perf core: Pass max stack as a perf_callchain_entry context

This makes perf_callchain_{user,kernel}() receive the max stack
as context for the perf_callchain_entry, instead of accessing
the global sysctl_perf_event_max_stack.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent a831100a
......@@ -48,7 +48,7 @@ struct arc_callchain_trace {
static int callchain_trace(unsigned int addr, void *data)
{
struct arc_callchain_trace *ctrl = data;
struct perf_callchain_entry *entry = ctrl->perf_stuff;
struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
perf_callchain_store(entry, addr);
if (ctrl->depth++ < 3)
......@@ -58,7 +58,7 @@ static int callchain_trace(unsigned int addr, void *data)
}
void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct arc_callchain_trace ctrl = {
.depth = 0,
......@@ -69,7 +69,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
}
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
/*
* User stack can't be unwound trivially with kernel dwarf unwinder
......
......@@ -31,7 +31,7 @@ struct frame_tail {
*/
static struct frame_tail __user *
user_backtrace(struct frame_tail __user *tail,
struct perf_callchain_entry *entry)
struct perf_callchain_entry_ctx *entry)
{
struct frame_tail buftail;
unsigned long err;
......@@ -59,7 +59,7 @@ user_backtrace(struct frame_tail __user *tail,
}
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct frame_tail __user *tail;
......@@ -75,7 +75,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
tail = (struct frame_tail __user *)regs->ARM_fp - 1;
while ((entry->nr < sysctl_perf_event_max_stack) &&
while ((entry->entry->nr < entry->max_stack) &&
tail && !((unsigned long)tail & 0x3))
tail = user_backtrace(tail, entry);
}
......@@ -89,13 +89,13 @@ static int
callchain_trace(struct stackframe *fr,
void *data)
{
struct perf_callchain_entry *entry = data;
struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, fr->pc);
return 0;
}
void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct stackframe fr;
......
......@@ -31,7 +31,7 @@ struct frame_tail {
*/
static struct frame_tail __user *
user_backtrace(struct frame_tail __user *tail,
struct perf_callchain_entry *entry)
struct perf_callchain_entry_ctx *entry)
{
struct frame_tail buftail;
unsigned long err;
......@@ -76,7 +76,7 @@ struct compat_frame_tail {
static struct compat_frame_tail __user *
compat_user_backtrace(struct compat_frame_tail __user *tail,
struct perf_callchain_entry *entry)
struct perf_callchain_entry_ctx *entry)
{
struct compat_frame_tail buftail;
unsigned long err;
......@@ -106,7 +106,7 @@ compat_user_backtrace(struct compat_frame_tail __user *tail,
}
#endif /* CONFIG_COMPAT */
void perf_callchain_user(struct perf_callchain_entry *entry,
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
......@@ -122,7 +122,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
tail = (struct frame_tail __user *)regs->regs[29];
while (entry->nr < sysctl_perf_event_max_stack &&
while (entry->entry->nr < entry->max_stack &&
tail && !((unsigned long)tail & 0xf))
tail = user_backtrace(tail, entry);
} else {
......@@ -132,7 +132,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
while ((entry->nr < sysctl_perf_event_max_stack) &&
while ((entry->entry->nr < entry->max_stack) &&
tail && !((unsigned long)tail & 0x3))
tail = compat_user_backtrace(tail, entry);
#endif
......@@ -146,12 +146,12 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
*/
static int callchain_trace(struct stackframe *frame, void *data)
{
struct perf_callchain_entry *entry = data;
struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, frame->pc);
return 0;
}
void perf_callchain_kernel(struct perf_callchain_entry *entry,
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
struct stackframe frame;
......
......@@ -29,7 +29,7 @@ static bool is_valid_call(unsigned long calladdr)
static struct metag_frame __user *
user_backtrace(struct metag_frame __user *user_frame,
struct perf_callchain_entry *entry)
struct perf_callchain_entry_ctx *entry)
{
struct metag_frame frame;
unsigned long calladdr;
......@@ -56,7 +56,7 @@ user_backtrace(struct metag_frame __user *user_frame,
}
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
unsigned long sp = regs->ctx.AX[0].U0;
struct metag_frame __user *frame;
......@@ -65,7 +65,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
--frame;
while ((entry->nr < sysctl_perf_event_max_stack) && frame)
while ((entry->entry->nr < entry->max_stack) && frame)
frame = user_backtrace(frame, entry);
}
......@@ -78,13 +78,13 @@ static int
callchain_trace(struct stackframe *fr,
void *data)
{
struct perf_callchain_entry *entry = data;
struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, fr->pc);
return 0;
}
void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct stackframe fr;
......
......@@ -25,8 +25,8 @@
* the user stack callchains, we will add it here.
