diff mbox series

[08/10] arm64: mops: handle single stepping after MOPS exception

Message ID 20230216160012.272345-9-kristina.martsenko@arm.com
State New
Headers
Series arm64: support Armv8.8 memcpy instructions in userspace |

Commit Message

Kristina Martsenko Feb. 16, 2023, 4 p.m. UTC 
  When a MOPS main or epilogue instruction is being executed, the task may
get scheduled on a different CPU and restart execution from the prologue
instruction. If the main or epilogue instruction is being single stepped
then it makes sense to finish the step and take the step exception
before starting to execute the next (prologue) instruction. So
fast-forward the single step state machine when taking a MOPS exception.

This means that if a main or epilogue instruction is single stepped with
ptrace, the debugger will sometimes observe the PC moving back to the
prologue instruction. (As already mentioned, this should be rare as it
only happens when the task is scheduled to another CPU during the step.)

This also ensures that perf breakpoints count prologue instructions
consistently (i.e. every time they are executed), rather than skipping
them when there also happens to be a breakpoint on a main or epilogue
instruction.

Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>
---
 arch/arm64/kernel/traps.c | 6 ++++++
 1 file changed, 6 insertions(+)

Comments

Catalin Marinas March 17, 2023, 4:02 p.m. UTC | #1 
On Thu, Feb 16, 2023 at 04:00:10PM +0000, Kristina Martsenko wrote:
> When a MOPS main or epilogue instruction is being executed, the task may
> get scheduled on a different CPU and restart execution from the prologue
> instruction. If the main or epilogue instruction is being single stepped
> then it makes sense to finish the step and take the step exception
> before starting to execute the next (prologue) instruction. So
> fast-forward the single step state machine when taking a MOPS exception.
> 
> This means that if a main or epilogue instruction is single stepped with
> ptrace, the debugger will sometimes observe the PC moving back to the
> prologue instruction. (As already mentioned, this should be rare as it
> only happens when the task is scheduled to another CPU during the step.)
> 
> This also ensures that perf breakpoints count prologue instructions
> consistently (i.e. every time they are executed), rather than skipping
> them when there also happens to be a breakpoint on a main or epilogue
> instruction.
> 
> Signed-off-by: Kristina Martsenko <kristina.martsenko@arm.com>

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
diff mbox series

Patch

diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 689188712909..3dfc901a430b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -549,6 +549,12 @@  void do_el0_mops(struct pt_regs *regs, unsigned long esr)
 		regs->pc -= 8;
 	else
 		regs->pc -= 4;
+
+	/*
+	 * If single stepping then finish the step before executing the
+	 * prologue instruction.
+	 */
+	user_fastforward_single_step(current);
 }
 
 #define __user_cache_maint(insn, address, res)			\