linux-stable/arch/arm64/kernel/perf_callchain.c

179 lines
4.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* arm64 callchain support
*
* Copyright (C) 2015 ARM Limited
*/
#include <linux/perf_event.h>
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>
2021-11-29 14:28:44 +00:00
#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 */
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:57:57 +00:00
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 */
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:57:57 +00:00
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_state()) {
/* 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;
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>
2021-11-29 14:28:44 +00:00
return perf_callchain_store(entry, pc) == 0;
}
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
if (perf_guest_state()) {
/* We don't support guest os callchain now */
return;
}
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>
2021-11-29 14:28:44 +00:00
arch_stack_walk(callchain_trace, entry, current, regs);
}
unsigned long perf_instruction_pointer(struct pt_regs *regs)
{
if (perf_guest_state())
return perf_guest_get_ip();
return instruction_pointer(regs);
}
unsigned long perf_misc_flags(struct pt_regs *regs)
{
unsigned int guest_state = perf_guest_state();
int misc = 0;
if (guest_state) {
if (guest_state & PERF_GUEST_USER)
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;
}