diff mbox series

[v7,05/36] function_graph: Convert ret_stack to a series of longs

Message ID 170723210553.502590.11433819353474145840.stgit@devnote2 (mailing list archive)
State Not Applicable
Headers show
Series tracing: fprobe: function_graph: Multi-function graph and fprobe on fgraph | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-13 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-15 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 fail Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 fail Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 fail Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 fail Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17 and -O2 optimization
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 fail Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-32 fail Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18 and -O2 optimization
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-38 fail Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-39 fail Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-40 fail Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / veristat
netdev/series_format fail Series longer than 15 patches (and no cover letter)
netdev/tree_selection success Guessed tree name to be net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 15518 this patch: 15518
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 9 maintainers not CCed: vschneid@redhat.com bsegall@google.com juri.lelli@redhat.com dietmar.eggemann@arm.com mathieu.desnoyers@efficios.com mingo@redhat.com mgorman@suse.de bristot@redhat.com vincent.guittot@linaro.org
netdev/build_clang success Errors and warnings before: 3235 this patch: 3235
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 16662 this patch: 16662
netdev/checkpatch warning CHECK: Macro argument 'c' may be better as '(c)' to avoid precedence issues WARNING: line length of 81 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 4 this patch: 4
netdev/source_inline success Was 0 now: 0

Commit Message

Masami Hiramatsu (Google) Feb. 6, 2024, 3:08 p.m. UTC
From: Steven Rostedt (VMware) <rostedt@goodmis.org>

In order to make it possible to have multiple callbacks registered with the
function_graph tracer, the retstack needs to be converted from an array of
ftrace_ret_stack structures to an array of longs. This will allow to store
the list of callbacks on the stack for the return side of the functions.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 include/linux/sched.h |    2 -
 kernel/trace/fgraph.c |  124 ++++++++++++++++++++++++++++---------------------
 2 files changed, 71 insertions(+), 55 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/sched.h b/include/linux/sched.h
index cdb8ea53c365..1cfabb44dcbb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1393,7 +1393,7 @@  struct task_struct {
 	int				curr_ret_depth;
 
 	/* Stack of return addresses for return function tracing: */
-	struct ftrace_ret_stack		*ret_stack;
+	unsigned long			*ret_stack;
 
 	/* Timestamp for last schedule: */
 	unsigned long long		ftrace_timestamp;
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index c83c005e654e..30edeb6d4aa9 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -25,6 +25,18 @@ 
 #define ASSIGN_OPS_HASH(opsname, val)
 #endif
 
+#define FGRAPH_RET_SIZE sizeof(struct ftrace_ret_stack)
+#define FGRAPH_RET_INDEX (ALIGN(FGRAPH_RET_SIZE, sizeof(long)) / sizeof(long))
+#define SHADOW_STACK_SIZE (PAGE_SIZE)
+#define SHADOW_STACK_INDEX			\
+	(ALIGN(SHADOW_STACK_SIZE, sizeof(long)) / sizeof(long))
+/* Leave on a buffer at the end */
+#define SHADOW_STACK_MAX_INDEX (SHADOW_STACK_INDEX - FGRAPH_RET_INDEX)
+
+#define RET_STACK(t, index) ((struct ftrace_ret_stack *)(&(t)->ret_stack[index]))
+#define RET_STACK_INC(c) ({ c += FGRAPH_RET_INDEX; })
+#define RET_STACK_DEC(c) ({ c -= FGRAPH_RET_INDEX; })
+
 DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
 int ftrace_graph_active;
 
@@ -69,6 +81,7 @@  static int
 ftrace_push_return_trace(unsigned long ret, unsigned long func,
 			 unsigned long frame_pointer, unsigned long *retp)
 {
+	struct ftrace_ret_stack *ret_stack;
 	unsigned long long calltime;
 	int index;
 
@@ -85,23 +98,25 @@  ftrace_push_return_trace(unsigned long ret, unsigned long func,
 	smp_rmb();
 
 	/* The return trace stack is full */
-	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
+	if (current->curr_ret_stack >= SHADOW_STACK_MAX_INDEX) {
 		atomic_inc(&current->trace_overrun);
 		return -EBUSY;
 	}
 
 	calltime = trace_clock_local();
 
