linux_dsm_epyc7002/arch/arm64/kernel/stacktrace.c

216 lines
5.2 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Stack tracing support
*
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/kernel.h>
#include <linux/export.h>
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 15:33:41 +07:00
#include <linux/ftrace.h>
#include <linux/kprobes.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
#include <asm/irq.h>
#include <asm/pointer_auth.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
/*
* AArch64 PCS assigns the frame pointer to x29.
*
* A simple function prologue looks like this:
* sub sp, sp, #0x10
* stp x29, x30, [sp]
* mov x29, sp
*
* A simple function epilogue looks like this:
* mov sp, x29
* ldp x29, x30, [sp]
* add sp, sp, #0x10
*/
/*
* Unwind from one frame record (A) to the next frame record (B).
*
* We terminate early if the location of B indicates a malformed chain of frame
* records (e.g. a cycle), determined based on the location and fp value of A
* and the location (but not the fp value) of B.
*/
int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
{
unsigned long fp = frame->fp;
struct stack_info info;
if (fp & 0xf)
return -EINVAL;
arm64: fix dump_backtrace/unwind_frame with NULL tsk In some places, dump_backtrace() is called with a NULL tsk parameter, e.g. in bug_handler() in arch/arm64, or indirectly via show_stack() in core code. The expectation is that this is treated as if current were passed instead of NULL. Similar is true of unwind_frame(). Commit a80a0eb70c358f8c ("arm64: make irq_stack_ptr more robust") didn't take this into account. In dump_backtrace() it compares tsk against current *before* we check if tsk is NULL, and in unwind_frame() we never set tsk if it is NULL. Due to this, we won't initialise irq_stack_ptr in either function. In dump_backtrace() this results in calling dump_mem() for memory immediately above the IRQ stack range, rather than for the relevant range on the task stack. In unwind_frame we'll reject unwinding frames on the IRQ stack. In either case this results in incomplete or misleading backtrace information, but is not otherwise problematic. The initial percpu areas (including the IRQ stacks) are allocated in the linear map, and dump_mem uses __get_user(), so we shouldn't access anything with side-effects, and will handle holes safely. This patch fixes the issue by having both functions handle the NULL tsk case before doing anything else with tsk. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Fixes: a80a0eb70c358f8c ("arm64: make irq_stack_ptr more robust") Acked-by: James Morse <james.morse@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yang Shi <yang.shi@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-09-23 23:55:05 +07:00
if (!tsk)
tsk = current;
if (!on_accessible_stack(tsk, fp, &info))
return -EINVAL;
if (test_bit(info.type, frame->stacks_done))
return -EINVAL;
/*
* As stacks grow downward, any valid record on the same stack must be
* at a strictly higher address than the prior record.
*
* Stacks can nest in several valid orders, e.g.
*
* TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL
* TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW
*
* ... but the nesting itself is strict. Once we transition from one
* stack to another, it's never valid to unwind back to that first
* stack.
*/
if (info.type == frame->prev_type) {
if (fp <= frame->prev_fp)
return -EINVAL;
} else {
set_bit(frame->prev_type, frame->stacks_done);
}
/*
* Record this frame record's values and location. The prev_fp and
* prev_type are only meaningful to the next unwind_frame() invocation.
