linux/arch/powerpc/include/asm/ptrace.h

327 lines
9 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright (C) 2001 PPC64 Team, IBM Corp
*
* This struct defines the way the registers are stored on the
* kernel stack during a system call or other kernel entry.
*
* this should only contain volatile regs
* since we can keep non-volatile in the thread_struct
* should set this up when only volatiles are saved
* by intr code.
*
* Since this is going on the stack, *CARE MUST BE TAKEN* to insure
* that the overall structure is a multiple of 16 bytes in length.
*
* Note that the offsets of the fields in this struct correspond with
* the PT_* values below. This simplifies arch/powerpc/kernel/ptrace.c.
*/
#ifndef _ASM_POWERPC_PTRACE_H
#define _ASM_POWERPC_PTRACE_H
#include <uapi/asm/ptrace.h>
#include <asm/asm-const.h>
#ifndef __ASSEMBLY__
struct pt_regs
{
union {
struct user_pt_regs user_regs;
struct {
unsigned long gpr[32];
unsigned long nip;
unsigned long msr;
unsigned long orig_gpr3;
unsigned long ctr;
unsigned long link;
unsigned long xer;
unsigned long ccr;
#ifdef CONFIG_PPC64
unsigned long softe;
#else
unsigned long mq;
#endif
unsigned long trap;
unsigned long dar;
unsigned long dsisr;
unsigned long result;
};
};
union {
struct {
#ifdef CONFIG_PPC64
unsigned long ppr;
#endif
union {
#ifdef CONFIG_PPC_KUAP
unsigned long kuap;
#endif
#ifdef CONFIG_PPC_PKEY
unsigned long amr;
#endif
};
#ifdef CONFIG_PPC_PKEY
unsigned long iamr;
#endif
};
unsigned long __pad[4]; /* Maintain 16 byte interrupt stack alignment */
};
};
#endif
#ifdef __powerpc64__
/*
* Size of redzone that userspace is allowed to use below the stack
* pointer. This is 288 in the 64-bit big-endian ELF ABI, and 512 in
* the new ELFv2 little-endian ABI, so we allow the larger amount.
*
* For kernel code we allow a 288-byte redzone, in order to conserve
* kernel stack space; gcc currently only uses 288 bytes, and will
* hopefully allow explicit control of the redzone size in future.
*/
#define USER_REDZONE_SIZE 512
#define KERNEL_REDZONE_SIZE 288
#define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */
#define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */
#define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265)
#define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \
STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
#define STACK_FRAME_MARKER 12
#ifdef PPC64_ELF_ABI_v2
#define STACK_FRAME_MIN_SIZE 32
#else
#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD
#endif
/* Size of dummy stack frame allocated when calling signal handler. */
#define __SIGNAL_FRAMESIZE 128
#define __SIGNAL_FRAMESIZE32 64
#else /* __powerpc64__ */
#define USER_REDZONE_SIZE 0
#define KERNEL_REDZONE_SIZE 0
#define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */
#define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */
#define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773)
#define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD)
#define STACK_FRAME_MARKER 2
#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD
/* Size of stack frame allocated when calling signal handler. */
#define __SIGNAL_FRAMESIZE 64
#endif /* __powerpc64__ */
#ifndef __ASSEMBLY__
static inline unsigned long instruction_pointer(struct pt_regs *regs)
{
return regs->nip;
}
static inline void instruction_pointer_set(struct pt_regs *regs,
unsigned long val)
{
regs->nip = val;
}
static inline unsigned long user_stack_pointer(struct pt_regs *regs)
{
return regs->gpr[1];
}
static inline unsigned long frame_pointer(struct pt_regs *regs)
{
return 0;
}
#ifdef CONFIG_SMP
extern unsigned long profile_pc(struct pt_regs *regs);
#else
#define profile_pc(regs) instruction_pointer(regs)
#endif
powerpc/64/sycall: Implement syscall entry/exit logic in C System call entry and particularly exit code is beyond the limit of what is reasonable to implement in asm. This conversion moves all conditional branches out of the asm code, except for the case that all GPRs should be restored at exit. Null syscall test is about 5% faster after this patch, because the exit work is handled under local_irq_disable, and the hard mask and pending interrupt replay is handled after that, which avoids games with MSR. mpe: Includes subsequent fixes from Nick: This fixes 4 issues caught by TM selftests. First was a tm-syscall bug that hit due to tabort_syscall being called after interrupts were reconciled (in a subsequent patch), which led to interrupts being enabled before tabort_syscall was called. Rather than going through an un-reconciling interrupts for the return, I just go back to