318f5a2a67
Three places in the kernel assume that the only long mode CPL 3
selector is __USER_CS. This is not true on Xen -- Xen's sysretq
changes cs to the magic value 0xe033.
Two of the places are corner cases, but as of "x86-64: Improve
vsyscall emulation CS and RIP handling"
(c9712944b2), vsyscalls will segfault
if called with Xen's extra CS selector. This causes a panic when
older init builds die.
It seems impossible to make Xen use __USER_CS reliably without
taking a performance hit on every system call, so this fixes the
tests instead with a new paravirt op. It's a little ugly because
ptrace.h can't include paravirt.h.
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Link: http://lkml.kernel.org/r/f4fcb3947340d9e96ce1054a432f183f9da9db83.1312378163.git.luto@mit.edu
Reported-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
307 lines
7.3 KiB
C
307 lines
7.3 KiB
C
#ifndef _ASM_X86_PTRACE_H
|
|
#define _ASM_X86_PTRACE_H
|
|
|
|
#include <linux/compiler.h> /* For __user */
|
|
#include <asm/ptrace-abi.h>
|
|
#include <asm/processor-flags.h>
|
|
|
|
#ifdef __KERNEL__
|
|
#include <asm/segment.h>
|
|
#include <asm/page_types.h>
|
|
#endif
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#ifdef __i386__
|
|
/* this struct defines the way the registers are stored on the
|
|
stack during a system call. */
|
|
|
|
#ifndef __KERNEL__
|
|
|
|
struct pt_regs {
|
|
long ebx;
|
|
long ecx;
|
|
long edx;
|
|
long esi;
|
|
long edi;
|
|
long ebp;
|
|
long eax;
|
|
int xds;
|
|
int xes;
|
|
int xfs;
|
|
int xgs;
|
|
long orig_eax;
|
|
long eip;
|
|
int xcs;
|
|
long eflags;
|
|
long esp;
|
|
int xss;
|
|
};
|
|
|
|
#else /* __KERNEL__ */
|
|
|
|
struct pt_regs {
|
|
unsigned long bx;
|
|
unsigned long cx;
|
|
unsigned long dx;
|
|
unsigned long si;
|
|
unsigned long di;
|
|
unsigned long bp;
|
|
unsigned long ax;
|
|
unsigned long ds;
|
|
unsigned long es;
|
|
unsigned long fs;
|
|
unsigned long gs;
|
|
unsigned long orig_ax;
|
|
unsigned long ip;
|
|
unsigned long cs;
|
|
unsigned long flags;
|
|
unsigned long sp;
|
|
unsigned long ss;
|
|
};
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#else /* __i386__ */
|
|
|
|
#ifndef __KERNEL__
|
|
|
|
struct pt_regs {
|
|
unsigned long r15;
|
|
unsigned long r14;
|
|
unsigned long r13;
|
|
unsigned long r12;
|
|
unsigned long rbp;
|
|
unsigned long rbx;
|
|
/* arguments: non interrupts/non tracing syscalls only save up to here*/
|
|
unsigned long r11;
|
|
unsigned long r10;
|
|
unsigned long r9;
|
|
unsigned long r8;
|
|
unsigned long rax;
|
|
unsigned long rcx;
|
|
unsigned long rdx;
|
|
unsigned long rsi;
|
|
unsigned long rdi;
|
|
unsigned long orig_rax;
|
|
/* end of arguments */
|
|
/* cpu exception frame or undefined */
|
|
unsigned long rip;
|
|
unsigned long cs;
|
|
unsigned long eflags;
|
|
unsigned long rsp;
|
|
unsigned long ss;
|
|
/* top of stack page */
|
|
};
|
|
|
|
#else /* __KERNEL__ */
|
|
|
|
struct pt_regs {
|
|
unsigned long r15;
|
|
unsigned long r14;
|
|
unsigned long r13;
|
|
unsigned long r12;
|
|
unsigned long bp;
|
|
unsigned long bx;
|
|
/* arguments: non interrupts/non tracing syscalls only save up to here*/
|
|
unsigned long r11;
|
|
unsigned long r10;
|
|
unsigned long r9;
|
|
unsigned long r8;
|
|
unsigned long ax;
|
|
unsigned long cx;
|
|
unsigned long dx;
|
|
unsigned long si;
|
|
unsigned long di;
|
|
unsigned long orig_ax;
|
|
/* end of arguments */
|
|
/* cpu exception frame or undefined */
|
|
unsigned long ip;
|
|
unsigned long cs;
|
|
unsigned long flags;
|
|
unsigned long sp;
|
|
unsigned long ss;
|
|
/* top of stack page */
|
|
};
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* !__i386__ */
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <linux/init.h>
|
|
#ifdef CONFIG_PARAVIRT
|
|
#include <asm/paravirt_types.h>
|
|
#endif
|
|
|
|
struct cpuinfo_x86;
|
|
struct task_struct;
|
|
|
|
extern unsigned long profile_pc(struct pt_regs *regs);
|
|
#define profile_pc profile_pc
|
|
|
|
extern unsigned long
|
|
convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
|
|
extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
|
|
int error_code, int si_code);
|
|
void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
|
|
|
|
extern long syscall_trace_enter(struct pt_regs *);
|
|
extern void syscall_trace_leave(struct pt_regs *);
|
|
|
|
static inline unsigned long regs_return_value(struct pt_regs *regs)
|
|
{
|
|
return regs->ax;
|
|
}
|
|
|
|
/*
|
|
* user_mode_vm(regs) determines whether a register set came from user mode.
