linux_old1/arch/arm64/kernel/perf_callchain.c

192 lines
4.5 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>
#include <linux/uaccess.h>
#include <asm/pointer_auth.h>
#include <asm/stacktrace.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 10:57:57 +08:00
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 10:57:57 +08:00
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_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 & 0xf))
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
}
}
/*
* Gets called by walk_stackframe() for every stackframe. This will be called
* whist unwinding the stackframe and is like a subroutine return so we use
* the PC.
*/
static int callchain_trace(struct stackframe *frame, void *data)
{
struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, frame->pc);
return 0;
}
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
struct stackframe frame;
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
frame.fp = regs->regs[29];
frame.pc = regs->pc;
arm64: ftrace: fix a stack tracer's output under function graph tracer Function graph tracer modifies a return address (LR) in a stack frame to hook a function return. This will result in many useless entries (return_to_handler) showing up in a) a stack tracer's output b) perf call graph (with perf record -g) c) dump_backtrace (at panic et al.) For example, in case of a), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo 1 > /proc/sys/kernel/stack_trace_enabled $ cat /sys/kernel/debug/tracing/stack_trace Depth Size Location (54 entries) ----- ---- -------- 0) 4504 16 gic_raise_softirq+0x28/0x150 1) 4488 80 smp_cross_call+0x38/0xb8 2) 4408 48 return_to_handler+0x0/0x40 3) 4360 32 return_to_handler+0x0/0x40 ... In case of b), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ perf record -e mem:XXX:x -ag -- sleep 10 $ perf report ... | | |--0.22%-- 0x550f8 | | | 0x10888 | | | el0_svc_naked | | | sys_openat | | | return_to_handler | | | return_to_handler ... In case of c), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo c > /proc/sysrq-trigger ... Call trace: [<ffffffc00044d3ac>] sysrq_handle_crash+0x24/0x30 [<ffffffc000092250>] return_to_handler+0x0/0x40 [<ffffffc000092250>] return_to_handler+0x0/0x40 ... This patch replaces such entries with real addresses preserved in current->ret_stack[] at unwind_frame(). This way, we can cover all the cases. Reviewed-by: Jungseok Lee <jungseoklee85@gmail.com> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> [will: fixed minor context changes conflicting with irq stack bits] Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-12-15 16:33:41 +08:00
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = 0;
arm64: ftrace: fix a stack tracer's output under function graph tracer Function graph tracer modifies a return address (LR) in a stack frame to hook a function return. This will result in many useless entries (return_to_handler) showing up in a) a stack tracer's output b) perf call graph (with perf record -g) c) dump_backtrace (at panic et al.) For example, in case of a), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo 1 > /proc/sys/kernel/stack_trace_enabled $ cat /sys/kernel/debug/tracing/stack_trace Depth Size Location (54 entries) ----- ---- -------- 0) 4504 16 gic_raise_softirq+0x28/0x150 1) 4488 80 smp_cross_call+0x38/0xb8 2) 4408 48 return_to_handler+0x0/0x40 3) 4360 32 return_to_handler+0x0/0x40 ... In case of b), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ perf record -e mem:XXX:x -ag -- sleep 10 $ perf report ... | | |--0.22%-- 0x550f8 | | | 0x10888 | | | el0_svc_naked | | | sys_openat | | | return_to_handler | | | return_to_handler ... In case of c), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo c > /proc/sysrq-trigger ... Call trace: [<ffffffc00044d3ac>] sysrq_handle_crash+0x24/0x30 [<ffffffc000092250>] return_to_handler+0x0/0x40 [<ffffffc000092250>] return_to_handler+0x0/0x40 ... This patch replaces such entries with real addresses preserved in current->ret_stack[] at unwind_frame(). This way, we can cover all the cases. Reviewed-by: Jungseok Lee <jungseoklee85@gmail.com> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> [will: fixed minor context changes conflicting with irq stack bits] Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-12-15 16:33:41 +08:00
#endif
walk_stackframe(current, &frame, callchain_trace, entry);
}
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;
}