09c0796adf
The major update to this release is that there's a new arch config option called: CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS. Currently, only x86_64 enables it. All the ftrace callbacks now take a struct ftrace_regs instead of a struct pt_regs. If the architecture has HAVE_DYNAMIC_FTRACE_WITH_ARGS enabled, then the ftrace_regs will have enough information to read the arguments of the function being traced, as well as access to the stack pointer. This way, if a user (like live kernel patching) only cares about the arguments, then it can avoid using the heavier weight "regs" callback, that puts in enough information in the struct ftrace_regs to simulate a breakpoint exception (needed for kprobes). New config option that audits the timestamps of the ftrace ring buffer at most every event recorded. The "check_buffer()" calls will conflict with mainline, because I purposely added the check without including the fix that it caught, which is in mainline. Running a kernel built from the commit of the added check will trigger it. Ftrace recursion protection has been cleaned up to move the protection to the callback itself (this saves on an extra function call for those callbacks). Perf now handles its own RCU protection and does not depend on ftrace to do it for it (saving on that extra function call). New debug option to add "recursed_functions" file to tracefs that lists all the places that triggered the recursion protection of the function tracer. This will show where things need to be fixed as recursion slows down the function tracer. The eval enum mapping updates done at boot up are now offloaded to a work queue, as it caused a noticeable pause on slow embedded boards. Various clean ups and last minute fixes. -----BEGIN PGP SIGNATURE----- iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCX9uq8xQccm9zdGVkdEBn b29kbWlzLm9yZwAKCRAp5XQQmuv6qtrwAQCHevqWMjKc1Q76bnCgwB0AbFKB6vqy 5b6g/co5+ihv8wD/eJPWlZMAt97zTVW7bdp5qj/GTiCDbAsODMZ597LsxA0= =rZEz -----END PGP SIGNATURE----- Merge tag 'trace-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace Pull tracing updates from Steven Rostedt: "The major update to this release is that there's a new arch config option called CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS. Currently, only x86_64 enables it. All the ftrace callbacks now take a struct ftrace_regs instead of a struct pt_regs. If the architecture has HAVE_DYNAMIC_FTRACE_WITH_ARGS enabled, then the ftrace_regs will have enough information to read the arguments of the function being traced, as well as access to the stack pointer. This way, if a user (like live kernel patching) only cares about the arguments, then it can avoid using the heavier weight "regs" callback, that puts in enough information in the struct ftrace_regs to simulate a breakpoint exception (needed for kprobes). A new config option that audits the timestamps of the ftrace ring buffer at most every event recorded. Ftrace recursion protection has been cleaned up to move the protection to the callback itself (this saves on an extra function call for those callbacks). Perf now handles its own RCU protection and does not depend on ftrace to do it for it (saving on that extra function call). New debug option to add "recursed_functions" file to tracefs that lists all the places that triggered the recursion protection of the function tracer. This will show where things need to be fixed as recursion slows down the function tracer. The eval enum mapping updates done at boot up are now offloaded to a work queue, as it caused a noticeable pause on slow embedded boards. Various clean ups and last minute fixes" * tag 'trace-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (33 commits) tracing: Offload eval map updates to a work queue Revert: "ring-buffer: Remove HAVE_64BIT_ALIGNED_ACCESS" ring-buffer: Add rb_check_bpage in __rb_allocate_pages ring-buffer: Fix two typos in comments tracing: Drop unneeded assignment in ring_buffer_resize() tracing: Disable ftrace selftests when any tracer is running seq_buf: Avoid type mismatch for seq_buf_init ring-buffer: Fix a typo in function description ring-buffer: Remove obsolete rb_event_is_commit() ring-buffer: Add test to validate the time stamp deltas ftrace/documentation: Fix RST C code blocks tracing: Clean up after filter logic rewriting tracing: Remove the useless value assignment in test_create_synth_event() livepatch: Use the default ftrace_ops instead of REGS when ARGS is available ftrace/x86: Allow for arguments to be passed in to ftrace_regs by default ftrace: Have the callbacks receive a struct ftrace_regs instead of pt_regs MAINTAINERS: assign ./fs/tracefs to TRACING tracing: Fix some typos in comments ftrace: Remove unused varible 'ret' ring-buffer: Add recording of ring buffer recursion into recursed_functions ...
217 lines
5.6 KiB
C
217 lines
5.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Dynamic function tracer architecture backend.
|
|
*
|
|
* Copyright IBM Corp. 2009,2014
|
|
*
|
|
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
|
|
* Martin Schwidefsky <schwidefsky@de.ibm.com>
|
|
*/
|
|
|
|
#include <linux/moduleloader.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/types.h>
|
|
#include <linux/kprobes.h>
|
|
#include <trace/syscall.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/set_memory.h>
|
|
#include "entry.h"
|
|
|
|
/*
|
|
* To generate function prologue either gcc's hotpatch feature (since gcc 4.8)
|
|
* or a combination of -pg -mrecord-mcount -mnop-mcount -mfentry flags
|
|
* (since gcc 9 / clang 10) is used.
|
|
* In both cases the original and also the disabled function prologue contains
|
|
* only a single six byte instruction and looks like this:
|
|
* > brcl 0,0 # offset 0
|
|
* To enable ftrace the code gets patched like above and afterwards looks
|
|
* like this:
|
|
* > brasl %r0,ftrace_caller # offset 0
|
|
*
|
|
* The instruction will be patched by ftrace_make_call / ftrace_make_nop.
|
|
* The ftrace function gets called with a non-standard C function call ABI
|
|
* where r0 contains the return address. It is also expected that the called
|
|
* function only clobbers r0 and r1, but restores r2-r15.
|
|
* For module code we can't directly jump to ftrace caller, but need a
|
|
* trampoline (ftrace_plt), which clobbers also r1.
|
|
*/
|
|
|
|
unsigned long ftrace_plt;
|
|
|
|
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
|
|
unsigned long addr)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
|
|
unsigned long addr)
|
|
{
|
|
struct ftrace_insn orig, new, old;
|
|
|
|
if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
|
|
return -EFAULT;
|
|
/* Replace ftrace call with a nop. */
|
|
ftrace_generate_call_insn(&orig, rec->ip);
|
|
ftrace_generate_nop_insn(&new);
|
|
|
|
/* Verify that the to be replaced code matches what we expect. */
|
|
if (memcmp(&orig, &old, sizeof(old)))
|
|
return -EINVAL;
|
|
s390_kernel_write((void *) rec->ip, &new, sizeof(new));
|
|
return 0;
|
|
}
|
|
|
|
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
|
|
{
|
|
struct ftrace_insn orig, new, old;
|
|
|
|
if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
|
|
return -EFAULT;
|
|
/* Replace nop with an ftrace call. */
|
|
ftrace_generate_nop_insn(&orig);
|
|
ftrace_generate_call_insn(&new, rec->ip);
|
|
|
|
/* Verify that the to be replaced code matches what we expect. */
|
|
if (memcmp(&orig, &old, sizeof(old)))
|
|
return -EINVAL;
|
|
s390_kernel_write((void *) rec->ip, &new, sizeof(new));
|
|
return 0;
|
|
}
|
|
|
|
int ftrace_update_ftrace_func(ftrace_func_t func)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
int __init ftrace_dyn_arch_init(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_MODULES
|
|
|
|
static int __init ftrace_plt_init(void)
|
|
{
|
|
unsigned int *ip;
|
|
|
|
ftrace_plt = (unsigned long) module_alloc(PAGE_SIZE);
|
|
if (!ftrace_plt)
|
|
panic("cannot allocate ftrace plt\n");
|
|
ip = (unsigned int *) ftrace_plt;
|
|
ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */
|
|
ip[1] = 0x100a0004;
|
|
ip[2] = 0x07f10000;
|
|
ip[3] = FTRACE_ADDR >> 32;
|
|
ip[4] = FTRACE_ADDR & 0xffffffff;
|
|
set_memory_ro(ftrace_plt, 1);
|
|
return 0;
|
|
}
|
|
device_initcall(ftrace_plt_init);
|
|
|
|
#endif /* CONFIG_MODULES */
|
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
/*
|
|
* Hook the return address and push it in the stack of return addresses
|
|
* in current thread info.
|
|
*/
|
|
unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp,
|
|
unsigned long ip)
|
|
{
|
|
if (unlikely(ftrace_graph_is_dead()))
|
|
goto out;
|
|
if (unlikely(atomic_read(¤t->tracing_graph_pause)))
|
|
goto out;
|
|
ip -= MCOUNT_INSN_SIZE;
|
|
if (!function_graph_enter(ra, ip, 0, (void *) sp))
|
|
ra = (unsigned long) return_to_handler;
|
|
out:
|
|
return ra;
|
|
}
|
|
NOKPROBE_SYMBOL(prepare_ftrace_return);
|
|
|
|
/*
|
|
* Patch the kernel code at ftrace_graph_caller location. The instruction
|
|
* there is branch relative on condition. To enable the ftrace graph code
|
|
* block, we simply patch the mask field of the instruction to zero and
|
|
* turn the instruction into a nop.
|
|
* To disable the ftrace graph code the mask field will be patched to
|
|
* all ones, which turns the instruction into an unconditional branch.
|
|
*/
|
|
int ftrace_enable_ftrace_graph_caller(void)
|
|
{
|
|
u8 op = 0x04; /* set mask field to zero */
|
|
|
|
s390_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
|
|
return 0;
|
|
}
|
|
|
|
int ftrace_disable_ftrace_graph_caller(void)
|
|
{
|
|
u8 op = 0xf4; /* set mask field to all ones */
|
|
|
|
s390_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
|
|
return 0;
|
|
}
|
|
|
|
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
|
|
|
|
#ifdef CONFIG_KPROBES_ON_FTRACE
|
|
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
|
|
struct ftrace_ops *ops, struct ftrace_regs *fregs)
|
|
{
|
|
struct kprobe_ctlblk *kcb;
|
|
struct pt_regs *regs;
|
|
struct kprobe *p;
|
|
int bit;
|
|
|
|
bit = ftrace_test_recursion_trylock(ip, parent_ip);
|
|
if (bit < 0)
|
|
return;
|
|
|
|
regs = ftrace_get_regs(fregs);
|
|
preempt_disable_notrace();
|
|
p = get_kprobe((kprobe_opcode_t *)ip);
|
|
if (unlikely(!p) || kprobe_disabled(p))
|
|
goto out;
|
|
|
|
if (kprobe_running()) {
|
|
kprobes_inc_nmissed_count(p);
|
|
goto out;
|
|
}
|
|
|
|
__this_cpu_write(current_kprobe, p);
|
|
|
|
kcb = get_kprobe_ctlblk();
|
|
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
|
|
|
|
instruction_pointer_set(regs, ip);
|
|
|
|
if (!p->pre_handler || !p->pre_handler(p, regs)) {
|
|
|
|
instruction_pointer_set(regs, ip + MCOUNT_INSN_SIZE);
|
|
|
|
if (unlikely(p->post_handler)) {
|
|
kcb->kprobe_status = KPROBE_HIT_SSDONE;
|
|
p->post_handler(p, regs, 0);
|
|
}
|
|
}
|
|
__this_cpu_write(current_kprobe, NULL);
|
|
out:
|
|
preempt_enable_notrace();
|
|
ftrace_test_recursion_unlock(bit);
|
|
}
|
|
NOKPROBE_SYMBOL(kprobe_ftrace_handler);
|
|
|
|
int arch_prepare_kprobe_ftrace(struct kprobe *p)
|
|
{
|
|
p->ainsn.insn = NULL;
|
|
return 0;
|
|
}
|
|
#endif
|