$(call cc-option,-fno-unit-at-a-time))
# CPU-specific tuning. Anything which can be shared with UML should go here.
- include $(srctree)/arch/x86/Makefile_32.cpu
+ include arch/x86/Makefile_32.cpu
KBUILD_CFLAGS += $(cflags-y)
# temporary until string.h is fixed
# Use -mpreferred-stack-boundary=3 if supported.
KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+ # Use -mskip-rax-setup if supported.
+ KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
+
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
swapgs
sysretl
ENDPROC(native_usergs_sysret32)
-
-ENTRY(native_irq_enable_sysexit)
- swapgs
- sti
- sysexit
-ENDPROC(native_irq_enable_sysexit)
#endif
/*
pushq_cfi_reg rsi /* pt_regs->si */
pushq_cfi_reg rdx /* pt_regs->dx */
pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
+ pushq_cfi $-ENOSYS /* pt_regs->ax */
cld
sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
CFI_ADJUST_CFA_OFFSET 10*8
testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
CFI_REMEMBER_STATE
jnz sysenter_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
sysenter_do_call:
/* 32bit syscall -> 64bit C ABI argument conversion */
movl %edi,%r8d /* arg5 */
movl %ebx,%edi /* arg1 */
movl %edx,%edx /* arg3 (zero extension) */
sysenter_dispatch:
+ cmpq $(IA32_NR_syscalls-1),%rax
+ ja 1f
call *ia32_sys_call_table(,%rax,8)
movq %rax,RAX(%rsp)
+1:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
movl %ebx,%esi /* 2nd arg: 1st syscall arg */
movl %eax,%edi /* 1st arg: syscall number */
call __audit_syscall_entry
- movl RAX(%rsp),%eax /* reload syscall number */
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
+ movl ORIG_RAX(%rsp),%eax /* reload syscall number */
movl %ebx,%edi /* reload 1st syscall arg */
movl RCX(%rsp),%esi /* reload 2nd syscall arg */
movl RDX(%rsp),%edx /* reload 3rd syscall arg */
#endif
SAVE_EXTRA_REGS
CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
jmp sysenter_do_call
CFI_ENDPROC
ENDPROC(ia32_sysenter_target)
pushq_cfi_reg rdx /* pt_regs->dx */
pushq_cfi_reg rbp /* pt_regs->cx */
movl %ebp,%ecx
- pushq_cfi_reg rax /* pt_regs->ax */
+ pushq_cfi $-ENOSYS /* pt_regs->ax */
sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
CFI_ADJUST_CFA_OFFSET 10*8
testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
CFI_REMEMBER_STATE
jnz cstar_tracesys
- cmpq $IA32_NR_syscalls-1,%rax
- ja ia32_badsys
cstar_do_call:
/* 32bit syscall -> 64bit C ABI argument conversion */
movl %edi,%r8d /* arg5 */
movl %ebx,%edi /* arg1 */
movl %edx,%edx /* arg3 (zero extension) */
cstar_dispatch:
+ cmpq $(IA32_NR_syscalls-1),%rax
+ ja 1f
call *ia32_sys_call_table(,%rax,8)
movq %rax,RAX(%rsp)
+1:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
* cs and ss are loaded from MSRs.
* (Note: 32bit->32bit SYSRET is different: since r11
* does not exist, it merely sets eflags.IF=1).
+ *
+ * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+ * descriptor is not reinitialized. This means that we must
+ * avoid SYSRET with SS == NULL, which could happen if we schedule,
+ * exit the kernel, and re-enter using an interrupt vector. (All
+ * interrupt entries on x86_64 set SS to NULL.) We prevent that
+ * from happening by reloading SS in __switch_to.
