited("%s: tss fixup for long mode. \n",
__func__);
vmcs_write32(GUEST_TR_AR_BYTES,
- (guest_tr_ar & ~AR_TYPE_MASK)
- | AR_TYPE_BUSY_64_TSS);
+ (guest_tr_ar & ~VMX_AR_TYPE_MASK)
+ | VMX_AR_TYPE_BUSY_64_TSS);
}
vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
}
@@ -3719,7 +3719,7 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu)
return 0;
else {
int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
- return AR_DPL(ar);
+ return VMX_AR_DPL(ar);
}
}
@@ -3847,11 +3847,11 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu)
if (cs.unusable)
return false;
- if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK))
+ if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK))
return false;
if (!cs.s)
return false;
- if (cs.type & AR_TYPE_WRITEABLE_MASK) {
+ if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) {
if (cs.dpl > cs_rpl)
return false;
} else {
@@ -3901,7 +3901,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
return false;
if (!var.present)
return false;
- if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) {
+ if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) {
if (var.dpl < rpl) /* DPL < RPL */
return false;
}
@@ -5759,73 +5759,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
}
-static u64 ept_rsvd_mask(u64 spte, int level)
-{
- int i;
- u64 mask = 0;
-
- for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
- mask |= (1ULL << i);
-
- if (level == 4)
- /* bits 7:3 reserved */
- mask |= 0xf8;
- else if (spte & (1ULL << 7))
- /*
- * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively,
- * level == 1 if the hypervisor is using the ignored bit 7.
- */
- mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE;
- else if (level > 1)
- /* bits 6:3 reserved */
- mask |= 0x78;
-
- return mask;
-}
-
-static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
- int level)
-{
- printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level);
-
- /* 010b (write-only) */
- WARN_ON((spte & 0x7) == 0x2);
-
- /* 110b (write/execute) */
- WARN_ON((spte & 0x7) == 0x6);
-
- /* 100b (execute-only) and value not supported by logical processor */
- if (!cpu_has_vmx_ept_execute_only())
- WARN_ON((spte & 0x7) == 0x4);
-
- /* not 000b */
- if ((spte & 0x7)) {
- u64 rsvd_bits = spte & ept_rsvd_mask(spte, level);
-
- if (rsvd_bits != 0) {
- printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n",
- __func__, rsvd_bits);
- WARN_ON(1);
- }
-
- /* bits 5:3 are _not_ reserved for large page or leaf page */
- if ((rsvd_bits & 0x38) == 0) {
- u64 ept_mem_type = (spte & 0x38) >> 3;
-
- if (ept_mem_type == 2 || ept_mem_type == 3 ||
- ept_mem_type == 7) {
- printk(KERN_ERR "%s: ept_mem_type=0x%llx\n",
- __func__, ept_mem_type);
- WARN_ON(1);
- }
- }
- }
-}
-
static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
{
- u64 sptes[4];
- int nr_sptes, i, ret;
+ int ret;
gpa_t gpa;
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
@@ -5846,13 +5782,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
return 1;
/* It is the real ept misconfig */
- printk(KERN_ERR "EPT: Misconfiguration.\n");
- printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
-
- nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes);
-
- for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i)
- ept_misconfig_inspect_spte(vcpu, sptes[i-1], i);
+ WARN_ON(1);
vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;
@@ -6246,6 +6176,11 @@ static int handle_mwait(struct kvm_vcpu *vcpu)
return handle_nop(vcpu);
}
+static int handle_monitor_trap(struct kvm_vcpu *vcpu)
+{
+ return 1;
+}
+
static int handle_monitor(struct kvm_vcpu *vcpu)
{
printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
@@ -6408,8 +6343,12 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
*/
static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
unsigned long exit_qualification,
- u32 vmx_instruction_info, gva_t *ret)
+ u32 vmx_instruction_info, bool wr, gva_t *ret)
{
+ gva_t off;
+ bool exn;
+ struct kvm_segment s;
+
/*
* According to Vol. 3B, "Information for VM Exits Due to Instruction
* Execution", on an exit, vmx_instruction_info holds most of the
@@ -6434,22 +6373,63 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
/* Addr = segment_base + offset */
/* offset = base + [index * scale] + displacement */
- *ret = vmx_get_segment_base(vcpu, seg_reg);
+ off = exit_qualification; /* holds the displacement */
if (base_is_valid)
- *ret += kvm_register_read(vcpu, base_reg);
+ off += kvm_register_read(vcpu, base_reg);
if (index_is_valid)
- *ret += kvm_register_read(vcpu, index_reg)<<scaling;
- *ret += exit_qualification; /* holds the displacement */
+ off += kvm_register_read(vcpu, index_reg)<<scaling;
+ vmx_get_segment(vcpu, &s, seg_reg);
+ *ret = s.base + off;
if (addr_size == 1) /* 32 bit */
*ret &= 0xffffffff;
- /*
- * TODO: throw #GP (and return 1) in various cases that the VM*
- * instructions require it - e.g., offset beyond segment limit,
- * unusable or unreadable/unwritable segment, non-canonical 64-bit
- * address, and so on. Currently these are not checked.
