diff options
author | Nicholas Piggin <npiggin@gmail.com> | 2022-03-30 19:37:19 +0530 |
---|---|---|
committer | Michael Ellerman <mpe@ellerman.id.au> | 2022-05-06 00:00:20 +1000 |
commit | a553476c44fb6bd3dc3a7e5efef8f130f0f34850 (patch) | |
tree | c5a576e27e9364ab43cf255e42e3bb480b03cb0a /arch/powerpc/lib/sstep.c | |
parent | 54cdacd7d3b3c1a8dc10965f56c8b5eb8eda1a33 (diff) |
powerpc/64: remove system call instruction emulation
emulate_step() instruction emulation including sc instruction emulation
initially appeared in xmon. It was then moved into sstep.c where kprobes
could use it too, and later hw_breakpoint and uprobes started to use it.
Until uprobes, the only instruction emulation users were for kernel
mode instructions.
- xmon only steps / breaks on kernel addresses.
- kprobes is kernel only.
- hw_breakpoint only emulates kernel instructions, single steps user.
At one point, there was support for the kernel to execute sc
instructions, although that is long removed and it's not clear whether
there were any in-tree users. So system call emulation is not required
by the above users.
uprobes uses emulate_step and it appears possible to emulate sc
instruction in userspace. Userspace system call emulation is broken and
it's not clear it ever worked well.
The big complication is that userspace takes an interrupt to the kernel
to emulate the instruction. The user->kernel interrupt sets up registers
and interrupt stack frame expecting to return to userspace, then system
call instruction emulation re-directs that stack frame to the kernel,
early in the system call interrupt handler. This means the interrupt
return code takes the kernel->kernel restore path, which does not
restore everything as the system call interrupt handler would expect
coming from userspace. regs->iamr appears to get lost for example,
because the kernel->kernel return does not restore the user iamr.
Accounting such as irqflags tracing and CPU accounting does not get
flipped back to user mode as the system call handler expects, so those
appear to enter the kernel twice without returning to userspace.
These things may be individually fixable with various complication, but
it is a big complexity for unclear real benefit.
Furthermore, it is not possible to single step a system call instruction
since it causes an interrupt. As such, a separate patch disables probing
on system call instructions.
This patch removes system call emulation and disables stepping system
calls.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[minor commit log edit, and also get rid of '#ifdef CONFIG_PPC64']
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/a412e3b3791ed83de18704c8d90f492e7a0049c0.1648648712.git.naveen.n.rao@linux.vnet.ibm.com
Diffstat (limited to 'arch/powerpc/lib/sstep.c')
-rw-r--r-- | arch/powerpc/lib/sstep.c | 46 |
1 files changed, 10 insertions, 36 deletions
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 72d4ce289eef..398b5694aeb7 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -15,9 +15,6 @@ #include <asm/cputable.h> #include <asm/disassemble.h> -extern char system_call_common[]; -extern char system_call_vectored_emulate[]; - #ifdef CONFIG_PPC64 /* Bits in SRR1 that are copied from MSR */ #define MSR_MASK 0xffffffff87c0ffffUL @@ -1376,7 +1373,6 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, if (branch_taken(word, regs, op)) op->type |= BRTAKEN; return 1; -#ifdef CONFIG_PPC64 case 17: /* sc */ if ((word & 0xfe2) == 2) op->type = SYSCALL; @@ -1388,7 +1384,6 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, } else op->type = UNKNOWN; return 0; -#endif case 18: /* b */ op->type = BRANCH | BRTAKEN; imm = word & 0x03fffffc; @@ -3643,43 +3638,22 @@ int emulate_step(struct pt_regs *regs, ppc_inst_t instr) regs_set_return_msr(regs, (regs->msr & ~op.val) | (val & op.val)); goto instr_done; -#ifdef CONFIG_PPC64 case SYSCALL: /* sc */ /* - * N.B. this uses knowledge about how the syscall - * entry code works. If that is changed, this will - * need to be changed also. + * Per ISA v3.1, section 7.5.15 'Trace Interrupt', we can't + * single step a system call instruction: + * + * Successful completion for an instruction means that the + * instruction caused no other interrupt. Thus a Trace + * interrupt never occurs for a System Call or System Call + * Vectored instruction, or for a Trap instruction that + * traps. */ - if (IS_ENABLED(CONFIG_PPC_FAST_ENDIAN_SWITCH) && - cpu_has_feature(CPU_FTR_REAL_LE) && - regs->gpr[0] == 0x1ebe) { - regs_set_return_msr(regs, regs->msr ^ MSR_LE); - goto instr_done; - } - regs->gpr[9] = regs->gpr[13]; - regs->gpr[10] = MSR_KERNEL; - regs->gpr[11] = regs->nip + 4; - regs->gpr[12] = regs->msr & MSR_MASK; - regs->gpr[13] = (unsigned long) get_paca(); - regs_set_return_ip(regs, (unsigned long) &system_call_common); - regs_set_return_msr(regs, MSR_KERNEL); - return 1; - -#ifdef CONFIG_PPC_BOOK3S_64 + return -1; case SYSCALL_VECTORED_0: /* scv 0 */ - regs->gpr[9] = regs->gpr[13]; - regs->gpr[10] = MSR_KERNEL; - regs->gpr[11] = regs->nip + 4; - regs->gpr[12] = regs->msr & MSR_MASK; - regs->gpr[13] = (unsigned long) get_paca(); - regs_set_return_ip(regs, (unsigned long) &system_call_vectored_emulate); - regs_set_return_msr(regs, MSR_KERNEL); - return 1; -#endif - + return -1; case RFI: return -1; -#endif } return 0; |