*/
USERGS_SYSRET32
xchgl %r9d,%ebp
SAVE_EXTRA_REGS
CLEAR_RREGS r9
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
xchgl %ebp,%r9d
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
jmp cstar_do_call
END(ia32_cstar_target)
pushq_cfi_reg rsi /* pt_regs->si */
pushq_cfi_reg rdx /* pt_regs->dx */
pushq_cfi_reg rcx /* pt_regs->cx */
- pushq_cfi_reg rax /* pt_regs->ax */
+ pushq_cfi $-ENOSYS /* pt_regs->ax */
cld
sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
CFI_ADJUST_CFA_OFFSET 10*8
orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
jnz ia32_tracesys
- cmpq $(IA32_NR_syscalls-1),%rax
- ja ia32_badsys
ia32_do_call:
/* 32bit syscall -> 64bit C ABI argument conversion */
movl %edi,%r8d /* arg5 */
xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */
movl %ebx,%edi /* arg1 */
movl %edx,%edx /* arg3 (zero extension) */
+ cmpq $(IA32_NR_syscalls-1),%rax
+ ja 1f
call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
ia32_sysret:
movq %rax,RAX(%rsp)
+1:
ia32_ret_from_sys_call:
CLEAR_RREGS
jmp int_ret_from_sys_call
ia32_tracesys:
SAVE_EXTRA_REGS
CLEAR_RREGS
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
- cmpq $(IA32_NR_syscalls-1),%rax
- ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
jmp ia32_do_call
+ CFI_ENDPROC
END(ia32_syscall)
-ia32_badsys:
- movq $0,ORIG_RAX(%rsp)
- movq $-ENOSYS,%rax
- jmp ia32_sysret
-
- CFI_ENDPROC
-
.macro PTREGSCALL label, func
ALIGN
GLOBAL(\label)
u64 (*read_pmc)(int counter);
unsigned long long (*read_tscp)(unsigned int *aux);
+#ifdef CONFIG_X86_32
/*
* Atomically enable interrupts and return to userspace. This
- * is only ever used to return to 32-bit processes; in a
- * 64-bit kernel, it's used for 32-on-64 compat processes, but
- * never native 64-bit processes. (Jump, not call.)
+ * is only used in 32-bit kernels. 64-bit kernels use
+ * usergs_sysret32 instead.
*/
void (*irq_enable_sysexit)(void);
+#endif
/*
* Switch to usermode gs and return to 64-bit usermode using
struct paravirt_callee_save pgd_val;
struct paravirt_callee_save make_pgd;
- #if PAGETABLE_LEVELS >= 3
+ #if CONFIG_PGTABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
struct paravirt_callee_save pmd_val;
struct paravirt_callee_save make_pmd;
- #if PAGETABLE_LEVELS == 4
+ #if CONFIG_PGTABLE_LEVELS == 4
struct paravirt_callee_save pud_val;
struct paravirt_callee_save make_pud;
void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
- #endif /* PAGETABLE_LEVELS == 4 */
- #endif /* PAGETABLE_LEVELS >= 3 */
+ #endif /* CONFIG_PGTABLE_LEVELS == 4 */
+ #endif /* CONFIG_PGTABLE_LEVELS >= 3 */
struct pv_lazy_ops lazy_mode;
* rflags from r11 (but RF and VM bits are forced to 0),
* cs and ss are loaded from MSRs.
* Restoration of rflags re-enables interrupts.
+ *
+ * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+ * descriptor is not reinitialized. This means that we should
+ * avoid SYSRET with SS == NULL, which could happen if we schedule,
+ * exit the kernel, and re-enter using an interrupt vector. (All
+ * interrupt entries on x86_64 set SS to NULL.) We prevent that
+ * from happening by reloading SS in __switch_to. (Actually
+ * detecting the failure in 64-bit userspace is tricky but can be
+ * done.)
*/
USERGS_SYSRET64
* a completely clean 64-bit userspace context.
*/
movq RCX(%rsp),%rcx
- cmpq %rcx,RIP(%rsp) /* RCX == RIP */
+ movq RIP(%rsp),%r11
+ cmpq %rcx,%r11 /* RCX == RIP */
jne opportunistic_sysret_failed
/*
* On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
* in kernel space. This essentially lets the user take over
- * the kernel, since userspace controls RSP. It's not worth
- * testing for canonicalness exactly -- this check detects any
- * of the 17 high bits set, which is true for non-canonical
- * or kernel addresses. (This will pessimize vsyscall=native.
- * Big deal.)
+ * the kernel, since userspace controls RSP.
*
- * If virtual addresses ever become wider, this will need
+ * If width of "canonical tail" ever becomes variable, this will need
* to be updated to remain correct on both old and new CPUs.