- */
+ /* Checks for #GP/#SS exceptions. */
+ exn = false;
+ if (is_protmode(vcpu)) {
+ /* Protected mode: apply checks for segment validity in the
+ * following order:
+ * - segment type check (#GP(0) may be thrown)
+ * - usability check (#GP(0)/#SS(0))
+ * - limit check (#GP(0)/#SS(0))
+ */
+ if (wr)
+ /* #GP(0) if the destination operand is located in a
+ * read-only data segment or any code segment.
+ */
+ exn = ((s.type & 0xa) == 0 || (s.type & 8));
+ else
+ /* #GP(0) if the source operand is located in an
+ * execute-only code segment
+ */
+ exn = ((s.type & 0xa) == 8);
+ }
+ if (exn) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
+ if (is_long_mode(vcpu)) {
+ /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+ * non-canonical form. This is an only check for long mode.
+ */
+ exn = is_noncanonical_address(*ret);
+ } else if (is_protmode(vcpu)) {
+ /* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
+ */
+ exn = (s.unusable != 0);
+ /* Protected mode: #GP(0)/#SS(0) if the memory
+ * operand is outside the segment limit.
+ */
+ exn = exn || (off + sizeof(u64) > s.limit);
+ }
+ if (exn) {
+ kvm_queue_exception_e(vcpu,
+ seg_reg == VCPU_SREG_SS ?
+ SS_VECTOR : GP_VECTOR,
+ 0);
+ return 1;
+ }
+
return 0;
}
@@ -6471,7 +6451,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
int maxphyaddr = cpuid_maxphyaddr(vcpu);
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
- vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+ vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
return 1;
if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
@@ -6999,7 +6979,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
field_value);
} else {
if (get_vmx_mem_address(vcpu, exit_qualification,
- vmx_instruction_info, &gva))
+ vmx_instruction_info, true, &gva))
return 1;
/* _system ok, as nested_vmx_check_permission verified cpl=0 */
kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
@@ -7036,7 +7016,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
(((vmx_instruction_info) >> 3) & 0xf));
else {
if (get_vmx_mem_address(vcpu, exit_qualification,
- vmx_instruction_info, &gva))
+ vmx_instruction_info, false, &gva))
return 1;
if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
&field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
@@ -7128,7 +7108,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
return 1;
if (get_vmx_mem_address(vcpu, exit_qualification,
- vmx_instruction_info, &vmcs_gva))
+ vmx_instruction_info, true, &vmcs_gva))
return 1;
/* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */
if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
@@ -7184,7 +7164,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
* operand is read even if it isn't needed (e.g., for type==global)
*/
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
- vmx_instruction_info, &gva))
+ vmx_instruction_info, false, &gva))
return 1;
if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
sizeof(operand), &e)) {
@@ -7282,6 +7262,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig,
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
[EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait,
+ [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap,
[EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor,
[EXIT_REASON_INVEPT] = handle_invept,
[EXIT_REASON_INVVPID] = handle_invvpid,
@@ -7542,6 +7523,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
return true;
case EXIT_REASON_MWAIT_INSTRUCTION:
return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
+ case EXIT_REASON_MONITOR_TRAP_FLAG:
+ return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
case EXIT_REASON_MONITOR_INSTRUCTION:
return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
