linux/arch/arm64/kernel/stacktrace.c

447 lines
11 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/efi.h>
#include <linux/export.h>
#include <linux/filter.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 17:33:41 +09:00
#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/efi.h>
#include <asm/irq.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
/*
* Kernel unwind state
*
* @common: Common unwind state.
* @task: The task being unwound.
* @kr_cur: When KRETPROBES is selected, holds the kretprobe instance
* associated with the most recently encountered replacement lr
* value.
*/
struct kunwind_state {
struct unwind_state common;
struct task_struct *task;
#ifdef CONFIG_KRETPROBES
struct llist_node *kr_cur;
#endif
};
static __always_inline void
kunwind_init(struct kunwind_state *state,
struct task_struct *task)
{
unwind_init_common(&state->common);
state->task = task;
}
/*
* Start an unwind from a pt_regs.
*
* The unwind will begin at the PC within the regs.
*
* The regs must be on a stack currently owned by the calling task.
*/
static __always_inline void
kunwind_init_from_regs(struct kunwind_state *state,
struct pt_regs *regs)
{
kunwind_init(state, current);
state->common.fp = regs->regs[29];
state->common.pc = regs->pc;
}
/*
* Start an unwind from a caller.
*
* The unwind will begin at the caller of whichever function this is inlined
* into.
*
* The function which invokes this must be noinline.
*/
static __always_inline void
kunwind_init_from_caller(struct kunwind_state *state)
{
kunwind_init(state, current);
state->common.fp = (unsigned long)__builtin_frame_address(1);
state->common.pc = (unsigned long)__builtin_return_address(0);
}
/*
* Start an unwind from a blocked task.
*
* The unwind will begin at the blocked tasks saved PC (i.e. the caller of
* cpu_switch_to()).
*
* The caller should ensure the task is blocked in cpu_switch_to() for the
* duration of the unwind, or the unwind will be bogus. It is never valid to
* call this for the current task.
*/
static __always_inline void
kunwind_init_from_task(struct kunwind_state *state,
struct task_struct *task)
{
kunwind_init(state, task);
state->common.fp = thread_saved_fp(task);
state->common.pc = thread_saved_pc(task);
}
static __always_inline int
kunwind_recover_return_address(struct kunwind_state *state)
{
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
if (state->task->ret_stack &&
(state->common.pc == (unsigned long)return_to_handler)) {
unsigned long orig_pc;
orig_pc = ftrace_graph_ret_addr(state->task, NULL,
state->common.pc,
(void *)state->common.fp);
if (WARN_ON_ONCE(state->common.pc == orig_pc))
return -EINVAL;
state->common.pc = orig_pc;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#ifdef CONFIG_KRETPROBES
if (is_kretprobe_trampoline(state->common.pc)) {
unsigned long orig_pc;
orig_pc = kretprobe_find_ret_addr(state->task,
(void *)state->common.fp,
&state->kr_cur);
state->common.pc = orig_pc;
}
#endif /* CONFIG_KRETPROBES */
return 0;
}
/*
* 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.
*/
static __always_inline int
kunwind_next(struct kunwind_state *state)
{
struct task_struct *tsk = state->task;
unsigned long fp = state->common.fp;
int err;
/* Final frame; nothing to unwind */
if (fp == (unsigned long)task_pt_regs(tsk)->stackframe)
return -ENOENT;
err = unwind_next_frame_record(&state->common);
if (err)
return err;
state->common.pc = ptrauth_strip_kernel_insn_pac(state->common.pc);
return kunwind_recover_return_address(state);
}
arm64: stacktrace: factor out kunwind_stack_walk() Currently arm64 uses the generic arch_stack_walk() interface for all stack walking code. This only passes a PC value and cookie to the unwind callback, whereas we'd like to pass some additional information in some cases. For example, the BPF exception unwinder wants the FP, for reliable stacktrace we'll want to perform additional checks on other portions of unwind state, and we'd like to expand the information printed by dump_backtrace() to include provenance and reliability information. As preparation for all of the above, this patch factors the core unwind logic out of arch_stack_walk() and into a new kunwind_stack_walk() function which provides all of the unwind state to a callback function. The existing arch_stack_walk() interface is implemented atop this. The kunwind_stack_walk() function is intended to be a private implementation detail of unwinders in stacktrace.c, and not something to be exported generally to kernel code. It is __always_inline'd into its caller so that neither it or its caller appear in stactraces (which is the existing/required behavior for arch_stack_walk() and friends) and so that the compiler can optimize away some of the indirection. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Puranjay Mohan <puranjay12@gmail.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Puranjay Mohan <puranjay12@gmail.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20231124110511.2795958-3-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-11-24 11:05:11 +00:00