*/
.ifne __VIRTUAL_MASK_SHIFT - 47
.error "virtual address width changed -- SYSRET checks need update"
.endif
- shr $__VIRTUAL_MASK_SHIFT, %rcx
- jnz opportunistic_sysret_failed
+ /* Change top 16 bits to be the sign-extension of 47th bit */
+ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+ sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+ /* If this changed %rcx, it was not canonical */
+ cmpq %rcx, %r11
+ jne opportunistic_sysret_failed
cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */
jne opportunistic_sysret_failed
*/
syscall_return_via_sysret:
CFI_REMEMBER_STATE
- /* r11 is already restored (see code above) */
- RESTORE_C_REGS_EXCEPT_R11
+ /* rcx and r11 are already restored (see code above) */
+ RESTORE_C_REGS_EXCEPT_RCX_R11
movq RSP(%rsp),%rsp
USERGS_SYSRET64
CFI_RESTORE_STATE
CFI_ENDPROC
END(stub_execveat)
-#ifdef CONFIG_X86_X32_ABI
+#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
.align 8
GLOBAL(stub_x32_execve)
+GLOBAL(stub32_execve)
CFI_STARTPROC
DEFAULT_FRAME 0, 8
call compat_sys_execve
jmp return_from_execve
CFI_ENDPROC
+END(stub32_execve)
END(stub_x32_execve)
.align 8
GLOBAL(stub_x32_execveat)
- CFI_STARTPROC
- DEFAULT_FRAME 0, 8
- call compat_sys_execveat
- jmp return_from_execve
- CFI_ENDPROC
-END(stub_x32_execveat)
-#endif
-
-#ifdef CONFIG_IA32_EMULATION
- .align 8
-GLOBAL(stub32_execve)
- CFI_STARTPROC
- call compat_sys_execve
- jmp return_from_execve
- CFI_ENDPROC
-END(stub32_execve)
- .align 8
GLOBAL(stub32_execveat)
CFI_STARTPROC
+ DEFAULT_FRAME 0, 8
call compat_sys_execveat
jmp return_from_execve
CFI_ENDPROC
END(stub32_execveat)
+END(stub_x32_execveat)
#endif
/*
RESTORE_EXTRA_REGS
- testl $3,CS(%rsp) # from kernel_thread?
+ testb $3, CS(%rsp) # from kernel_thread?
/*
* By the time we get here, we have no idea whether our pt_regs,
leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */
- testl $3, CS-RBP(%rsp)
- je 1f
+ testb $3, CS-RBP(%rsp)
+ jz 1f
SWAPGS
1:
/*
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET RBP
- testl $3,CS(%rsp)
- je retint_kernel
+ testb $3, CS(%rsp)
+ jz retint_kernel
/* Interrupt came from user space */
GET_THREAD_INFO(%rcx)
.if \paranoid
.if \paranoid == 1
CFI_REMEMBER_STATE
- testl $3, CS(%rsp) /* If coming from userspace, switch */
+ testb $3, CS(%rsp) /* If coming from userspace, switch */
jnz 1f /* stacks. */
.endif
call paranoid_entry
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
xorl %ebx,%ebx
- testl $3,CS+8(%rsp)
- je error_kernelspace
+ testb $3, CS+8(%rsp)
+ jz error_kernelspace
error_swapgs:
SWAPGS
error_sti:
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
testl %eax,%eax
- jne retint_kernel
+ jnz retint_kernel
LOCKDEP_SYS_EXIT_IRQ
movl TI_flags(%rcx),%edx
movl $_TIF_WORK_MASK,%edi
je 1f
movq %r12, %cr2
1:
-
testl %ebx,%ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
ret = paravirt_patch_ident_64(insnbuf, len);
else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+#ifdef CONFIG_X86_32
type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
+#endif
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
/* If operation requires a jmp, then jmp */
.load_sp0 = native_load_sp0,
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_32)
.irq_enable_sysexit = native_irq_enable_sysexit,
#endif
#ifdef CONFIG_X86_64
.ptep_modify_prot_start = __ptep_modify_prot_start,
.ptep_modify_prot_commit = __ptep_modify_prot_commit,
- #if PAGETABLE_LEVELS >= 3
+ #if CONFIG_PGTABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
.set_pte_atomic = native_set_pte_atomic,
.pte_clear = native_pte_clear,
.pmd_val = PTE_IDENT,
.make_pmd = PTE_IDENT,
- #if PAGETABLE_LEVELS == 4
+ #if CONFIG_PGTABLE_LEVELS == 4
.pud_val = PTE_IDENT,
.make_pud = PTE_IDENT,
.set_pgd = native_set_pgd,
#endif