case EXIT_REASON_PAUSE_INSTRUCTION:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5ef2560..4bbc2a1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -29,6 +29,7 @@
#include "cpuid.h"
#include "assigned-dev.h"
#include "pmu.h"
+#include "hyperv.h"
#include <linux/clocksource.h>
#include <linux/interrupt.h>
@@ -221,11 +222,9 @@ static void shared_msr_update(unsigned slot, u32 msr)
void kvm_define_shared_msr(unsigned slot, u32 msr)
{
BUG_ON(slot >= KVM_NR_SHARED_MSRS);
+ shared_msrs_global.msrs[slot] = msr;
if (slot >= shared_msrs_global.nr)
shared_msrs_global.nr = slot + 1;
- shared_msrs_global.msrs[slot] = msr;
- /* we need ensured the shared_msr_global have been updated */
- smp_wmb();
}
EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
@@ -526,7 +525,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
}
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
if (is_present_gpte(pdpte[i]) &&
- (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
+ (pdpte[i] &
+ vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
ret = 0;
goto out;
}
@@ -949,6 +949,8 @@ static u32 emulated_msrs[] = {
MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
+ HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
+ HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
MSR_KVM_PV_EOI_EN,
@@ -1217,11 +1219,6 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
__func__, base_khz, scaled_khz, shift, *pmultiplier);
}
-static inline u64 get_kernel_ns(void)
-{
- return ktime_get_boot_ns();
-}
-
#ifdef CONFIG_X86_64
static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
#endif
@@ -1869,123 +1866,6 @@ out:
return r;
}
-static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
-{
- return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
-}
-
-static bool kvm_hv_msr_partition_wide(u32 msr)
-{
- bool r = false;
- switch (msr) {
- case HV_X64_MSR_GUEST_OS_ID:
- case HV_X64_MSR_HYPERCALL:
- case HV_X64_MSR_REFERENCE_TSC:
- case HV_X64_MSR_TIME_REF_COUNT:
- r = true;
- break;
- }
-
- return r;
-}
-
-static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
- struct kvm *kvm = vcpu->kvm;
-
- switch (msr) {
- case HV_X64_MSR_GUEST_OS_ID:
- kvm->arch.hv_guest_os_id = data;
- /* setting guest os id to zero disables hypercall page */
- if (!kvm->arch.hv_guest_os_id)
- kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
- break;
- case HV_X64_MSR_HYPERCALL: {
- u64 gfn;
- unsigned long addr;
- u8 instructions[4];
-
- /* if guest os id is not set hypercall should remain disabled */
- if (!kvm->arch.hv_guest_os_id)
- break;
- if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
- kvm->arch.hv_hypercall = data;
- break;
- }
- gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
- addr = gfn_to_hva(kvm, gfn);
- if (kvm_is_error_hva(addr))
- return 1;
- kvm_x86_ops->patch_hypercall(vcpu, instructions);
- ((unsigned char *)instructions)[3] = 0xc3; /* ret */
- if (__copy_to_user((void __user *)addr, instructions, 4))
- return 1;
- kvm->arch.hv_hypercall = data;
- mark_page_dirty(kvm, gfn);
- break;
- }
- case HV_X64_MSR_REFERENCE_TSC: {
- u64 gfn;
- HV_REFERENCE_TSC_PAGE tsc_ref;
- memset(&tsc_ref, 0, sizeof(tsc_ref));
- kvm->arch.hv_tsc_page = data;
- if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
- break;
- gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
- if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
- &tsc_ref, sizeof(tsc_ref)))
- return 1;
- mark_page_dirty(kvm, gfn);
- break;
- }
- default:
- vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
- "data 0x%llx\n", msr, data);
- return 1;
- }
- return 0;
-}
-
-static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
- switch (msr) {
- case HV_X64_MSR_APIC_ASSIST_PAGE: {
- u64 gfn;