typedef bool (*kunwind_consume_fn)(const struct kunwind_state *state, void *cookie);
static __always_inline void
arm64: stacktrace: factor out kunwind_stack_walk() Currently arm64 uses the generic arch_stack_walk() interface for all stack walking code. This only passes a PC value and cookie to the unwind callback, whereas we'd like to pass some additional information in some cases. For example, the BPF exception unwinder wants the FP, for reliable stacktrace we'll want to perform additional checks on other portions of unwind state, and we'd like to expand the information printed by dump_backtrace() to include provenance and reliability information. As preparation for all of the above, this patch factors the core unwind logic out of arch_stack_walk() and into a new kunwind_stack_walk() function which provides all of the unwind state to a callback function. The existing arch_stack_walk() interface is implemented atop this. The kunwind_stack_walk() function is intended to be a private implementation detail of unwinders in stacktrace.c, and not something to be exported generally to kernel code. It is __always_inline'd into its caller so that neither it or its caller appear in stactraces (which is the existing/required behavior for arch_stack_walk() and friends) and so that the compiler can optimize away some of the indirection. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Puranjay Mohan <puranjay12@gmail.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Puranjay Mohan <puranjay12@gmail.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20231124110511.2795958-3-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-11-24 11:05:11 +00:00
do_kunwind(struct kunwind_state *state, kunwind_consume_fn consume_state,
void *cookie)
{
if (kunwind_recover_return_address(state))
return;
while (1) {
int ret;
arm64: stacktrace: factor out kunwind_stack_walk() Currently arm64 uses the generic arch_stack_walk() interface for all stack walking code. This only passes a PC value and cookie to the unwind callback, whereas we'd like to pass some additional information in some cases. For example, the BPF exception unwinder wants the FP, for reliable stacktrace we'll want to perform additional checks on other portions of unwind state, and we'd like to expand the information printed by dump_backtrace() to include provenance and reliability information. As preparation for all of the above, this patch factors the core unwind logic out of arch_stack_walk() and into a new kunwind_stack_walk() function which provides all of the unwind state to a callback function. The existing arch_stack_walk() interface is implemented atop this. The kunwind_stack_walk() function is intended to be a private implementation detail of unwinders in stacktrace.c, and not something to be exported generally to kernel code. It is __always_inline'd into its caller so that neither it or its caller appear in stactraces (which is the existing/required behavior for arch_stack_walk() and friends) and so that the compiler can optimize away some of the indirection. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Puranjay Mohan <puranjay12@gmail.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Puranjay Mohan <puranjay12@gmail.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20231124110511.2795958-3-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-11-24 11:05:11 +00:00
if (!consume_state(state, cookie))
break;
ret = kunwind_next(state);
if (ret < 0)
break;
}
}
arm64: stacktrace: track all stack boundaries explicitly Currently we call an on_accessible_stack() callback for each step of the unwinder, requiring redundant work to be performed in the core of the unwind loop (e.g. disabling preemption around accesses to per-cpu variables containing stack boundaries). To prevent unwind loops which go through a stack multiple times, we have to track the set of unwound stacks, requiring a stack_type enum which needs to cater for all the stacks of all possible callees. To prevent loops within a stack, we must track the prior FP values. This patch reworks the unwinder to minimize the work in the core of the unwinder, and to remove the need for the stack_type enum. The set of accessible stacks (and their boundaries) are determined at the start of the unwind, and the current stack is tracked during the unwind, with completed stacks removed from the set of accessible stacks. This makes the boundary checks more accurate (e.g. detecting overlapped frame records), and removes the need for separate tracking of the prior FP and visited stacks. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Cc: Fuad Tabba <tabba@google.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20220901130646.1316937-9-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-09-01 14:06:45 +01:00
/*
* Per-cpu stacks are only accessible when unwinding the current task in a
* non-preemptible context.
*/
#define STACKINFO_CPU(name) \
({ \
((task == current) && !preemptible()) \
? stackinfo_get_##name() \
: stackinfo_get_unknown(); \
})
/*
* SDEI stacks are only accessible when unwinding the current task in an NMI
* context.