*/
arm64: disable kasan when accessing frame->fp in unwind_frame When boot arm64 kernel with KASAN enabled, the below error is reported by kasan: BUG: KASAN: out-of-bounds in unwind_frame+0xec/0x260 at addr ffffffc064d57ba0 Read of size 8 by task pidof/499 page:ffffffbdc39355c0 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x0() page dumped because: kasan: bad access detected CPU: 2 PID: 499 Comm: pidof Not tainted 4.5.0-rc1 #119 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [<ffffffc00008d078>] dump_backtrace+0x0/0x290 [<ffffffc00008d32c>] show_stack+0x24/0x30 [<ffffffc0006a981c>] dump_stack+0x8c/0xd8 [<ffffffc0002e4400>] kasan_report_error+0x558/0x588 [<ffffffc0002e4958>] kasan_report+0x60/0x70 [<ffffffc0002e3188>] __asan_load8+0x60/0x78 [<ffffffc00008c92c>] unwind_frame+0xec/0x260 [<ffffffc000087e60>] get_wchan+0x110/0x160 [<ffffffc0003b647c>] do_task_stat+0xb44/0xb68 [<ffffffc0003b7730>] proc_tgid_stat+0x40/0x50 [<ffffffc0003ac840>] proc_single_show+0x88/0xd8 [<ffffffc000345be8>] seq_read+0x370/0x770 [<ffffffc00030aba0>] __vfs_read+0xc8/0x1d8 [<ffffffc00030c0ec>] vfs_read+0x94/0x168 [<ffffffc00030d458>] SyS_read+0xb8/0x128 [<ffffffc000086530>] el0_svc_naked+0x24/0x28 Memory state around the buggy address: ffffffc064d57a80: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 f4 f4 ffffffc064d57b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffffffc064d57b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffffffc064d57c00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc064d57c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Since the shadow byte pointed by the report is 0, so it may mean it is just hit oob in non-current task. So, disable the instrumentation to silence these warnings. Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Signed-off-by: Yang Shi <yang.shi@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-02-09 00:13:09 +07:00
frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
frame->prev_fp = fp;
frame->prev_type = info.type;
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 15:33:41 +07:00
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
arm64: fix dump_backtrace/unwind_frame with NULL tsk In some places, dump_backtrace() is called with a NULL tsk parameter, e.g. in bug_handler() in arch/arm64, or indirectly via show_stack() in core code. The expectation is that this is treated as if current were passed instead of NULL. Similar is true of unwind_frame(). Commit a80a0eb70c358f8c ("arm64: make irq_stack_ptr more robust") didn't take this into account. In dump_backtrace() it compares tsk against current *before* we check if tsk is NULL, and in unwind_frame() we never set tsk if it is NULL. Due to this, we won't initialise irq_stack_ptr in either function. In dump_backtrace() this results in calling dump_mem() for memory immediately above the IRQ stack range, rather than for the relevant range on the task stack. In unwind_frame we'll reject unwinding frames on the IRQ stack. In either case this results in incomplete or misleading backtrace information, but is not otherwise problematic. The initial percpu areas (including the IRQ stacks) are allocated in the linear map, and dump_mem uses __get_user(), so we shouldn't access anything with side-effects, and will handle holes safely. This patch fixes the issue by having both functions handle the NULL tsk case before doing anything else with tsk. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Fixes: a80a0eb70c358f8c ("arm64: make irq_stack_ptr more robust") Acked-by: James Morse <james.morse@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yang Shi <yang.shi@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-09-23 23:55:05 +07:00
if (tsk->ret_stack &&
(ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) {
struct ftrace_ret_stack *ret_stack;
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 15:33:41 +07:00
/*
* This is a case where function graph tracer has
* modified a return address (LR) in a stack frame
* to hook a function return.
* So replace it to an original value.