*/
static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
unsigned long reg29)
static void save_raw_perf_callchain(struct perf_callchain_entry_ctx *entry,
unsigned long reg29)
{
unsigned long *sp = (unsigned long *)reg29;
unsigned long addr;
......@@ -35,14 +35,14 @@ static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
addr = *sp++;
if (__kernel_text_address(addr)) {
perf_callchain_store(entry, addr);
if (entry->nr >= sysctl_perf_event_max_stack)
if (entry->entry->nr >= entry->max_stack)
break;
}
}
}
void perf_callchain_kernel(struct perf_callchain_entry *entry,
struct pt_regs *regs)
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long sp = regs->regs[29];
#ifdef CONFIG_KALLSYMS
......@@ -59,7 +59,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
}
do {
perf_callchain_store(entry, pc);
if (entry->nr >= sysctl_perf_event_max_stack)
if (entry->entry->nr >= entry->max_stack)
break;
pc = unwind_stack(current, &sp, pc, &ra);
} while (pc);
......
......@@ -47,7 +47,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
}
void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
unsigned long sp, next_sp;
unsigned long next_ip;
......@@ -232,7 +232,7 @@ static int sane_signal_64_frame(unsigned long sp)
puc == (unsigned long) &sf->uc;
}
static void perf_callchain_user_64(struct perf_callchain_entry *entry,
static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long sp, next_sp;
......@@ -247,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
while (entry->nr < sysctl_perf_event_max_stack) {
while (entry->entry->nr < entry->max_stack) {
fp = (unsigned long __user *) sp;
if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
return;
......@@ -319,7 +319,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
return rc;
}
static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
......@@ -439,7 +439,7 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
return mctx->mc_gregs;
}
static void perf_callchain_user_32(struct perf_callchain_entry *entry,
static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned int sp, next_sp;
......@@ -453,7 +453,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
while (entry->nr < sysctl_perf_event_max_stack) {
while (entry->entry->nr < entry->max_stack) {
fp = (unsigned int __user *) (unsigned long) sp;
if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
return;
......@@ -487,7 +487,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
}
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
if (current_is_64bit())
perf_callchain_user_64(entry, regs);
......
......@@ -224,13 +224,13 @@ arch_initcall(service_level_perf_register);
static int __perf_callchain_kernel(void *data, unsigned long address)
{
struct perf_callchain_entry *entry = data;
struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, address);
return 0;
}
void perf_callchain_kernel(struct perf_callchain_entry *entry,
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
if (user_mode(regs))
......
......@@ -21,7 +21,7 @@ static int callchain_stack(void *data, char *name)
static void callchain_address(void *data, unsigned long addr, int reliable)
{
struct perf_callchain_entry *entry = data;
struct perf_callchain_entry_ctx *entry = data;
if (reliable)
perf_callchain_store(entry, addr);
......@@ -33,7 +33,7 @@ static const struct stacktrace_ops callchain_ops = {
};
void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
perf_callchain_store(entry, regs->pc);
......
......@@ -1711,7 +1711,7 @@ static int __init init_hw_perf_events(void)
}
pure_initcall(init_hw_perf_events);
void perf_callchain_kernel(struct perf_callchain_entry *entry,
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long ksp, fp;
......@@ -1756,7 +1756,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
}
}
#endif
} while (entry->nr < sysctl_perf_event_max_stack);
} while (entry->entry->nr < entry->max_stack);
}
static inline int
......@@ -1769,7 +1769,7 @@ valid_user_frame(const void __user *fp, unsigned long size)
return (__range_not_ok(fp, size, TASK_SIZE) == 0);
}
static void perf_callchain_user_64(struct perf_callchain_entry *entry,
static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long ufp;
......@@ -1790,10 +1790,10 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
pc = sf.callers_pc;
ufp = (unsigned long)sf.fp + STACK_BIAS;
perf_callchain_store(entry, pc);
} while (entry->nr < sysctl_perf_event_max_stack);
} while (entry->entry->nr < entry->max_stack);
}
static void perf_callchain_user_32(struct perf_callchain_entry *entry,
static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
unsigned long ufp;
......@@ -1822,11 +1822,11 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
ufp = (unsigned long)sf.fp;
}
perf_callchain_store(entry, pc);
} while (entry->nr < sysctl_perf_event_max_stack);
} while (entry->entry->nr < entry->max_stack);
}
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
u64 saved_fault_address = current_thread_info()->fault_address;
u8 saved_fault_code = get_thread_fault_code();
......
......@@ -941,7 +941,7 @@ arch_initcall(init_hw_perf_events);
/*
* Tile specific backtracing code for perf_events.
*/
static inline void perf_callchain(struct perf_callchain_entry *entry,
static inline void perf_callchain(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
struct KBacktraceIterator kbt;
......@@ -992,13 +992,13 @@ static inline void perf_callchain(struct perf_callchain_entry *entry,
}
}
void perf_callchain_user(struct perf_callchain_entry *entry,
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
perf_callchain(entry, regs);
}
void perf_callchain_kernel(struct perf_callchain_entry *entry,
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
perf_callchain(entry, regs);
......