*/
#define STACKINFO_SDEI(name) \
({ \
((task == current) && in_nmi()) \
? stackinfo_get_sdei_##name() \
: stackinfo_get_unknown(); \
})
#define STACKINFO_EFI \
({ \
((task == current) && current_in_efi()) \
? stackinfo_get_efi() \
: stackinfo_get_unknown(); \
})
arm64: stacktrace: factor out kunwind_stack_walk() Currently arm64 uses the generic arch_stack_walk() interface for all stack walking code. This only passes a PC value and cookie to the unwind callback, whereas we'd like to pass some additional information in some cases. For example, the BPF exception unwinder wants the FP, for reliable stacktrace we'll want to perform additional checks on other portions of unwind state, and we'd like to expand the information printed by dump_backtrace() to include provenance and reliability information. As preparation for all of the above, this patch factors the core unwind logic out of arch_stack_walk() and into a new kunwind_stack_walk() function which provides all of the unwind state to a callback function. The existing arch_stack_walk() interface is implemented atop this. The kunwind_stack_walk() function is intended to be a private implementation detail of unwinders in stacktrace.c, and not something to be exported generally to kernel code. It is __always_inline'd into its caller so that neither it or its caller appear in stactraces (which is the existing/required behavior for arch_stack_walk() and friends) and so that the compiler can optimize away some of the indirection. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Puranjay Mohan <puranjay12@gmail.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Puranjay Mohan <puranjay12@gmail.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20231124110511.2795958-3-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-11-24 11:05:11 +00:00
static __always_inline void
kunwind_stack_walk(kunwind_consume_fn consume_state,
void *cookie, struct task_struct *task,
struct pt_regs *regs)
{
arm64: stacktrace: track all stack boundaries explicitly Currently we call an on_accessible_stack() callback for each step of the unwinder, requiring redundant work to be performed in the core of the unwind loop (e.g. disabling preemption around accesses to per-cpu variables containing stack boundaries). To prevent unwind loops which go through a stack multiple times, we have to track the set of unwound stacks, requiring a stack_type enum which needs to cater for all the stacks of all possible callees. To prevent loops within a stack, we must track the prior FP values. This patch reworks the unwinder to minimize the work in the core of the unwinder, and to remove the need for the stack_type enum. The set of accessible stacks (and their boundaries) are determined at the start of the unwind, and the current stack is tracked during the unwind, with completed stacks removed from the set of accessible stacks. This makes the boundary checks more accurate (e.g. detecting overlapped frame records), and removes the need for separate tracking of the prior FP and visited stacks. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Cc: Fuad Tabba <tabba@google.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20220901130646.1316937-9-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-09-01 14:06:45 +01:00
struct stack_info stacks[] = {
stackinfo_get_task(task),
STACKINFO_CPU(irq),
#if defined(CONFIG_VMAP_STACK)
STACKINFO_CPU(overflow),
#endif
#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_ARM_SDE_INTERFACE)
STACKINFO_SDEI(normal),
STACKINFO_SDEI(critical),
#endif
#ifdef CONFIG_EFI
STACKINFO_EFI,
arm64: stacktrace: track all stack boundaries explicitly Currently we call an on_accessible_stack() callback for each step of the unwinder, requiring redundant work to be performed in the core of the unwind loop (e.g. disabling preemption around accesses to per-cpu variables containing stack boundaries). To prevent unwind loops which go through a stack multiple times, we have to track the set of unwound stacks, requiring a stack_type enum which needs to cater for all the stacks of all possible callees. To prevent loops within a stack, we must track the prior FP values. This patch reworks the unwinder to minimize the work in the core of the unwinder, and to remove the need for the stack_type enum. The set of accessible stacks (and their boundaries) are determined at the start of the unwind, and the current stack is tracked during the unwind, with completed stacks removed from the set of accessible stacks. This makes the boundary checks more accurate (e.g. detecting overlapped frame records), and removes the need for separate tracking of the prior FP and visited stacks. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Cc: Fuad Tabba <tabba@google.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20220901130646.1316937-9-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-09-01 14:06:45 +01:00
#endif
};
struct kunwind_state state = {
.common = {
.stacks = stacks,
.nr_stacks = ARRAY_SIZE(stacks),
},