*/
ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++);
if (WARN_ON_ONCE(!ret_stack))
return -EINVAL;
frame->pc = ret_stack->ret;
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 15:33:41 +07:00
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
frame->pc = ptrauth_strip_insn_pac(frame->pc);
/*
arm64: unwind: reference pt_regs via embedded stack frame As it turns out, the unwind code is slightly broken, and probably has been for a while. The problem is in the dumping of the exception stack, which is intended to dump the contents of the pt_regs struct at each level in the call stack where an exception was taken and routed to a routine marked as __exception (which means its stack frame is right below the pt_regs struct on the stack). 'Right below the pt_regs struct' is ill defined, though: the unwind code assigns 'frame pointer + 0x10' to the .sp member of the stackframe struct at each level, and dump_backtrace() happily dereferences that as the pt_regs pointer when encountering an __exception routine. However, the actual size of the stack frame created by this routine (which could be one of many __exception routines we have in the kernel) is not known, and so frame.sp is pretty useless to figure out where struct pt_regs really is. So it seems the only way to ensure that we can find our struct pt_regs when walking the stack frames is to put it at a known fixed offset of the stack frame pointer that is passed to such __exception routines. The simplest way to do that is to put it inside pt_regs itself, which is the main change implemented by this patch. As a bonus, doing this allows us to get rid of a fair amount of cruft related to walking from one stack to the other, which is especially nice since we intend to introduce yet another stack for overflow handling once we add support for vmapped stacks. It also fixes an inconsistency where we only add a stack frame pointing to ELR_EL1 if we are executing from the IRQ stack but not when we are executing from the task stack. To consistly identify exceptions regs even in the presence of exceptions taken from entry code, we must check whether the next frame was created by entry text, rather than whether the current frame was crated by exception text. To avoid backtracing using PCs that fall in the idmap, or are controlled by userspace, we must explcitly zero the FP and LR in startup paths, and must ensure that the frame embedded in pt_regs is zeroed upon entry from EL0. To avoid these NULL entries showin in the backtrace, unwind_frame() is updated to avoid them. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> [Mark: compare current frame against .entry.text, avoid bogus PCs] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: James Morse <james.morse@arm.com> Cc: Will Deacon <will.deacon@arm.com>
2017-07-23 00:45:33 +07:00
* Frames created upon entry from EL0 have NULL FP and PC values, so
* don't bother reporting these. Frames created by __noreturn functions
* might have a valid FP even if PC is bogus, so only terminate where
* both are NULL.
*/
arm64: unwind: reference pt_regs via embedded stack frame As it turns out, the unwind code is slightly broken, and probably has been for a while. The problem is in the dumping of the exception stack, which is intended to dump the contents of the pt_regs struct at each level in the call stack where an exception was taken and routed to a routine marked as __exception (which means its stack frame is right below the pt_regs struct on the stack). 'Right below the pt_regs struct' is ill defined, though: the unwind code assigns 'frame pointer + 0x10' to the .sp member of the stackframe struct at each level, and dump_backtrace() happily dereferences that as the pt_regs pointer when encountering an __exception routine. However, the actual size of the stack frame created by this routine (which could be one of many __exception routines we have in the kernel) is not known, and so frame.sp is pretty useless to figure out where struct pt_regs really is. So it seems the only way to ensure that we can find our struct pt_regs when walking the stack frames is to put it at a known fixed offset of the stack frame pointer that is passed to such __exception routines. The simplest way to do that is to put it inside pt_regs itself, which is the main change implemented by this patch. As a bonus, doing this allows us to get rid of a fair amount of cruft related to walking from one stack to