putting the test early in asm, the C-ification of that wasn't a big win anyway. Second is the syscall return _TIF_USER_WORK_MASK check would go into an infinite loop if _TIF_RESTORE_TM became set. The asm code uses _TIF_USER_WORK_MASK to brach to slowpath which includes restore_tm_state. Third is system call return was not calling restore_tm_state, I missed this completely (alhtough it's in the return from interrupt C conversion because when the asm syscall code encountered problems it would branch to the interrupt return code. Fourth is MSR_VEC missing from restore_math, which was caught by tm-unavailable selftest taking an unexpected facility unavailable interrupt when testing VSX unavailble exception with MSR.FP=1 MSR.VEC=1. Fourth case also has a fixup in a subsequent patch. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michal Suchanek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200225173541.1549955-26-npiggin@gmail.com
2020-02-26 03:35:34 +10:00
long do_syscall_trace_enter(struct pt_regs *regs);
void do_syscall_trace_leave(struct pt_regs *regs);
#define kernel_stack_pointer(regs) ((regs)->gpr[1])
Audit: push audit success and retcode into arch ptrace.h The audit system previously expected arches calling to audit_syscall_exit to supply as arguments if the syscall was a success and what the return code was. Audit also provides a helper AUDITSC_RESULT which was supposed to simplify things by converting from negative retcodes to an audit internal magic value stating success or failure. This helper was wrong and could indicate that a valid pointer returned to userspace was a failed syscall. The fix is to fix the layering foolishness. We now pass audit_syscall_exit a struct pt_reg and it in turns calls back into arch code to collect the return value and to determine if the syscall was a success or failure. We also define a generic is_syscall_success() macro which determines success/failure based on if the value is < -MAX_ERRNO. This works for arches like x86 which do not use a separate mechanism to indicate syscall failure. We make both the is_syscall_success() and regs_return_value() static inlines instead of macros. The reason is because the audit function must take a void* for the regs. (uml calls theirs struct uml_pt_regs instead of just struct pt_regs so audit_syscall_exit can't take a struct pt_regs). Since the audit function takes a void* we need to use static inlines to cast it back to the arch correct structure to dereference it. The other major change is that on some arches, like ia64, MIPS and ppc, we change regs_return_value() to give us the negative value on syscall failure. THE only other user of this macro, kretprobe_example.c, won't notice and it makes the value signed consistently for the audit functions across all archs. In arch/sh/kernel/ptrace_64.c I see that we were using regs[9] in the old audit code as the return value. But the ptrace_64.h code defined the macro regs_return_value() as regs[3]. I have no idea which one is correct, but this patch now uses the regs_return_value() function, so it now uses regs[3]. For powerpc we previously used regs->result but now use the regs_return_value() function which uses regs->gprs[3]. regs->gprs[3] is always positive so the regs_return_value(), much like ia64 makes it negative before calling the audit code when appropriate. Signed-off-by: Eric Paris <eparis@redhat.com> Acked-by: H. Peter Anvin <hpa@zytor.com> [for x86 portion] Acked-by: Tony Luck <tony.luck@intel.com> [for ia64] Acked-by: Richard Weinberger <richard@nod.at> [for uml] Acked-by: David S. Miller <davem@davemloft.net> [for sparc] Acked-by: Ralf Baechle <ralf@linux-mips.org> [for mips] Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [for ppc]
2012-01-03 14:23:06 -05:00
static inline int is_syscall_success(struct pt_regs *regs)
{
return !(regs->ccr & 0x10000000);
}
static inline long regs_return_value(struct pt_regs *regs)
{
if (is_syscall_success(regs))
return regs->gpr[3];
else
return -regs->gpr[3];
}
static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
{
regs->gpr[3] = rc;
}
#ifdef __powerpc64__
#define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
#else
#define user_mode(regs) (((regs)->msr & MSR_PR) != 0)
#endif
#define force_successful_syscall_return() \
do { \