- unsigned long addr;
-
- if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
- vcpu->arch.hv_vapic = data;
- if (kvm_lapic_enable_pv_eoi(vcpu, 0))
- return 1;
- break;
- }
- gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
- addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
- if (kvm_is_error_hva(addr))
- return 1;
- if (__clear_user((void __user *)addr, PAGE_SIZE))
- return 1;
- vcpu->arch.hv_vapic = data;
- kvm_vcpu_mark_page_dirty(vcpu, gfn);
- if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
- return 1;
- break;
- }
- case HV_X64_MSR_EOI:
- return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
- case HV_X64_MSR_ICR:
- return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
- case HV_X64_MSR_TPR:
- return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
- default:
- vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
- "data 0x%llx\n", msr, data);
- return 1;
- }
-
- return 0;
-}
-
static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
{
gpa_t gpa = data & ~0x3f;
@@ -2105,7 +1985,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (guest_cpuid_has_tsc_adjust(vcpu)) {
if (!msr_info->host_initiated) {
s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
- kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true);
+ adjust_tsc_offset_guest(vcpu, adj);
}
vcpu->arch.ia32_tsc_adjust_msr = data;
}
@@ -2224,15 +2104,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
*/
break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
- if (kvm_hv_msr_partition_wide(msr)) {
- int r;
- mutex_lock(&vcpu->kvm->lock);
- r = set_msr_hyperv_pw(vcpu, msr, data);
- mutex_unlock(&vcpu->kvm->lock);
- return r;
- } else
- return set_msr_hyperv(vcpu, msr, data);
- break;
+ case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+ case HV_X64_MSR_CRASH_CTL:
+ return kvm_hv_set_msr_common(vcpu, msr, data,
+ msr_info->host_initiated);
case MSR_IA32_BBL_CR_CTL3:
/* Drop writes to this legacy MSR -- see rdmsr
* counterpart for further detail.
@@ -2315,68 +2190,6 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
return 0;
}
-static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
- u64 data = 0;
- struct kvm *kvm = vcpu->kvm;
-
- switch (msr) {
- case HV_X64_MSR_GUEST_OS_ID:
- data = kvm->arch.hv_guest_os_id;
- break;
- case HV_X64_MSR_HYPERCALL:
- data = kvm->arch.hv_hypercall;
- break;
- case HV_X64_MSR_TIME_REF_COUNT: {
- data =
- div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
- break;
- }
- case HV_X64_MSR_REFERENCE_TSC:
- data = kvm->arch.hv_tsc_page;
- break;
- default:
- vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
- return 1;
- }
-
- *pdata = data;
- return 0;
-}
-
-static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
- u64 data = 0;
-
- switch (msr) {
- case HV_X64_MSR_VP_INDEX: {
- int r;
- struct kvm_vcpu *v;
- kvm_for_each_vcpu(r, v, vcpu->kvm) {
- if (v == vcpu) {
- data = r;
- break;
- }
- }
- break;
- }
- case HV_X64_MSR_EOI:
- return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
- case HV_X64_MSR_ICR:
- return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
- case HV_X64_MSR_TPR:
- return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
- case HV_X64_MSR_APIC_ASSIST_PAGE:
- data = vcpu->arch.hv_vapic;
- break;
- default:
- vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
- return 1;
- }
- *pdata = data;
- return 0;
-}
-
int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
switch (msr_info->index) {
@@ -2493,14 +2306,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = 0x20000000;
break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
- if (kvm_hv_msr_partition_wide(msr_info->index)) {
- int r;
- mutex_lock(&vcpu->kvm->lock);
- r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data);