the other, which is especially nice since we intend to introduce yet another stack for overflow handling once we add support for vmapped stacks. It also fixes an inconsistency where we only add a stack frame pointing to ELR_EL1 if we are executing from the IRQ stack but not when we are executing from the task stack. To consistly identify exceptions regs even in the presence of exceptions taken from entry code, we must check whether the next frame was created by entry text, rather than whether the current frame was crated by exception text. To avoid backtracing using PCs that fall in the idmap, or are controlled by userspace, we must explcitly zero the FP and LR in startup paths, and must ensure that the frame embedded in pt_regs is zeroed upon entry from EL0. To avoid these NULL entries showin in the backtrace, unwind_frame() is updated to avoid them. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> [Mark: compare current frame against .entry.text, avoid bogus PCs] Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: James Morse <james.morse@arm.com> Cc: Will Deacon <will.deacon@arm.com>
2017-07-23 00:45:33 +07:00
if (!frame->fp && !frame->pc)
return -EINVAL;
return 0;
}
NOKPROBE_SYMBOL(unwind_frame);
void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
int (*fn)(struct stackframe *, void *), void *data)
{
while (1) {
int ret;
if (fn(frame, data))
break;
ret = unwind_frame(tsk, frame);
if (ret < 0)
break;
}
}
NOKPROBE_SYMBOL(walk_stackframe);
#ifdef CONFIG_STACKTRACE
struct stack_trace_data {
struct stack_trace *trace;
unsigned int no_sched_functions;
unsigned int skip;
};
static int save_trace(struct stackframe *frame, void *d)
{
struct stack_trace_data *data = d;
struct stack_trace *trace = data->trace;
unsigned long addr = frame->pc;
if (data->no_sched_functions && in_sched_functions(addr))
return 0;
if (data->skip) {
data->skip--;
return 0;
}
trace->entries[trace->nr_entries++] = addr;
return trace->nr_entries >= trace->max_entries;
}
arm64: ftrace: add save_stack_trace_regs() Currently, enabling stacktrace of a kprobe events generates warning: echo stacktrace > /sys/kernel/debug/tracing/trace_options echo "p xhci_irq" > /sys/kernel/debug/tracing/kprobe_events echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable save_stack_trace_regs() not implemented yet. ------------[ cut here ]------------ WARNING: CPU: 1 PID: 0 at ../kernel/stacktrace.c:74 save_stack_trace_regs+0x3c/0x48 Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.8.0-rc4-dirty #5128 Hardware name: ARM Juno development board (r1) (DT) task: ffff800975dd1900 task.stack: ffff800975ddc000 PC is at save_stack_trace_regs+0x3c/0x48 LR is at save_stack_trace_regs+0x3c/0x48 pc : [<ffff000008126c64>] lr : [<ffff000008126c64>] pstate: 600003c5 sp : ffff80097ef52c00 Call trace: save_stack_trace_regs+0x3c/0x48 __ftrace_trace_stack+0x168/0x208 trace_buffer_unlock_commit_regs+0x5c/0x7c kprobe_trace_func+0x308/0x3d8 kprobe_dispatcher+0x58/0x60 kprobe_breakpoint_handler+0xbc/0x18c brk_handler+0x50/0x90 do_debug_exception+0x50/0xbc This patch implements save_stack_trace_regs(), so that stacktrace of a kprobe events can be obtained. After this patch, there is no warning and we can see the stacktrace for kprobe events in trace buffer. more /sys/kernel/debug/tracing/trace <idle>-0 [004] d.h. 1356.000496: p_xhci_irq_0:(xhci_irq+0x0/0x9ac) <idle>-0 [004] d.h. 1356.000497: <stack trace> => xhci_irq => __handle_irq_event_percpu => handle_irq_event_percpu => handle_irq_event => handle_fasteoi_irq => generic_handle_irq => __handle_domain_irq => gic_handle_irq => el1_irq => arch_cpu_idle => default_idle_call => cpu_startup_entry => secondary_start_kernel => Tested-by: David A. Long <dave.long@linaro.org> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Pratyush Anand <panand@redhat.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-09-05 09:33:16 +07:00
void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
{
struct stack_trace_data data;
struct stackframe frame;
data.trace = trace;
data.skip = trace->skip;
data.no_sched_functions = 0;
start_backtrace(&frame, regs->regs[29], regs->pc);
