| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20240525023742.786834257@goodmis.org>
Date: Fri, 24 May 2024 22:37:02 -0400
From: Steven Rostedt <rostedt@...dmis.org>
To: linux-kernel@...r.kernel.org,
linux-trace-kernel@...r.kernel.org
Cc: Masami Hiramatsu <mhiramat@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Alexei Starovoitov <alexei.starovoitov@...il.com>,
Florent Revest <revest@...omium.org>,
Martin KaFai Lau <martin.lau@...ux.dev>,
bpf <bpf@...r.kernel.org>,
Sven Schnelle <svens@...ux.ibm.com>,
Alexei Starovoitov <ast@...nel.org>,
Jiri Olsa <jolsa@...nel.org>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Alan Maguire <alan.maguire@...cle.com>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Guo Ren <guoren@...nel.org>
Subject: [PATCH 10/20] function_graph: Have the instances use their own ftrace_ops for
filtering
From: "Steven Rostedt (VMware)" <rostedt@...dmis.org>
Allow for instances to have their own ftrace_ops part of the fgraph_ops
that makes the funtion_graph tracer filter on the set_ftrace_filter file
of the instance and not the top instance.
Note that this also requires to update ftrace_graph_func() to call new
function_graph_enter_ops() instead of function_graph_enter() so that
it avoid pushing on shadow stack multiple times on the same function.
Co-developed with Masami Hiramatsu:
Link: https://lore.kernel.org/linux-trace-kernel/171509102088.162236.15758883237657317789.stgit@devnote2
Signed-off-by: Steven Rostedt (VMware) <rostedt@...dmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@...nel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@...dmis.org>
---
arch/arm64/kernel/ftrace.c | 21 ++++-
arch/loongarch/kernel/ftrace_dyn.c | 15 ++-
arch/powerpc/kernel/trace/ftrace.c | 3 +-
arch/riscv/kernel/ftrace.c | 15 ++-
arch/x86/kernel/ftrace.c | 19 +++-
include/linux/ftrace.h | 6 ++
kernel/trace/fgraph.c | 131 ++++++++++++++++++++-------
kernel/trace/ftrace.c | 4 +-
kernel/trace/trace.h | 16 ++--
kernel/trace/trace_functions.c | 2 +-
kernel/trace/trace_functions_graph.c | 8 +-
11 files changed, 190 insertions(+), 50 deletions(-)
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index a650f5e11fc5..b96740829798 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -481,7 +481,26 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
- prepare_ftrace_return(ip, &fregs->lr, fregs->fp);
+ struct fgraph_ops *gops = container_of(op, struct fgraph_ops, ops);
+ unsigned long frame_pointer = fregs->fp;
+ unsigned long *parent = &fregs->lr;
+ int bit;
+
+ if (unlikely(ftrace_graph_is_dead()))
+ return;
+
+ if (unlikely(atomic_read(¤t->tracing_graph_pause)))
+ return;
+
+ bit = ftrace_test_recursion_trylock(ip, *parent);
+ if (bit < 0)
+ return;
+
+ if (!function_graph_enter_ops(*parent, ip, frame_pointer,
+ (void *)frame_pointer, gops))
+ *parent = (unsigned long)&return_to_handler;
+
+ ftrace_test_recursion_unlock(bit);
}
#else
/*
diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c
index bff058317062..77acb69ad153 100644
--- a/arch/loongarch/kernel/ftrace_dyn.c
+++ b/arch/loongarch/kernel/ftrace_dyn.c
@@ -241,10 +241,21 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent)
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
+ struct fgraph_ops *gops = container_of(op, struct fgraph_ops, ops);
+ unsigned long return_hooker = (unsigned long)&return_to_handler;
struct pt_regs *regs = &fregs->regs;
- unsigned long *parent = (unsigned long *)®s->regs[1];
+ unsigned long *parent;
+ unsigned long old;
+
+ parent = (unsigned long *)®s->regs[1];
- prepare_ftrace_return(ip, (unsigned long *)parent);
+ if (unlikely(atomic_read(¤t->tracing_graph_pause)))
+ return;
+
+ old = *parent;
+
+ if (!function_graph_enter_ops(old, ip, 0, parent, gops))
+ *parent = return_hooker;
}
#else
static int ftrace_modify_graph_caller(bool enable)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index d8d6b4fd9a14..4a9294821c0d 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -421,6 +421,7 @@ int __init ftrace_dyn_arch_init(void)
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
+ struct fgraph_ops *gops = container_of(op, struct fgraph_ops, ops);
unsigned long sp = fregs->regs.gpr[1];
int bit;
@@ -434,7 +435,7 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
if (bit < 0)
goto out;
- if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp))
+ if (!function_graph_enter_ops(parent_ip, ip, 0, (unsigned long *)sp, gops))
parent_ip = ppc_function_entry(return_to_handler);
ftrace_test_recursion_unlock(bit);
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 4f4987a6d83d..7bcb5f321523 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -218,10 +218,23 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
+ struct fgraph_ops *gops = container_of(op, struct fgraph_ops, ops);
+ unsigned long return_hooker = (unsigned long)&return_to_handler;
struct pt_regs *regs = arch_ftrace_get_regs(fregs);
unsigned long *parent = (unsigned long *)®s->ra;
+ unsigned long old;
+
+ if (unlikely(atomic_read(¤t->tracing_graph_pause)))
+ return;
+
+ /*
+ * We don't suffer access faults, so no extra fault-recovery assembly
+ * is needed here.