- #endif /* PAGETABLE_LEVELS >= 3 */
+ #endif /* CONFIG_PGTABLE_LEVELS >= 3 */
.pte_val = PTE_IDENT,
.pgd_val = PTE_IDENT,
{
}
- #ifdef CONFIG_X86_LOCAL_APIC
- static unsigned long xen_set_apic_id(unsigned int x)
- {
- WARN_ON(1);
- return x;
- }
- static unsigned int xen_get_apic_id(unsigned long x)
- {
- return ((x)>>24) & 0xFFu;
- }
- static u32 xen_apic_read(u32 reg)
- {
- struct xen_platform_op op = {
- .cmd = XENPF_get_cpuinfo,
- .interface_version = XENPF_INTERFACE_VERSION,
- .u.pcpu_info.xen_cpuid = 0,
- };
- int ret = 0;
-
- /* Shouldn't need this as APIC is turned off for PV, and we only
- * get called on the bootup processor. But just in case. */
- if (!xen_initial_domain() || smp_processor_id())
- return 0;
-
- if (reg == APIC_LVR)
- return 0x10;
-
- if (reg != APIC_ID)
- return 0;
-
- ret = HYPERVISOR_dom0_op(&op);
- if (ret)
- return 0;
-
- return op.u.pcpu_info.apic_id << 24;
- }
-
- static void xen_apic_write(u32 reg, u32 val)
- {
- /* Warn to see if there's any stray references */
- WARN_ON(1);
- }
-
- static u64 xen_apic_icr_read(void)
- {
- return 0;
- }
-
- static void xen_apic_icr_write(u32 low, u32 id)
- {
- /* Warn to see if there's any stray references */
- WARN_ON(1);
- }
-
- static void xen_apic_wait_icr_idle(void)
- {
- return;
- }
-
- static u32 xen_safe_apic_wait_icr_idle(void)
- {
- return 0;
- }
-
- static void set_xen_basic_apic_ops(void)
- {
- apic->read = xen_apic_read;
- apic->write = xen_apic_write;
- apic->icr_read = xen_apic_icr_read;
- apic->icr_write = xen_apic_icr_write;
- apic->wait_icr_idle = xen_apic_wait_icr_idle;
- apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
- apic->set_apic_id = xen_set_apic_id;
- apic->get_apic_id = xen_get_apic_id;
-
- #ifdef CONFIG_SMP
- apic->send_IPI_allbutself = xen_send_IPI_allbutself;
- apic->send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself;
- apic->send_IPI_mask = xen_send_IPI_mask;
- apic->send_IPI_all = xen_send_IPI_all;
- apic->send_IPI_self = xen_send_IPI_self;
- #endif
- }
-
- #endif
-
static void xen_clts(void)
{
struct multicall_space mcs;
.read_tscp = native_read_tscp,
.iret = xen_iret,
- .irq_enable_sysexit = xen_sysexit,
#ifdef CONFIG_X86_64
.usergs_sysret32 = xen_sysret32,
.usergs_sysret64 = xen_sysret64,
+#else
+ .irq_enable_sysexit = xen_sysexit,
#endif
.load_tr_desc = paravirt_nop,
/*
* set up the basic apic ops.
*/
- set_xen_basic_apic_ops();
+ xen_init_apic();
#endif
if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
if (HYPERVISOR_dom0_op(&op) == 0)
boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
- xen_init_apic();
-
/* Make sure ACS will be enabled */
pci_request_acs();
static void __init xen_hvm_guest_init(void)
{
+ if (xen_pv_domain())
+ return;
+
init_hvm_pv_info();
xen_hvm_init_shared_info();
xen_hvm_init_time_ops();
xen_hvm_init_mmu_ops();
}
+ #endif
static bool xen_nopv = false;
static __init int xen_parse_nopv(char *arg)
}
early_param("xen_nopv", xen_parse_nopv);
- static uint32_t __init xen_hvm_platform(void)
+ static uint32_t __init xen_platform(void)
{
if (xen_nopv)
return 0;
- if (xen_pv_domain())
- return 0;
-
return xen_cpuid_base();
}
}
EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
- const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
- .name = "Xen HVM",
- .detect = xen_hvm_platform,
+ static void xen_set_cpu_features(struct cpuinfo_x86 *c)
+ {
+ if (xen_pv_domain())
+ clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+ }
+
+ const struct hypervisor_x86 x86_hyper_xen = {
+ .name = "Xen",
+ .detect = xen_platform,
+ #ifdef CONFIG_XEN_PVHVM
.init_platform = xen_hvm_guest_init,
+ #endif
.x2apic_available = xen_x2apic_para_available,
+ .set_cpu_features = xen_set_cpu_features,
};
- EXPORT_SYMBOL(x86_hyper_xen_hvm);
- #endif
+ EXPORT_SYMBOL(x86_hyper_xen);