arm64: ftrace: add save_stack_trace_regs() Currently, enabling stacktrace of a kprobe events generates warning: echo stacktrace > /sys/kernel/debug/tracing/trace_options echo "p xhci_irq" > /sys/kernel/debug/tracing/kprobe_events echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable save_stack_trace_regs() not implemented yet. ------------[ cut here ]------------ WARNING: CPU: 1 PID: 0 at ../kernel/stacktrace.c:74 save_stack_trace_regs+0x3c/0x48 Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.8.0-rc4-dirty #5128 Hardware name: ARM Juno development board (r1) (DT) task: ffff800975dd1900 task.stack: ffff800975ddc000 PC is at save_stack_trace_regs+0x3c/0x48 LR is at save_stack_trace_regs+0x3c/0x48 pc : [<ffff000008126c64>] lr : [<ffff000008126c64>] pstate: 600003c5 sp : ffff80097ef52c00 Call trace: save_stack_trace_regs+0x3c/0x48 __ftrace_trace_stack+0x168/0x208 trace_buffer_unlock_commit_regs+0x5c/0x7c kprobe_trace_func+0x308/0x3d8 kprobe_dispatcher+0x58/0x60 kprobe_breakpoint_handler+0xbc/0x18c brk_handler+0x50/0x90 do_debug_exception+0x50/0xbc This patch implements save_stack_trace_regs(), so that stacktrace of a kprobe events can be obtained. After this patch, there is no warning and we can see the stacktrace for kprobe events in trace buffer. more /sys/kernel/debug/tracing/trace <idle>-0 [004] d.h. 1356.000496: p_xhci_irq_0:(xhci_irq+0x0/0x9ac) <idle>-0 [004] d.h. 1356.000497: <stack trace> => xhci_irq => __handle_irq_event_percpu => handle_irq_event_percpu => handle_irq_event => handle_fasteoi_irq => generic_handle_irq => __handle_domain_irq => gic_handle_irq => el1_irq => arch_cpu_idle => default_idle_call => cpu_startup_entry => secondary_start_kernel => Tested-by: David A. Long <dave.long@linaro.org> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Pratyush Anand <panand@redhat.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-09-05 09:33:16 +07:00
walk_stackframe(current, &frame, save_trace, &data);
}
EXPORT_SYMBOL_GPL(save_stack_trace_regs);
arm64: ftrace: add save_stack_trace_regs() Currently, enabling stacktrace of a kprobe events generates warning: echo stacktrace > /sys/kernel/debug/tracing/trace_options echo "p xhci_irq" > /sys/kernel/debug/tracing/kprobe_events echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable save_stack_trace_regs() not implemented yet. ------------[ cut here ]------------ WARNING: CPU: 1 PID: 0 at ../kernel/stacktrace.c:74 save_stack_trace_regs+0x3c/0x48 Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.8.0-rc4-dirty #5128 Hardware name: ARM Juno development board (r1) (DT) task: ffff800975dd1900 task.stack: ffff800975ddc000 PC is at save_stack_trace_regs+0x3c/0x48 LR is at save_stack_trace_regs+0x3c/0x48 pc : [<ffff000008126c64>] lr : [<ffff000008126c64>] pstate: 600003c5 sp : ffff80097ef52c00 Call trace: save_stack_trace_regs+0x3c/0x48 __ftrace_trace_stack+0x168/0x208 trace_buffer_unlock_commit_regs+0x5c/0x7c kprobe_trace_func+0x308/0x3d8 kprobe_dispatcher+0x58/0x60 kprobe_breakpoint_handler+0xbc/0x18c brk_handler+0x50/0x90 do_debug_exception+0x50/0xbc This patch implements save_stack_trace_regs(), so that stacktrace of a kprobe events can be obtained. After this patch, there is no warning and we can see the stacktrace for kprobe events in trace buffer. more /sys/kernel/debug/tracing/trace <idle>-0 [004] d.h. 1356.000496: p_xhci_irq_0:(xhci_irq+0x0/0x9ac) <idle>-0 [004] d.h. 1356.000497: <stack trace> => xhci_irq => __handle_irq_event_percpu => handle_irq_event_percpu => handle_irq_event => handle_fasteoi_irq => generic_handle_irq => __handle_domain_irq => gic_handle_irq => el1_irq => arch_cpu_idle => default_idle_call => cpu_startup_entry => secondary_start_kernel => Tested-by: David A. Long <dave.long@linaro.org> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Pratyush Anand <panand@redhat.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-09-05 09:33:16 +07:00
static noinline void __save_stack_trace(struct task_struct *tsk,
struct stack_trace *trace, unsigned int nosched)
{
struct stack_trace_data data;
struct stackframe frame;
if (!try_get_task_stack(tsk))
return;
data.trace = trace;
data.skip = trace->skip;
data.no_sched_functions = nosched;
if (tsk != current) {
start_backtrace(&frame, thread_saved_fp(tsk),
thread_saved_pc(tsk));
} else {
/* We don't want this function nor the caller */
data.skip += 2;
start_backtrace(&frame,
(unsigned long)__builtin_frame_address(0),
(unsigned long)__save_stack_trace);
}
walk_stackframe(tsk, &frame, save_trace, &data);
put_task_stack(tsk);
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
__save_stack_trace(tsk, trace, 1);
}
void save_stack_trace(struct stack_trace *trace)
{
__save_stack_trace(current, trace, 0);
}
EXPORT_SYMBOL_GPL(save_stack_trace);
#endif