-	index = ++current->curr_ret_stack;
+	index = current->curr_ret_stack;
+	RET_STACK_INC(current->curr_ret_stack);
+	ret_stack = RET_STACK(current, index);
 	barrier();
-	current->ret_stack[index].ret = ret;
-	current->ret_stack[index].func = func;
-	current->ret_stack[index].calltime = calltime;
+	ret_stack->ret = ret;
+	ret_stack->func = func;
+	ret_stack->calltime = calltime;
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	current->ret_stack[index].fp = frame_pointer;
+	ret_stack->fp = frame_pointer;
 #endif
 #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
-	current->ret_stack[index].retp = retp;
+	ret_stack->retp = retp;
 #endif
 	return 0;
 }
@@ -148,7 +163,7 @@  int function_graph_enter(unsigned long ret, unsigned long func,
 
 	return 0;
  out_ret:
-	current->curr_ret_stack--;
+	RET_STACK_DEC(current->curr_ret_stack);
  out:
 	current->curr_ret_depth--;
 	return -EBUSY;
@@ -159,11 +174,13 @@  static void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 			unsigned long frame_pointer)
 {
+	struct ftrace_ret_stack *ret_stack;
 	int index;
 
 	index = current->curr_ret_stack;
+	RET_STACK_DEC(index);
 
-	if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
+	if (unlikely(index < 0 || index > SHADOW_STACK_MAX_INDEX)) {
 		ftrace_graph_stop();
 		WARN_ON(1);
 		/* Might as well panic, otherwise we have no where to go */
@@ -171,6 +188,7 @@  ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 		return;
 	}
 
+	ret_stack = RET_STACK(current, index);
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	/*
 	 * The arch may choose to record the frame pointer used
@@ -186,22 +204,22 @@  ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 	 * Note, -mfentry does not use frame pointers, and this test
 	 *  is not needed if CC_USING_FENTRY is set.
 	 */
-	if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
+	if (unlikely(ret_stack->fp != frame_pointer)) {
 		ftrace_graph_stop();
 		WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
 		     "  from func %ps return to %lx\n",
 		     current->ret_stack[index].fp,
 		     frame_pointer,
-		     (void *)current->ret_stack[index].func,
-		     current->ret_stack[index].ret);
+		     (void *)ret_stack->func,
+		     ret_stack->ret);
 		*ret = (unsigned long)panic;
 		return;
 	}
 #endif
 
-	*ret = current->ret_stack[index].ret;
-	trace->func = current->ret_stack[index].func;
-	trace->calltime = current->ret_stack[index].calltime;
+	*ret = ret_stack->ret;
+	trace->func = ret_stack->func;
+	trace->calltime = ret_stack->calltime;
 	trace->overrun = atomic_read(&current->trace_overrun);
 	trace->depth = current->curr_ret_depth--;
 	/*
@@ -262,7 +280,7 @@  static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 	 * curr_ret_stack is after that.
 	 */
 	barrier();
-	current->curr_ret_stack--;
+	RET_STACK_DEC(current->curr_ret_stack);
 
 	if (unlikely(!ret)) {
 		ftrace_graph_stop();
@@ -305,12 +323,13 @@  unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 struct ftrace_ret_stack *
 ftrace_graph_get_ret_stack(struct task_struct *task, int idx)
 {
-	idx = task->curr_ret_stack - idx;
+	int index = task->curr_ret_stack;
 
-	if (idx >= 0 && idx <= task->curr_ret_stack)
-		return &task->ret_stack[idx];
+	index -= FGRAPH_RET_INDEX * (idx + 1);
+	if (index < 0)
+		return NULL;
 
-	return NULL;
+	return RET_STACK(task, index);
 }
 
 /**
@@ -332,18 +351,20 @@  ftrace_graph_get_ret_stack(struct task_struct *task, int idx)
 unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp)
 {
+	struct ftrace_ret_stack *ret_stack;
 	int index = task->curr_ret_stack;
 	int i;
 
 	if (ret != (unsigned long)dereference_kernel_function_descriptor(return_to_handler))
 		return ret;
 
-	if (index < 0)
-		return ret;
+	RET_STACK_DEC(index);
 
-	for (i = 0; i <= index; i++)
-		if (task->ret_stack[i].retp == retp)
-			return task->ret_stack[i].ret;
+	for (i = index; i >= 0; RET_STACK_DEC(i)) {
+		ret_stack = RET_STACK(task, i);
+		if (ret_stack->retp == retp)
+			return ret_stack->ret;
+	}
 
 	return ret;
 }
@@ -357,14 +378,15 @@  unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 		return ret;
 
 	task_idx = task->curr_ret_stack;
+	RET_STACK_DEC(task_idx);
 
 	if (!task->ret_stack || task_idx < *idx)
 		return ret;
 
 	task_idx -= *idx;
-	(*idx)++;
+	RET_STACK_INC(*idx);
 
-	return task->ret_stack[task_idx].ret;
+	return RET_STACK(task, task_idx);
 }
 #endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
 
@@ -402,7 +424,7 @@  trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
 static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
 