arm64: stacktrace: track all stack boundaries explicitly Currently we call an on_accessible_stack() callback for each step of the unwinder, requiring redundant work to be performed in the core of the unwind loop (e.g. disabling preemption around accesses to per-cpu variables containing stack boundaries). To prevent unwind loops which go through a stack multiple times, we have to track the set of unwound stacks, requiring a stack_type enum which needs to cater for all the stacks of all possible callees. To prevent loops within a stack, we must track the prior FP values. This patch reworks the unwinder to minimize the work in the core of the unwinder, and to remove the need for the stack_type enum. The set of accessible stacks (and their boundaries) are determined at the start of the unwind, and the current stack is tracked during the unwind, with completed stacks removed from the set of accessible stacks. This makes the boundary checks more accurate (e.g. detecting overlapped frame records), and removes the need for separate tracking of the prior FP and visited stacks. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Cc: Fuad Tabba <tabba@google.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20220901130646.1316937-9-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2022-09-01 14:06:45 +01:00
};
if (regs) {
if (task != current)
return;
kunwind_init_from_regs(&state, regs);
} else if (task == current) {
kunwind_init_from_caller(&state);
} else {
kunwind_init_from_task(&state, task);
}
arm64: stacktrace: factor out kunwind_stack_walk() Currently arm64 uses the generic arch_stack_walk() interface for all stack walking code. This only passes a PC value and cookie to the unwind callback, whereas we'd like to pass some additional information in some cases. For example, the BPF exception unwinder wants the FP, for reliable stacktrace we'll want to perform additional checks on other portions of unwind state, and we'd like to expand the information printed by dump_backtrace() to include provenance and reliability information. As preparation for all of the above, this patch factors the core unwind logic out of arch_stack_walk() and into a new kunwind_stack_walk() function which provides all of the unwind state to a callback function. The existing arch_stack_walk() interface is implemented atop this. The kunwind_stack_walk() function is intended to be a private implementation detail of unwinders in stacktrace.c, and not something to be exported generally to kernel code. It is __always_inline'd into its caller so that neither it or its caller appear in stactraces (which is the existing/required behavior for arch_stack_walk() and friends) and so that the compiler can optimize away some of the indirection. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Puranjay Mohan <puranjay12@gmail.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Puranjay Mohan <puranjay12@gmail.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20231124110511.2795958-3-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-11-24 11:05:11 +00:00
do_kunwind(&state, consume_state, cookie);
}
struct kunwind_consume_entry_data {
stack_trace_consume_fn consume_entry;
void *cookie;
};
arm64: prohibit probing on arch_kunwind_consume_entry() Make arch_kunwind_consume_entry() as __always_inline otherwise the compiler might not inline it and allow attaching probes to it. Without this, just probing arch_kunwind_consume_entry() via <tracefs>/kprobe_events will crash the kernel on arm64. The crash can be reproduced using the following compiler and kernel combination: clang version 19.0.0git (https://github.com/llvm/llvm-project.git d68d29516102252f6bf6dc23fb22cef144ca1cb3) commit 87adedeba51a ("Merge tag 'net-6.8-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") [root@localhost ~]# echo 'p arch_kunwind_consume_entry' > /sys/kernel/debug/tracing/kprobe_events [root@localhost ~]# echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable Modules linked in: aes_ce_blk aes_ce_cipher ghash_ce sha2_ce virtio_net sha256_arm64 sha1_ce arm_smccc_trng net_failover failover virtio_mmio uio_pdrv_genirq uio sch_fq_codel dm_mod dax configfs CPU: 3 PID: 1405 Comm: bash Not tainted 6.8.0-rc6+ #14 Hardware name: linux,dummy-virt (DT) pstate: 604003c5 (nZCv DAIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : kprobe_breakpoint_handler+0x17c/0x258 lr : kprobe_breakpoint_handler+0x17c/0x258 sp : ffff800085d6ab60 x29: ffff800085d6ab60 x28: ffff0000066f0040 x27: ffff0000066f0b20 x26: ffff800081fa7b0c x25: 0000000000000002 x24: ffff00000b29bd18 x23: ffff00007904c590 x22: ffff800081fa6590 x21: ffff800081fa6588 x20: ffff00000b29bd18 x19: ffff800085d6ac40 x18: 0000000000000079 x17: 0000000000000001 x16: ffffffffffffffff x15: 0000000000000004 x14: ffff80008277a940 x13: 0000000000000003 x12: 0000000000000003 x11: 00000000fffeffff x10: c0000000fffeffff x9 : aa95616fdf80cc00 x8 : aa95616fdf80cc00 x7 : 205d343137373231 x6 : ffff800080fb48ec x5 : 0000000000000000 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000000 x1 : ffff800085d6a910 x0 : 0000000000000079 Call trace: kprobes: Failed to recover from reentered kprobes. kprobes: Dump kprobe: .symbol_name = arch_kunwind_consume_entry, .offset = 0, .addr = arch_kunwind_consume_entry+0x0/0x40 ------------[ cut here ]------------ kernel BUG at arch/arm64/kernel/probes/kprobes.c:241! kprobes: Failed to recover from reentered kprobes. kprobes: Dump kprobe: .symbol_name = arch_kunwind_consume_entry, .offset = 0, .addr = arch_kunwind_consume_entry+0x0/0x40 Fixes: 1aba06e7b2b4 ("arm64: stacktrace: factor out kunwind_stack_walk()") Signed-off-by: Puranjay Mohan <puranjay12@gmail.com> Reviewed-by: Mark Rutland <mark.rutland@arm.com> Link: https://lore.kernel.org/r/20240229231620.24846-1-puranjay12@gmail.com Signed-off-by: Will Deacon <will@kernel.org>