......@@ -2202,7 +2202,7 @@ static int backtrace_stack(void *data, char *name)
static int backtrace_address(void *data, unsigned long addr, int reliable)
{
struct perf_callchain_entry *entry = data;
struct perf_callchain_entry_ctx *entry = data;
return perf_callchain_store(entry, addr);
}
......@@ -2214,7 +2214,7 @@ static const struct stacktrace_ops backtrace_ops = {
};
void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* TODO: We don't support guest os callchain now */
......@@ -2268,7 +2268,7 @@ static unsigned long get_segment_base(unsigned int segment)
#include <asm/compat.h>
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
{
/* 32-bit process in 64-bit kernel. */
unsigned long ss_base, cs_base;
......@@ -2283,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
fp = compat_ptr(ss_base + regs->bp);
pagefault_disable();
while (entry->nr < sysctl_perf_event_max_stack) {
while (entry->entry->nr < entry->max_stack) {
unsigned long bytes;
frame.next_frame = 0;
frame.return_address = 0;
......@@ -2309,14 +2309,14 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
}
#else
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
{
return 0;
}
#endif
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct stack_frame frame;
const void __user *fp;
......@@ -2343,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
return;
pagefault_disable();
while (entry->nr < sysctl_perf_event_max_stack) {
while (entry->entry->nr < entry->max_stack) {
unsigned long bytes;
frame.next_frame = NULL;
frame.return_address = 0;
......
......@@ -323,23 +323,23 @@ static void xtensa_pmu_read(struct perf_event *event)
static int callchain_trace(struct stackframe *frame, void *data)
{
struct perf_callchain_entry *entry = data;
struct perf_callchain_entry_ctx *entry = data;
perf_callchain_store(entry, frame->pc);
return 0;
}
void perf_callchain_kernel(struct perf_callchain_entry *entry,
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
xtensa_backtrace_kernel(regs, sysctl_perf_event_max_stack,
xtensa_backtrace_kernel(regs, entry->max_stack,
callchain_trace, NULL, entry);
}
void perf_callchain_user(struct perf_callchain_entry *entry,
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
xtensa_backtrace_user(regs, sysctl_perf_event_max_stack,
xtensa_backtrace_user(regs, entry->max_stack,
callchain_trace, entry);
}
......
......@@ -61,6 +61,11 @@ struct perf_callchain_entry {
__u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
};
struct perf_callchain_entry_ctx {
struct perf_callchain_entry *entry;
u32 max_stack;
};
struct perf_raw_record {
u32 size;
void *data;
......@@ -1063,19 +1068,20 @@ extern void perf_event_fork(struct task_struct *tsk);
/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
bool crosstask, bool add_mark);
u32 max_stack, bool crosstask, bool add_mark);
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
extern int sysctl_perf_event_max_stack;
static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
if (entry->nr < sysctl_perf_event_max_stack) {
struct perf_callchain_entry *entry = ctx->entry;
if (entry->nr < ctx->max_stack) {
entry->ip[entry->nr++] = ip;
return 0;
} else {
......
......@@ -136,7 +136,8 @@ static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5)
BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
return -EINVAL;
trace = get_perf_callchain(regs, init_nr, kernel, user, false, false);
trace = get_perf_callchain(regs, init_nr, kernel, user,
sysctl_perf_event_max_stack, false, false);
if (unlikely(!trace))
/* couldn't fetch the stack trace */
......
......@@ -32,12 +32,12 @@ static DEFINE_MUTEX(callchain_mutex);
static struct callchain_cpus_entries *callchain_cpus_entries;
__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
__weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
__weak void perf_callchain_user(struct perf_callchain_entry *entry,
__weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
}
......@@ -176,14 +176,15 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
if (!kernel && !user)
return NULL;
return get_perf_callchain(regs, 0, kernel, user, crosstask, true);
return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true);
}
struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
bool crosstask, bool add_mark)
u32 max_stack, bool crosstask, bool add_mark)
{
struct perf_callchain_entry *entry;
struct perf_callchain_entry_ctx ctx;
int rctx;
entry = get_callchain_entry(&rctx);
......@@ -193,12 +194,15 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
if (!entry)
goto exit_put;
ctx.entry = entry;
ctx.max_stack = max_stack;
entry->nr = init_nr;
if (kernel && !user_mode(regs)) {
if (add_mark)
perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
perf_callchain_kernel(entry, regs);
perf_callchain_store(&ctx, PERF_CONTEXT_KERNEL);
perf_callchain_kernel(&ctx, regs);
}
if (user) {
......@@ -214,8 +218,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
goto exit_put;
if (add_mark)
perf_callchain_store(entry, PERF_CONTEXT_USER);
perf_callchain_user(entry, regs);
perf_callchain_store(&ctx, PERF_CONTEXT_USER);
perf_callchain_user(&ctx, regs);
}
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment