linux_dsm_epyc7002/arch/x86/include/asm/ptrace.h
Andy Lutomirski e0ffbaabc4 x86: Split syscall_trace_enter into two phases
This splits syscall_trace_enter into syscall_trace_enter_phase1 and
syscall_trace_enter_phase2.  Only phase 2 has full pt_regs, and only
phase 2 is permitted to modify any of pt_regs except for orig_ax.

The intent is that phase 1 can be called from the syscall fast path.

In this implementation, phase1 can handle any combination of
TIF_NOHZ (RCU context tracking), TIF_SECCOMP, and TIF_SYSCALL_AUDIT,
unless seccomp requests a ptrace event, in which case phase2 is
forced.

In principle, this could yield a big speedup for TIF_NOHZ as well as
for TIF_SECCOMP if syscall exit work were similarly split up.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Link: http://lkml.kernel.org/r/2df320a600020fda055fccf2b668145729dd0c04.1409954077.git.luto@amacapital.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2014-09-08 14:14:03 -07:00

263 lines
7.0 KiB
C

#ifndef _ASM_X86_PTRACE_H
#define _ASM_X86_PTRACE_H
#include <asm/segment.h>
#include <asm/page_types.h>
#include <uapi/asm/ptrace.h>
#ifndef __ASSEMBLY__
#ifdef __i386__
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;
};
#else /* __i386__ */
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 /* !__i386__ */
#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);
extern unsigned long syscall_trace_enter_phase1(struct pt_regs *, u32 arch);
extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch,
unsigned long phase1_result);
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
}
#define current_user_stack_pointer() this_cpu_read(old_rsp)
/* ia32 vs. x32 difference */
#define compat_user_stack_pointer() \
(test_thread_flag(TIF_IA32) \
? current_pt_regs()->sp \
: this_cpu_read(old_rsp))
#endif
#ifdef CONFIG_X86_32
extern unsigned long kernel_stack_pointer(struct pt_regs *regs);
#else
static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
{
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;
#ifdef CONFIG_X86_32
/*
* Traps from the kernel do not save sp and ss.
* Use the helper function to retrieve sp.
*/
if (offset == offsetof(struct pt_regs, sp) &&
regs->cs == __KERNEL_CS)
return kernel_stack_pointer(regs);
#endif
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
/*
* When hitting ptrace_stop(), we cannot return using SYSRET because
* that does not restore the full CPU state, only a minimal set. The
* ptracer can change arbitrary register values, which is usually okay
* because the usual ptrace stops run off the signal delivery path which
* forces IRET; however, ptrace_event() stops happen in arbitrary places
* in the kernel and don't force IRET path.
*
* So force IRET path after a ptrace stop.
*/
#define arch_ptrace_stop_needed(code, info) \
({ \
set_thread_flag(TIF_NOTIFY_RESUME); \
false; \
})
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 /* !__ASSEMBLY__ */
#endif /* _ASM_X86_PTRACE_H */