2024-02-29 23:16:20 +00:00
static __always_inline bool
arm64: stacktrace: factor out kunwind_stack_walk() Currently arm64 uses the generic arch_stack_walk() interface for all stack walking code. This only passes a PC value and cookie to the unwind callback, whereas we'd like to pass some additional information in some cases. For example, the BPF exception unwinder wants the FP, for reliable stacktrace we'll want to perform additional checks on other portions of unwind state, and we'd like to expand the information printed by dump_backtrace() to include provenance and reliability information. As preparation for all of the above, this patch factors the core unwind logic out of arch_stack_walk() and into a new kunwind_stack_walk() function which provides all of the unwind state to a callback function. The existing arch_stack_walk() interface is implemented atop this. The kunwind_stack_walk() function is intended to be a private implementation detail of unwinders in stacktrace.c, and not something to be exported generally to kernel code. It is __always_inline'd into its caller so that neither it or its caller appear in stactraces (which is the existing/required behavior for arch_stack_walk() and friends) and so that the compiler can optimize away some of the indirection. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Cc: Mark Brown <broonie@kernel.org> Cc: Puranjay Mohan <puranjay12@gmail.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Kalesh Singh <kaleshsingh@google.com> Reviewed-by: Puranjay Mohan <puranjay12@gmail.com> Reviewed-by: Madhavan T. Venkataraman <madvenka@linux.microsoft.com> Reviewed-by: Mark Brown <broonie@kernel.org> Link: https://lore.kernel.org/r/20231124110511.2795958-3-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-11-24 11:05:11 +00:00
arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie)
{
struct kunwind_consume_entry_data *data = cookie;
return data->consume_entry(data->cookie, state->common.pc);
}
noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task,
struct pt_regs *regs)
{
struct kunwind_consume_entry_data data = {
.consume_entry = consume_entry,
.cookie = cookie,
};
kunwind_stack_walk(arch_kunwind_consume_entry, &data, task, regs);
}
struct bpf_unwind_consume_entry_data {
bool (*consume_entry)(void *cookie, u64 ip, u64 sp, u64 fp);
void *cookie;
};
static bool
arch_bpf_unwind_consume_entry(const struct kunwind_state *state, void *cookie)
{
struct bpf_unwind_consume_entry_data *data = cookie;
return data->consume_entry(data->cookie, state->common.pc, 0,
state->common.fp);
}
noinline noinstr void arch_bpf_stack_walk(bool (*consume_entry)(void *cookie, u64 ip, u64 sp,
u64 fp), void *cookie)
{
struct bpf_unwind_consume_entry_data data = {
.consume_entry = consume_entry,
.cookie = cookie,
};
kunwind_stack_walk(arch_bpf_unwind_consume_entry, &data, current, NULL);
}
static bool dump_backtrace_entry(void *arg, unsigned long where)
{
char *loglvl = arg;
printk("%s %pSb\n", loglvl, (void *)where);
return true;
}
void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
const char *loglvl)
{
pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
if (regs && user_mode(regs))
return;
if (!tsk)
tsk = current;
if (!try_get_task_stack(tsk))
return;
printk("%sCall trace:\n", loglvl);
arch_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs);
put_task_stack(tsk);
}
void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
{
dump_backtrace(NULL, tsk, loglvl);
barrier();
}
/*
* The struct defined for userspace stack frame in AARCH64 mode.
*/
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 *
unwind_user_frame(struct frame_tail __user *tail, void *cookie,
stack_trace_consume_fn consume_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_user_insn_pac(buftail.lr);
if (!consume_entry(cookie, lr))
return NULL;
/*
* 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 *
unwind_compat_user_frame(struct compat_frame_tail __user *tail, void *cookie,
stack_trace_consume_fn consume_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;
if (!consume_entry(cookie, buftail.lr))
return NULL;
/*
* 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 arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
const struct pt_regs *regs)
{
if (!consume_entry(cookie, regs->pc))
return;
if (!compat_user_mode(regs)) {
/* AARCH64 mode */
struct frame_tail __user *tail;
tail = (struct frame_tail __user *)regs->regs[29];
while (tail && !((unsigned long)tail & 0x7))
tail = unwind_user_frame(tail, cookie, consume_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 (tail && !((unsigned long)tail & 0x3))
tail = unwind_compat_user_frame(tail, cookie, consume_entry);
#endif
}
}