|
|
* This is true if V8086 mode was enabled OR if the register set was from
|
|
* protected mode with RPL-3 CS value. This tricky test checks that with
|
|
* one comparison. Many places in the kernel can bypass this full check
|
|
* if they have already ruled out V8086 mode, so user_mode(regs) can be used.
|
|
*/
|
|
static inline int user_mode(struct pt_regs *regs)
|
|
{
|
|
#ifdef CONFIG_X86_32
|
|
return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL;
|
|
#else
|
|
return !!(regs->cs & 3);
|
|
#endif
|
|
}
|
|
|
|
static inline int user_mode_vm(struct pt_regs *regs)
|
|
{
|
|
#ifdef CONFIG_X86_32
|
|
return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >=
|
|
USER_RPL;
|
|
#else
|
|
return user_mode(regs);
|
|
#endif
|
|
}
|
|
|
|
static inline int v8086_mode(struct pt_regs *regs)
|
|
{
|
|
#ifdef CONFIG_X86_32
|
|
return (regs->flags & X86_VM_MASK);
|
|
#else
|
|
return 0; /* No V86 mode support in long mode */
|
|
#endif
|
|
}
|
|
|
|
#ifdef CONFIG_X86_64
|
|
static inline bool user_64bit_mode(struct pt_regs *regs)
|
|
{
|
|
#ifndef CONFIG_PARAVIRT
|
|
/*
|
|
* On non-paravirt systems, this is the only long mode CPL 3
|
|
* selector. We do not allow long mode selectors in the LDT.
|
|
*/
|
|
return regs->cs == __USER_CS;
|
|
#else
|
|
/* Headers are too twisted for this to go in paravirt.h. */
|
|
return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
|
|
#endif
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
|
|
* when it traps. The previous stack will be directly underneath the saved
|
|
* registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'.
|
|
*
|
|
* This is valid only for kernel mode traps.
|
|
*/
|
|
static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
|
|
{
|
|
#ifdef CONFIG_X86_32
|
|
return (unsigned long)(®s->sp);
|
|
#else
|
|
return regs->sp;
|
|
#endif
|
|
}
|
|
|
|
#define GET_IP(regs) ((regs)->ip)
|
|
#define GET_FP(regs) ((regs)->bp)
|
|
#define GET_USP(regs) ((regs)->sp)
|
|
|
|
#include <asm-generic/ptrace.h>
|
|
|
|
/* Query offset/name of register from its name/offset */
|
|
extern int regs_query_register_offset(const char *name);
|
|
extern const char *regs_query_register_name(unsigned int offset);
|
|
#define MAX_REG_OFFSET (offsetof(struct pt_regs, ss))
|
|
|
|
/**
|
|
* regs_get_register() - get register value from its offset
|
|
* @regs: pt_regs from which register value is gotten.
|
|
* @offset: offset number of the register.
|
|
*
|
|
* regs_get_register returns the value of a register. The @offset is the
|
|
* offset of the register in struct pt_regs address which specified by @regs.
|
|
* If @offset is bigger than MAX_REG_OFFSET, this returns 0.
|
|
*/
|
|
static inline unsigned long regs_get_register(struct pt_regs *regs,
|
|
unsigned int offset)
|
|
{
|
|
if (unlikely(offset > MAX_REG_OFFSET))
|
|
return 0;
|
|
return *(unsigned long *)((unsigned long)regs + offset);
|
|
}
|
|
|
|
/**
|
|
* regs_within_kernel_stack() - check the address in the stack
|
|
* @regs: pt_regs which contains kernel stack pointer.
|
|
* @addr: address which is checked.
|
|
*
|
|
* regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
|
|
* If @addr is within the kernel stack, it returns true. If not, returns false.
|
|
*/
|
|
static inline int regs_within_kernel_stack(struct pt_regs *regs,
|
|
unsigned long addr)
|
|
{
|
|
return ((addr & ~(THREAD_SIZE - 1)) ==
|
|
(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)));
|
|
}
|
|
|
|
/**
|
|
* regs_get_kernel_stack_nth() - get Nth entry of the stack
|
|
* @regs: pt_regs which contains kernel stack pointer.
|
|
* @n: stack entry number.
|
|
*
|
|
* regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
|
|
* is specified by @regs. If the @n th entry is NOT in the kernel stack,
|
|
* this returns 0.
|
|
*/
|
|
static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
|
|
unsigned int n)
|
|
{
|
|
unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
|
|
addr += n;
|
|
if (regs_within_kernel_stack(regs, (unsigned long)addr))
|
|
return *addr;
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
#define arch_has_single_step() (1)
|
|
#ifdef CONFIG_X86_DEBUGCTLMSR
|
|
#define arch_has_block_step() (1)
|
|
#else
|
|
#define arch_has_block_step() (boot_cpu_data.x86 >= 6)
|
|
#endif
|
|
|
|
#define ARCH_HAS_USER_SINGLE_STEP_INFO
|
|
|
|
struct user_desc;
|
|
extern int do_get_thread_area(struct task_struct *p, int idx,
|
|
struct user_desc __user *info);
|
|
extern int do_set_thread_area(struct task_struct *p, int idx,
|
|
struct user_desc __user *info, int can_allocate);
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#endif /* _ASM_X86_PTRACE_H */
|