mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 11:22:33 +07:00
86c269fea3
Perf reports user regs for kernel-mode samples so that samples can be backtraced through user code. The old code was very broken in syscall context, resulting in useless backtraces. The new code, in contrast, is still dangerously racy, but it should at least work most of the time. Tested-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: chenggang.qcg@taobao.com Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/243560c26ff0f739978e2459e203f6515367634d.1420396372.git.luto@amacapital.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
196 lines
5.4 KiB
C
196 lines
5.4 KiB
C
#include <linux/errno.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/stddef.h>
|
|
#include <asm/perf_regs.h>
|
|
#include <asm/ptrace.h>
|
|
|
|
#ifdef CONFIG_X86_32
|
|
#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX
|
|
#else
|
|
#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX
|
|
#endif
|
|
|
|
#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
|
|
|
|
static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
|
|
PT_REGS_OFFSET(PERF_REG_X86_AX, ax),
|
|
PT_REGS_OFFSET(PERF_REG_X86_BX, bx),
|
|
PT_REGS_OFFSET(PERF_REG_X86_CX, cx),
|
|
PT_REGS_OFFSET(PERF_REG_X86_DX, dx),
|
|
PT_REGS_OFFSET(PERF_REG_X86_SI, si),
|
|
PT_REGS_OFFSET(PERF_REG_X86_DI, di),
|
|
PT_REGS_OFFSET(PERF_REG_X86_BP, bp),
|
|
PT_REGS_OFFSET(PERF_REG_X86_SP, sp),
|
|
PT_REGS_OFFSET(PERF_REG_X86_IP, ip),
|
|
PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags),
|
|
PT_REGS_OFFSET(PERF_REG_X86_CS, cs),
|
|
PT_REGS_OFFSET(PERF_REG_X86_SS, ss),
|
|
#ifdef CONFIG_X86_32
|
|
PT_REGS_OFFSET(PERF_REG_X86_DS, ds),
|
|
PT_REGS_OFFSET(PERF_REG_X86_ES, es),
|
|
PT_REGS_OFFSET(PERF_REG_X86_FS, fs),
|
|
PT_REGS_OFFSET(PERF_REG_X86_GS, gs),
|
|
#else
|
|
/*
|
|
* The pt_regs struct does not store
|
|
* ds, es, fs, gs in 64 bit mode.
|
|
*/
|
|
(unsigned int) -1,
|
|
(unsigned int) -1,
|
|
(unsigned int) -1,
|
|
(unsigned int) -1,
|
|
#endif
|
|
#ifdef CONFIG_X86_64
|
|
PT_REGS_OFFSET(PERF_REG_X86_R8, r8),
|
|
PT_REGS_OFFSET(PERF_REG_X86_R9, r9),
|
|
PT_REGS_OFFSET(PERF_REG_X86_R10, r10),
|
|
PT_REGS_OFFSET(PERF_REG_X86_R11, r11),
|
|
PT_REGS_OFFSET(PERF_REG_X86_R12, r12),
|
|
PT_REGS_OFFSET(PERF_REG_X86_R13, r13),
|
|
PT_REGS_OFFSET(PERF_REG_X86_R14, r14),
|
|
PT_REGS_OFFSET(PERF_REG_X86_R15, r15),
|
|
#endif
|
|
};
|
|
|
|
u64 perf_reg_value(struct pt_regs *regs, int idx)
|
|
{
|
|
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
|
|
return 0;
|
|
|
|
return regs_get_register(regs, pt_regs_offset[idx]);
|
|
}
|
|
|
|
#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
|
|
|
|
#ifdef CONFIG_X86_32
|
|
int perf_reg_validate(u64 mask)
|
|
{
|
|
if (!mask || mask & REG_RESERVED)
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
u64 perf_reg_abi(struct task_struct *task)
|
|
{
|
|
return PERF_SAMPLE_REGS_ABI_32;
|
|
}
|
|
|
|
void perf_get_regs_user(struct perf_regs *regs_user,
|
|
struct pt_regs *regs,
|
|
struct pt_regs *regs_user_copy)
|
|
{
|
|
regs_user->regs = task_pt_regs(current);
|
|
regs_user->abi = perf_reg_abi(current);
|
|
}
|
|
#else /* CONFIG_X86_64 */
|
|
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
|
|
(1ULL << PERF_REG_X86_ES) | \
|
|
(1ULL << PERF_REG_X86_FS) | \
|
|
(1ULL << PERF_REG_X86_GS))
|
|
|
|
int perf_reg_validate(u64 mask)
|
|
{
|
|
if (!mask || mask & REG_RESERVED)
|
|
return -EINVAL;
|
|
|
|
if (mask & REG_NOSUPPORT)
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
u64 perf_reg_abi(struct task_struct *task)
|
|
{
|
|
if (test_tsk_thread_flag(task, TIF_IA32))
|
|
return PERF_SAMPLE_REGS_ABI_32;
|
|
else
|
|
return PERF_SAMPLE_REGS_ABI_64;
|
|
}
|
|
|
|
void perf_get_regs_user(struct perf_regs *regs_user,
|
|
struct pt_regs *regs,
|
|
struct pt_regs *regs_user_copy)
|
|
{
|
|
struct pt_regs *user_regs = task_pt_regs(current);
|
|
|
|
/*
|
|
* If we're in an NMI that interrupted task_pt_regs setup, then
|
|
* we can't sample user regs at all. This check isn't really
|
|
* sufficient, though, as we could be in an NMI inside an interrupt
|
|
* that happened during task_pt_regs setup.
|
|
*/
|
|
if (regs->sp > (unsigned long)&user_regs->r11 &&
|
|
regs->sp <= (unsigned long)(user_regs + 1)) {
|
|
regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
|
|
regs_user->regs = NULL;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* RIP, flags, and the argument registers are usually saved.
|
|
* orig_ax is probably okay, too.
|
|
*/
|
|
regs_user_copy->ip = user_regs->ip;
|
|
regs_user_copy->cx = user_regs->cx;
|
|
regs_user_copy->dx = user_regs->dx;
|
|
regs_user_copy->si = user_regs->si;
|
|
regs_user_copy->di = user_regs->di;
|
|
regs_user_copy->r8 = user_regs->r8;
|
|
regs_user_copy->r9 = user_regs->r9;
|
|
regs_user_copy->r10 = user_regs->r10;
|
|
regs_user_copy->r11 = user_regs->r11;
|
|
regs_user_copy->orig_ax = user_regs->orig_ax;
|
|
regs_user_copy->flags = user_regs->flags;
|
|
|
|
/*
|
|
* Don't even try to report the "rest" regs.
|
|
*/
|
|
regs_user_copy->bx = -1;
|
|
regs_user_copy->bp = -1;
|
|
regs_user_copy->r12 = -1;
|
|
regs_user_copy->r13 = -1;
|
|
regs_user_copy->r14 = -1;
|
|
regs_user_copy->r15 = -1;
|
|
|
|
/*
|
|
* For this to be at all useful, we need a reasonable guess for
|
|
* sp and the ABI. Be careful: we're in NMI context, and we're
|
|
* considering current to be the current task, so we should
|
|
* be careful not to look at any other percpu variables that might
|
|
* change during context switches.
|
|
*/
|
|
if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
|
|
task_thread_info(current)->status & TS_COMPAT) {
|
|
/* Easy case: we're in a compat syscall. */
|
|
regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
|
|
regs_user_copy->sp = user_regs->sp;
|
|
regs_user_copy->cs = user_regs->cs;
|
|
regs_user_copy->ss = user_regs->ss;
|
|
} else if (user_regs->orig_ax != -1) {
|
|
/*
|
|
* We're probably in a 64-bit syscall.
|
|
* Warning: this code is severely racy. At least it's better
|
|
* than just blindly copying user_regs.
|
|
*/
|
|
regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
|
|
regs_user_copy->sp = this_cpu_read(old_rsp);
|
|
regs_user_copy->cs = __USER_CS;
|
|
regs_user_copy->ss = __USER_DS;
|
|
regs_user_copy->cx = -1; /* usually contains garbage */
|
|
} else {
|
|
/* We're probably in an interrupt or exception. */
|
|
regs_user->abi = user_64bit_mode(user_regs) ?
|
|
PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
|
|
regs_user_copy->sp = user_regs->sp;
|
|
regs_user_copy->cs = user_regs->cs;
|
|
regs_user_copy->ss = user_regs->ss;
|
|
}
|
|
|
|
regs_user->regs = regs_user_copy;
|
|
}
|
|
#endif /* CONFIG_X86_32 */
|