[PATCH] syscall entry/exit revamp This cleanup patch speeds up the null syscall path on ppc64 by about 3%, and brings the ppc32 and ppc64 code slightly closer together. The ppc64 code was checking current_thread_info()->flags twice in the syscall exit path; once for TIF_SYSCALL_T_OR_A before disabling interrupts, and then again for TIF_SIGPENDING|TIF_NEED_RESCHED etc after disabling interrupts. Now we do the same as ppc32 -- check the flags only once in the fast path, and re-enable interrupts if necessary in the ptrace case. The patch abolishes the 'syscall_noerror' member of struct thread_info and replaces it with a TIF_NOERROR bit in the flags, which is handled in the slow path. This shortens the syscall entry code, which no longer needs to clear syscall_noerror. The patch adds a TIF_SAVE_NVGPRS flag which causes the syscall exit slow path to save the non-volatile GPRs into a signal frame. This removes the need for the assembly wrappers around sys_sigsuspend(), sys_rt_sigsuspend(), et al which existed solely to save those registers in advance. It also means I don't have to add new wrappers for ppoll() and pselect(), which is what I was supposed to be doing when I got distracted into this... Finally, it unifies the ppc64 and ppc32 methods of handling syscall exit directly into a signal handler (as required by sigsuspend et al) by introducing a TIF_RESTOREALL flag which causes _all_ the registers to be reloaded from the pt_regs by taking the ret_from_exception path, instead of the normal syscall exit path which stomps on the callee-saved GPRs. It appears to pass an LTP test run on ppc64, and passes basic testing on ppc32 too. Brief tests of ptrace functionality with strace and gdb also appear OK. I wouldn't send it to Linus for 2.6.15 just yet though :) Signed-off-by: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-15 18:52:18 +00:00
set_thread_flag(TIF_NOERROR); \
} while(0)
#define current_pt_regs() \
((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1)
#ifdef __powerpc64__
#ifdef CONFIG_PPC_BOOK3S
#define TRAP_FLAGS_MASK 0x10
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) true
#define SET_FULL_REGS(regs) do { } while (0)
#else
#define TRAP_FLAGS_MASK 0x11
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) (((regs)->trap & 1) == 0)
#define SET_FULL_REGS(regs) ((regs)->trap |= 1)
#endif
#define CHECK_FULL_REGS(regs) BUG_ON(!FULL_REGS(regs))
#define NV_REG_POISON 0xdeadbeefdeadbeefUL
#else
/*
* We use the least-significant bit of the trap field to indicate
* whether we have saved the full set of registers, or only a
* partial set. A 1 there means the partial set.
* On 4xx we use the next bit to indicate whether the exception
* is a critical exception (1 means it is).
*/
#define TRAP_FLAGS_MASK 0x1F
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) (((regs)->trap & 1) == 0)
#define SET_FULL_REGS(regs) ((regs)->trap |= 1)
#define IS_CRITICAL_EXC(regs) (((regs)->trap & 2) != 0)
#define IS_MCHECK_EXC(regs) (((regs)->trap & 4) != 0)
#define IS_DEBUG_EXC(regs) (((regs)->trap & 8) != 0)
#define NV_REG_POISON 0xdeadbeef
#define CHECK_FULL_REGS(regs) \
do { \
if ((regs)->trap & 1) \
printk(KERN_CRIT "%s: partial register set\n", __func__); \
} while (0)
#endif /* __powerpc64__ */
static inline void set_trap(struct pt_regs *regs, unsigned long val)
{
regs->trap = (regs->trap & TRAP_FLAGS_MASK) | (val & ~TRAP_FLAGS_MASK);
}
static inline bool trap_is_scv(struct pt_regs *regs)
{
return (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && TRAP(regs) == 0x3000);
}
static inline bool trap_is_syscall(struct pt_regs *regs)
{
return (trap_is_scv(regs) || TRAP(regs) == 0xc00);
}
static inline bool trap_norestart(struct pt_regs *regs)
{
return regs->trap & 0x10;
}
static inline void set_trap_norestart(struct pt_regs *regs)
{
regs->trap |= 0x10;
}
#define arch_has_single_step() (1)
#define arch_has_block_step() (true)
#define ARCH_HAS_USER_SINGLE_STEP_REPORT
/*
* kprobe-based event tracer support
*/
#include <linux/stddef.h>
#include <linux/thread_info.h>
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, dsisr))
/**
* 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 whose offset from @regs.
* The @offset is the offset of the register in struct pt_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 bool 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;
}
#endif /* __ASSEMBLY__ */
#ifndef __powerpc64__
/* We need PT_SOFTE defined at all time to avoid #ifdefs */
#define PT_SOFTE PT_MQ
#else /* __powerpc64__ */
#define PT_FPSCR32 (PT_FPR0 + 2*32 + 1) /* each FP reg occupies 2 32-bit userspace slots */
#define PT_VR0_32 164 /* each Vector reg occupies 4 slots in 32-bit */
#define PT_VSCR_32 (PT_VR0 + 32*4 + 3)
#define PT_VRSAVE_32 (PT_VR0 + 33*4)
#define PT_VSR0_32 300 /* each VSR reg occupies 4 slots in 32-bit */
#endif /* __powerpc64__ */
#endif /* _ASM_POWERPC_PTRACE_H */