- mutex_unlock(&vcpu->kvm->lock);
- return r;
- } else
- return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data);
+ case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+ case HV_X64_MSR_CRASH_CTL:
+ return kvm_hv_get_msr_common(vcpu,
+ msr_info->index, &msr_info->data);
break;
case MSR_IA32_BBL_CR_CTL3:
/* This legacy MSR exists but isn't fully documented in current
@@ -2651,6 +2460,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_TSC_DEADLINE_TIMER:
case KVM_CAP_ENABLE_CAP_VM:
case KVM_CAP_DISABLE_QUIRKS:
+ case KVM_CAP_SET_BOOT_CPU_ID:
#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_PCI_2_3:
@@ -3817,30 +3627,25 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_ioapic_init(kvm);
if (r) {
mutex_lock(&kvm->slots_lock);
- kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
- &vpic->dev_master);
- kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
- &vpic->dev_slave);
- kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
- &vpic->dev_eclr);
+ kvm_destroy_pic(vpic);
mutex_unlock(&kvm->slots_lock);
- kfree(vpic);
goto create_irqchip_unlock;
}
} else
goto create_irqchip_unlock;
- smp_wmb();
- kvm->arch.vpic = vpic;
- smp_wmb();
r = kvm_setup_default_irq_routing(kvm);
if (r) {
mutex_lock(&kvm->slots_lock);
mutex_lock(&kvm->irq_lock);
kvm_ioapic_destroy(kvm);
- kvm_destroy_pic(kvm);
+ kvm_destroy_pic(vpic);
mutex_unlock(&kvm->irq_lock);
mutex_unlock(&kvm->slots_lock);
+ goto create_irqchip_unlock;
}
+ /* Write kvm->irq_routing before kvm->arch.vpic. */
+ smp_wmb();
+ kvm->arch.vpic = vpic;
create_irqchip_unlock:
mutex_unlock(&kvm->lock);
break;
@@ -3967,6 +3772,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_vm_ioctl_reinject(kvm, &control);
break;
}
+ case KVM_SET_BOOT_CPU_ID:
+ r = 0;
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus) != 0)
+ r = -EBUSY;
+ else
+ kvm->arch.bsp_vcpu_id = arg;
+ mutex_unlock(&kvm->lock);
+ break;
case KVM_XEN_HVM_CONFIG: {
r = -EFAULT;
if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
@@ -5882,66 +5696,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
-int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
-{
- u64 param, ingpa, outgpa, ret;
- uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
- bool fast, longmode;
-
- /*
- * hypercall generates UD from non zero cpl and real mode
- * per HYPER-V spec
- */
- if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
- return 0;
- }
-
- longmode = is_64_bit_mode(vcpu);
-
- if (!longmode) {
- param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
- (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
- ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
- (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
- outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
- (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
- }
-#ifdef CONFIG_X86_64
- else {
- param = kvm_register_read(vcpu, VCPU_REGS_RCX);
- ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
- outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
- }
-#endif
-
- code = param & 0xffff;
- fast = (param >> 16) & 0x1;
- rep_cnt = (param >> 32) & 0xfff;
- rep_idx = (param >> 48) & 0xfff;
-
- trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
-
- switch (code) {
- case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
- kvm_vcpu_on_spin(vcpu);
- break;
- default:
- res = HV_STATUS_INVALID_HYPERCALL_CODE;
- break;
- }
-
- ret = res | (((u64)rep_done & 0xfff) << 32);
- if (longmode) {
- kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
- } else {
- kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
- kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
- }
-
- return 1;
-}
-
/*
* kvm_pv_kick_cpu_op: Kick a vcpu.