 /* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
-static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
+static int alloc_retstack_tasklist(unsigned long **ret_stack_list)
 {
 	int i;
 	int ret = 0;
@@ -410,10 +432,7 @@  static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 	struct task_struct *g, *t;
 
 	for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
-		ret_stack_list[i] =
-			kmalloc_array(FTRACE_RETFUNC_DEPTH,
-				      sizeof(struct ftrace_ret_stack),
-				      GFP_KERNEL);
+		ret_stack_list[i] = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
 		if (!ret_stack_list[i]) {
 			start = 0;
 			end = i;
@@ -431,9 +450,9 @@  static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 
 		if (t->ret_stack == NULL) {
 			atomic_set(&t->trace_overrun, 0);
-			t->curr_ret_stack = -1;
+			t->curr_ret_stack = 0;
 			t->curr_ret_depth = -1;
-			/* Make sure the tasks see the -1 first: */
+			/* Make sure the tasks see the 0 first: */
 			smp_wmb();
 			t->ret_stack = ret_stack_list[start++];
 		}
@@ -453,6 +472,7 @@  ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 				struct task_struct *next,
 				unsigned int prev_state)
 {
+	struct ftrace_ret_stack *ret_stack;
 	unsigned long long timestamp;
 	int index;
 
@@ -477,8 +497,11 @@  ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 	 */
 	timestamp -= next->ftrace_timestamp;
 
-	for (index = next->curr_ret_stack; index >= 0; index--)
-		next->ret_stack[index].calltime += timestamp;
+	for (index = next->curr_ret_stack - FGRAPH_RET_INDEX; index >= 0; ) {
+		ret_stack = RET_STACK(next, index);
+		ret_stack->calltime += timestamp;
+		index -= FGRAPH_RET_INDEX;
+	}
 }
 
 static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
@@ -521,10 +544,10 @@  void update_function_graph_func(void)
 		ftrace_graph_entry = __ftrace_graph_entry;
 }
 
-static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
+static DEFINE_PER_CPU(unsigned long *, idle_ret_stack);
 
 static void
-graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
+graph_init_task(struct task_struct *t, unsigned long *ret_stack)
 {
 	atomic_set(&t->trace_overrun, 0);
 	t->ftrace_timestamp = 0;
@@ -539,7 +562,7 @@  graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
  */
 void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
 {
-	t->curr_ret_stack = -1;
+	t->curr_ret_stack = 0;
 	t->curr_ret_depth = -1;
 	/*
 	 * The idle task has no parent, it either has its own
@@ -549,14 +572,11 @@  void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
 		WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu));
 
 	if (ftrace_graph_active) {
-		struct ftrace_ret_stack *ret_stack;
+		unsigned long *ret_stack;
 
 		ret_stack = per_cpu(idle_ret_stack, cpu);
 		if (!ret_stack) {
-			ret_stack =
-				kmalloc_array(FTRACE_RETFUNC_DEPTH,
-					      sizeof(struct ftrace_ret_stack),
-					      GFP_KERNEL);
+			ret_stack = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
 			if (!ret_stack)
 				return;
 			per_cpu(idle_ret_stack, cpu) = ret_stack;
@@ -570,15 +590,13 @@  void ftrace_graph_init_task(struct task_struct *t)
 {
 	/* Make sure we do not use the parent ret_stack */
 	t->ret_stack = NULL;
-	t->curr_ret_stack = -1;
+	t->curr_ret_stack = 0;
 	t->curr_ret_depth = -1;
 
 	if (ftrace_graph_active) {
-		struct ftrace_ret_stack *ret_stack;
+		unsigned long *ret_stack;
 
-		ret_stack = kmalloc_array(FTRACE_RETFUNC_DEPTH,
-					  sizeof(struct ftrace_ret_stack),
-					  GFP_KERNEL);
+		ret_stack = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
 		if (!ret_stack)
 			return;
 		graph_init_task(t, ret_stack);
@@ -587,7 +605,7 @@  void ftrace_graph_init_task(struct task_struct *t)
 
 void ftrace_graph_exit_task(struct task_struct *t)
 {
-	struct ftrace_ret_stack	*ret_stack = t->ret_stack;
+	unsigned long *ret_stack = t->ret_stack;
 
 	t->ret_stack = NULL;
 	/* NULL must become visible to IRQs before we free it: */
@@ -599,12 +617,10 @@  void ftrace_graph_exit_task(struct task_struct *t)
 /* Allocate a return stack for each task */
 static int start_graph_tracing(void)
 {
-	struct ftrace_ret_stack **ret_stack_list;
+	unsigned long **ret_stack_list;
 	int ret, cpu;
 
-	ret_stack_list = kmalloc_array(FTRACE_RETSTACK_ALLOC_SIZE,
-				       sizeof(struct ftrace_ret_stack *),
-				       GFP_KERNEL);
+	ret_stack_list = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
 
 	if (!ret_stack_list)
 		return -ENOMEM;