Files
linux/arch/arm64/kernel/perf_callchain.c
Madhavan T. Venkataraman ed876d35a1 arm64: Make perf_callchain_kernel() use arch_stack_walk()
To enable RELIABLE_STACKTRACE and LIVEPATCH on arm64, we need to
substantially rework arm64's unwinding code. As part of this, we want to
minimize the set of unwind interfaces we expose, and avoid open-coding
of unwind logic outside of stacktrace.c.

Currently perf_callchain_kernel() walks the stack of an interrupted
context by calling start_backtrace() with the context's PC and FP, and
iterating unwind steps using walk_stackframe(). This is functionally
equivalent to calling arch_stack_walk() with the interrupted context's
pt_regs, which will start with the PC and FP from the regs.

Make perf_callchain_kernel() use arch_stack_walk(). This simplifies
perf_callchain_kernel(), and in future will alow us to make
walk_stackframe() private to stacktrace.c.

At the same time, we update the callchain_trace() callback to check the
return value of perf_callchain_store(), which indicates whether there is
space for any further entries. When a non-zero value is returned,
further calls will be ignored, and are redundant, so we can stop the
unwind at this point.

We also remove the stale and confusing comment for callchain_trace.

There should be no functional change as a result of this patch.

Signed-off-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
[Mark: elaborate commit message, remove comment, fix includes]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20211129142849.3056714-5-mark.rutland@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2021-12-10 14:06:03 +00:00

178 lines
4.2 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* arm64 callchain support
*
* Copyright (C) 2015 ARM Limited
*/
#include <linux/perf_event.h>
#include <linux/stacktrace.h>
#include <linux/uaccess.h>
#include <asm/pointer_auth.h>
struct frame_tail {
struct frame_tail __user *fp;
unsigned long lr;
} __attribute__((packed));
/*
* Get the return address for a single stackframe and return a pointer to the
* next frame tail.
*/
static struct frame_tail __user *
user_backtrace(struct frame_tail __user *tail,
struct perf_callchain_entry_ctx *entry)
{
struct frame_tail buftail;
unsigned long err;
unsigned long lr;
/* Also check accessibility of one struct frame_tail beyond */
if (!access_ok(tail, sizeof(buftail)))
return NULL;
pagefault_disable();
err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
pagefault_enable();
if (err)
return NULL;
lr = ptrauth_strip_insn_pac(buftail.lr);
perf_callchain_store(entry, lr);
/*
* Frame pointers should strictly progress back up the stack
* (towards higher addresses).
*/
if (tail >= buftail.fp)
return NULL;
return buftail.fp;
}
#ifdef CONFIG_COMPAT
/*
* The registers we're interested in are at the end of the variable
* length saved register structure. The fp points at the end of this
* structure so the address of this struct is:
* (struct compat_frame_tail *)(xxx->fp)-1
*
* This code has been adapted from the ARM OProfile support.
*/
struct compat_frame_tail {
compat_uptr_t fp; /* a (struct compat_frame_tail *) in compat mode */
u32 sp;
u32 lr;
} __attribute__((packed));
static struct compat_frame_tail __user *
compat_user_backtrace(struct compat_frame_tail __user *tail,
struct perf_callchain_entry_ctx *entry)
{
struct compat_frame_tail buftail;
unsigned long err;
/* Also check accessibility of one struct frame_tail beyond */
if (!access_ok(tail, sizeof(buftail)))
return NULL;
pagefault_disable();
err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
pagefault_enable();
if (err)
return NULL;
perf_callchain_store(entry, buftail.lr);
/*
* Frame pointers should strictly progress back up the stack
* (towards higher addresses).
*/
if (tail + 1 >= (struct compat_frame_tail __user *)
compat_ptr(buftail.fp))
return NULL;
return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
}
#endif /* CONFIG_COMPAT */
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
perf_callchain_store(entry, regs->pc);
if (!compat_user_mode(regs)) {
/* AARCH64 mode */
struct frame_tail __user *tail;
tail = (struct frame_tail __user *)regs->regs[29];
while (entry->nr < entry->max_stack &&
tail && !((unsigned long)tail & 0x7))
tail = user_backtrace(tail, entry);
} else {
#ifdef CONFIG_COMPAT
/* AARCH32 compat mode */
struct compat_frame_tail __user *tail;
tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
while ((entry->nr < entry->max_stack) &&
tail && !((unsigned long)tail & 0x3))
tail = compat_user_backtrace(tail, entry);
#endif
}
}
static bool callchain_trace(void *data, unsigned long pc)
{
struct perf_callchain_entry_ctx *entry = data;
return perf_callchain_store(entry, pc) == 0;
}
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
arch_stack_walk(callchain_trace, entry, current, regs);
}
unsigned long perf_instruction_pointer(struct pt_regs *regs)
{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
return perf_guest_cbs->get_guest_ip();
return instruction_pointer(regs);
}
unsigned long perf_misc_flags(struct pt_regs *regs)
{
int misc = 0;
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
if (perf_guest_cbs->is_user_mode())
misc |= PERF_RECORD_MISC_GUEST_USER;
else
misc |= PERF_RECORD_MISC_GUEST_KERNEL;
} else {
if (user_mode(regs))
misc |= PERF_RECORD_MISC_USER;
else
misc |= PERF_RECORD_MISC_KERNEL;
}
return misc;
}