*
@@ -6327,6 +6081,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
static void process_smi(struct kvm_vcpu *vcpu)
{
struct kvm_segment cs, ds;
+ struct desc_ptr dt;
char buf[512];
u32 cr0;
@@ -6359,6 +6114,10 @@ static void process_smi(struct kvm_vcpu *vcpu)
kvm_x86_ops->set_cr4(vcpu, 0);
+ /* Undocumented: IDT limit is set to zero on entry to SMM. */
+ dt.address = dt.size = 0;
+ kvm_x86_ops->set_idt(vcpu, &dt);
+
__kvm_set_dr(vcpu, 7, DR7_FIXED_1);
cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
@@ -6513,6 +6272,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
vcpu_scan_ioapic(vcpu);
if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
kvm_vcpu_reload_apic_access_page(vcpu);
+ if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
+ vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+ vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
+ r = 0;
+ goto out;
+ }
}
if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -7535,6 +7300,17 @@ void kvm_arch_check_processor_compat(void *rtn)
kvm_x86_ops->check_processor_compatibility(rtn);
}
+bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
+{
+ return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);
+
+bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
+{
+ return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
+}
+
bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
{
return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 0ca2f3e..2f822cd 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -147,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
return kvm_register_write(vcpu, reg, val);
}
+static inline u64 get_kernel_ns(void)
+{
+ return ktime_get_boot_ns();
+}
+
static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
{
return !(kvm->arch.disabled_quirks & quirk);
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index f37e84a..3d8f2e4 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -29,7 +29,6 @@
#include <asm/uaccess.h>
#include <asm/traps.h>
-#include <asm/desc.h>
#include <asm/user.h>
#include <asm/fpu/internal.h>
@@ -181,7 +180,7 @@ void math_emulate(struct math_emu_info *info)
math_abort(FPU_info, SIGILL);
}
- code_descriptor = LDT_DESCRIPTOR(FPU_CS);
+ code_descriptor = FPU_get_ldt_descriptor(FPU_CS);
if (SEG_D_SIZE(code_descriptor)) {
/* The above test may be wrong, the book is not clear */
/* Segmented 32 bit protected mode */
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 9ccecb6..5e044d5 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -16,9 +16,24 @@
#include <linux/kernel.h>
#include <linux/mm.h>
-/* s is always from a cpu register, and the cpu does bounds checking
- * during register load --> no further bounds checks needed */
-#define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3])
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg)
+{
+ static struct desc_struct zero_desc;
+ struct desc_struct ret = zero_desc;
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ seg >>= 3;
+ mutex_lock(&current->mm->context.lock);
+ if (current->mm->context.ldt && seg < current->mm->context.ldt->size)
+ ret = current->mm->context.ldt->entries[seg];
+ mutex_unlock(&current->mm->context.lock);
+#endif
+ return ret;
+}
+
#define SEG_D_SIZE(x) ((x).b & (3 << 21))
#define SEG_G_BIT(x) ((x).b & (1 << 23))
#define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1)
diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c
index 6ef5e99..8300db7 100644
--- a/arch/x86/math-emu/get_address.c
+++ b/arch/x86/math-emu/get_address.c
@@ -20,7 +20,6 @@
#include <linux/stddef.h>
#include <asm/uaccess.h>
-#include <asm/desc.h>
#include "fpu_system.h"
#include "exception.h"
@@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment,
addr->selector = PM_REG_(segment);
}
- descriptor = LDT_DESCRIPTOR(PM_REG_(segment));
+ descriptor = FPU_get_ldt_descriptor(addr->selector);
base_address = SEG_BASE_ADDR(descriptor);
address = base_address + offset;
limit = base_address
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 579a8fd..be2e7a2 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -269,7 +269,7 @@ static void emit_bpf_tail_call(u8 **pprog)
EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */
offsetof(struct bpf_array, map.max_entries));
EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */
-#define OFFSET1 44 /* number of bytes to jump */
+#define OFFSET1 47 /* number of bytes to jump */
EMIT2(X86_JBE, OFFSET1); /* jbe out */
label1 = cnt;
@@ -278,15 +278,15 @@ static void emit_bpf_tail_call(u8 **pprog)
*/
EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 33
+#define OFFSET2 36
EMIT2(X86_JA, OFFSET2); /* ja out */
label2 = cnt;
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
/* prog = array->prog[index]; */
- EMIT4(0x48, 0x8D, 0x44, 0xD6); /* lea rax, [rsi + rdx * 8 + 0x50] */
- EMIT1(offsetof(struct bpf_array, prog));
+ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
+ offsetof(struct bpf_array, prog));
EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */
/* if (prog == NULL)
