linux_dsm_epyc7002/arch/x86/include/asm/ptrace.h
Robert Richter 1022623842 x86-32: Fix invalid stack address while in softirq
In 32 bit the stack address provided by kernel_stack_pointer() may
point to an invalid range causing NULL pointer access or page faults
while in NMI (see trace below). This happens if called in softirq
context and if the stack is empty. The address at &regs->sp is then
out of range.

Fixing this by checking if regs and &regs->sp are in the same stack
context. Otherwise return the previous stack pointer stored in struct
thread_info. If that address is invalid too, return address of regs.

 BUG: unable to handle kernel NULL pointer dereference at 0000000a
 IP: [<c1004237>] print_context_stack+0x6e/0x8d
 *pde = 00000000
 Oops: 0000 [#1] SMP
 Modules linked in:
 Pid: 4434, comm: perl Not tainted 3.6.0-rc3-oprofile-i386-standard-g4411a05 #4 Hewlett-Packard HP xw9400 Workstation/0A1Ch
 EIP: 0060:[<c1004237>] EFLAGS: 00010093 CPU: 0
 EIP is at print_context_stack+0x6e/0x8d
 EAX: ffffe000 EBX: 0000000a ECX: f4435f94 EDX: 0000000a
 ESI: f4435f94 EDI: f4435f94 EBP: f5409ec0 ESP: f5409ea0
  DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
 CR0: 8005003b CR2: 0000000a CR3: 34ac9000 CR4: 000007d0
 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
 DR6: ffff0ff0 DR7: 00000400
 Process perl (pid: 4434, ti=f5408000 task=f5637850 task.ti=f4434000)
 Stack:
  000003e8 ffffe000 00001ffc f4e39b00 00000000 0000000a f4435f94 c155198c
  f5409ef0 c1003723 c155198c f5409f04 00000000 f5409edc 00000000 00000000
  f5409ee8 f4435f94 f5409fc4 00000001 f5409f1c c12dce1c 00000000 c155198c
 Call Trace:
  [<c1003723>] dump_trace+0x7b/0xa1
  [<c12dce1c>] x86_backtrace+0x40/0x88
  [<c12db712>] ? oprofile_add_sample+0x56/0x84
  [<c12db731>] oprofile_add_sample+0x75/0x84
  [<c12ddb5b>] op_amd_check_ctrs+0x46/0x260
  [<c12dd40d>] profile_exceptions_notify+0x23/0x4c
  [<c1395034>] nmi_handle+0x31/0x4a
  [<c1029dc5>] ? ftrace_define_fields_irq_handler_entry+0x45/0x45
  [<c13950ed>] do_nmi+0xa0/0x2ff
  [<c1029dc5>] ? ftrace_define_fields_irq_handler_entry+0x45/0x45
  [<c13949e5>] nmi_stack_correct+0x28/0x2d
  [<c1029dc5>] ? ftrace_define_fields_irq_handler_entry+0x45/0x45
  [<c1003603>] ? do_softirq+0x4b/0x7f
  <IRQ>
  [<c102a06f>] irq_exit+0x35/0x5b
  [<c1018f56>] smp_apic_timer_interrupt+0x6c/0x7a
  [<c1394746>] apic_timer_interrupt+0x2a/0x30
 Code: 89 fe eb 08 31 c9 8b 45 0c ff 55 ec 83 c3 04 83 7d 10 00 74 0c 3b 5d 10 73 26 3b 5d e4 73 0c eb 1f 3b 5d f0 76 1a 3b 5d e8 73 15 <8b> 13 89 d0 89 55 e0 e8 ad 42 03 00 85 c0 8b 55 e0 75 a6 eb cc
 EIP: [<c1004237>] print_context_stack+0x6e/0x8d SS:ESP 0068:f5409ea0
 CR2: 000000000000000a
 ---[ end trace 62afee3481b00012 ]---
 Kernel panic - not syncing: Fatal exception in interrupt

V2:
* add comments to kernel_stack_pointer()
* always return a valid stack address by falling back to the address
  of regs

Reported-by: Yang Wei <wei.yang@windriver.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Robert Richter <robert.richter@amd.com>
Link: http://lkml.kernel.org/r/20120912135059.GZ8285@erda.amd.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Jun Zhang <jun.zhang@intel.com>
2012-11-20 22:23:20 -08:00

300 lines
7.0 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);
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
#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;
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 */