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index cfba30f..e4308fe 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -972,6 +972,11 @@ u64 efi_mem_attributes(unsigned long phys_addr)
static int __init arch_parse_efi_cmdline(char *str)
{
+ if (!str) {
+ pr_warn("need at least one option\n");
+ return -EINVAL;
+ }
+
if (parse_option_str(str, "old_map"))
set_bit(EFI_OLD_MEMMAP, &efi.flags);
if (parse_option_str(str, "debug"))
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0d7dd1f..9ab5279 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -22,6 +22,7 @@
#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
#include <asm/cpu.h>
+#include <asm/mmu_context.h>
#ifdef CONFIG_X86_32
__visible unsigned long saved_context_ebx;
@@ -153,7 +154,7 @@ static void fix_processor_context(void)
syscall_init(); /* This sets MSR_*STAR and related */
#endif
load_TR_desc(); /* This does ltr */
- load_LDT(&current->active_mm->context); /* This does lldt */
+ load_mm_ldt(current->active_mm); /* This does lldt */
fpu__resume_cpu();
}
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index e88fda8..4841453 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -8,7 +8,7 @@ config XEN
select PARAVIRT_CLOCK
select XEN_HAVE_PVMMU
depends on X86_64 || (X86_32 && X86_PAE)
- depends on X86_TSC
+ depends on X86_LOCAL_APIC && X86_TSC
help
This is the Linux Xen port. Enabling this will allow the
kernel to boot in a paravirtualized environment under the
@@ -17,7 +17,7 @@ config XEN
config XEN_DOM0
def_bool y
depends on XEN && PCI_XEN && SWIOTLB_XEN
- depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI
+ depends on X86_IO_APIC && ACPI && PCI
config XEN_PVHVM
def_bool y
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 7322755..4b6e29a 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -13,13 +13,13 @@ CFLAGS_mmu.o := $(nostackp)
obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \
time.o xen-asm.o xen-asm_$(BITS).o \
grant-table.o suspend.o platform-pci-unplug.o \
- p2m.o
+ p2m.o apic.o
obj-$(CONFIG_EVENT_TRACING) += trace.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
-obj-$(CONFIG_XEN_DOM0) += apic.o vga.o
+obj-$(CONFIG_XEN_DOM0) += vga.o
obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o
obj-$(CONFIG_XEN_EFI) += efi.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0b95c9b..11d6fb4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
pte_t pte;
unsigned long pfn;
struct page *page;
+ unsigned char dummy;
ptep = lookup_address((unsigned long)v, &level);
BUG_ON(ptep == NULL);
@@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot)
pte = pfn_pte(pfn, prot);
+ /*
+ * Careful: update_va_mapping() will fail if the virtual address
+ * we're poking isn't populated in the page tables. We don't
+ * need to worry about the direct map (that's always in the page
+ * tables), but we need to be careful about vmap space. In
+ * particular, the top level page table can lazily propagate
+ * entries between processes, so if we've switched mms since we
+ * vmapped the target in the first place, we might not have the
+ * top-level page table entry populated.
+ *
+ * We disable preemption because we want the same mm active when
+ * we probe the target and when we issue the hypercall. We'll
+ * have the same nominal mm, but if we're a kernel thread, lazy
+ * mm dropping could change our pgd.
+ *
+ * Out of an abundance of caution, this uses __get_user() to fault
+ * in the target address just in case there's some obscure case
+ * in which the target address isn't readable.
+ */
+
+ preempt_disable();
+
+ pagefault_disable(); /* Avoid warnings due to being atomic. */
+ __get_user(dummy, (unsigned char __user __force *)v);
+ pagefault_enable();
+
if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
BUG();
@@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)
BUG();
} else
kmap_flush_unused();
+
+ preempt_enable();
}
static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
int i;
+ /*
+ * We need to mark the all aliases of the LDT pages RO. We
+ * don't need to call vm_flush_aliases(), though, since that's
+ * only responsible for flushing aliases out the TLBs, not the
+ * page tables, and Xen will flush the TLB for us if needed.
+ *
+ * To avoid confusing future readers: none of this is necessary
+ * to load the LDT. The hypervisor only checks this when the
+ * LDT is faulted in due to subsequent descriptor access.
+ */
+
for(i = 0; i < entries; i += entries_per_page)
set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
}
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c20fe29..2292721 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -101,17 +101,15 @@ struct dom0_vga_console_info;
#ifdef CONFIG_XEN_DOM0
void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
-void __init xen_init_apic(void);
#else
static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
size_t size)
{
}
-static inline void __init xen_init_apic(void)
-{
-}
#endif
+void __init xen_init_apic(void);
+
#ifdef CONFIG_XEN_EFI
extern void xen_efi_init(void);
#else