+ */
+ old = *parent;
- prepare_ftrace_return(parent, ip, frame_pointer(regs));
+ if (!function_graph_enter_ops(old, ip, frame_pointer(regs), parent, gops))
+ *parent = return_hooker;
}
#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
extern void ftrace_graph_call(void);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8da0e66ca22d..998558cb8f15 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -648,9 +648,24 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
struct pt_regs *regs = &fregs->regs;
- unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs);
+ unsigned long *parent = (unsigned long *)kernel_stack_pointer(regs);
+ struct fgraph_ops *gops = container_of(op, struct fgraph_ops, ops);
+ int bit;
+
+ if (unlikely(ftrace_graph_is_dead()))
+ return;
+
+ if (unlikely(atomic_read(¤t->tracing_graph_pause)))
+ return;
- prepare_ftrace_return(ip, (unsigned long *)stack, 0);
+ bit = ftrace_test_recursion_trylock(ip, *parent);
+ if (bit < 0)
+ return;
+
+ if (!function_graph_enter_ops(*parent, ip, 0, parent, gops))
+ *parent = (unsigned long)&return_to_handler;
+
+ ftrace_test_recursion_unlock(bit);
}
#endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 942a1f767280..e5b41683ffb9 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1041,6 +1041,7 @@ extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, struct fgraph
struct fgraph_ops {
trace_func_graph_ent_t entryfunc;
trace_func_graph_ret_t retfunc;
+ struct ftrace_ops ops; /* for the hash lists */
void *private;
int idx;
};
@@ -1076,6 +1077,11 @@ extern int
function_graph_enter(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp);
+extern int
+function_graph_enter_ops(unsigned long ret, unsigned long func,
+ unsigned long frame_pointer, unsigned long *retp,
+ struct fgraph_ops *gops);
+
struct ftrace_ret_stack *
ftrace_graph_get_ret_stack(struct task_struct *task, int skip);
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 54ed2ed2036b..67fa7fbf6aac 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -18,13 +18,6 @@
#include "ftrace_internal.h"
#include "trace.h"
-#ifdef CONFIG_DYNAMIC_FTRACE
-#define ASSIGN_OPS_HASH(opsname, val) \
- .func_hash = val, \
- .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock),
-#else
-#define ASSIGN_OPS_HASH(opsname, val)
-#endif
/*
* FGRAPH_FRAME_SIZE: Size in bytes of the meta data on the shadow stack
@@ -155,6 +148,13 @@ get_bitmap_bits(struct task_struct *t, int offset)
return (t->ret_stack[offset] >> FGRAPH_INDEX_SHIFT) & FGRAPH_INDEX_MASK;
}
+/* For BITMAP type: set the bits in the bitmap bitmask at @offset on ret_stack */
+static inline void
+set_bitmap_bits(struct task_struct *t, int offset, unsigned long bitmap)
+{
+ t->ret_stack[offset] |= (bitmap << FGRAPH_INDEX_SHIFT);
+}
+
/* Write the bitmap to the ret_stack at @offset (does index, offset and bitmask) */
static inline void
set_bitmap(struct task_struct *t, int offset, unsigned long bitmap)
@@ -381,7 +381,8 @@ int function_graph_enter(unsigned long ret, unsigned long func,
if (gops == &fgraph_stub)
continue;
- if (gops->entryfunc(&trace, gops))
+ if (ftrace_ops_test(&gops->ops, func, NULL) &&
+ gops->entryfunc(&trace, gops))
bitmap |= BIT(i);
}
@@ -402,6 +403,46 @@ int function_graph_enter(unsigned long ret, unsigned long func,
return -EBUSY;
}
+/* This is called from ftrace_graph_func() via ftrace */
+int function_graph_enter_ops(unsigned long ret, unsigned long func,
+ unsigned long frame_pointer, unsigned long *retp,
+ struct fgraph_ops *gops)
+{
+ struct ftrace_graph_ent trace;
+ int offset;
+ int type;
+
+ /* Check whether the fgraph_ops is unregistered. */
+ if (unlikely(fgraph_array[gops->idx] == &fgraph_stub))
+ return -ENODEV;
+
+ /* Use start for the distance to ret_stack (skipping over reserve) */
+ offset = ftrace_push_return_trace(ret, func, frame_pointer, retp, gops->idx);
+ if (offset < 0)
+ return offset;
+ type = get_fgraph_type(current, offset);
+
+ /* This is the first ret_stack for this fentry */
+ if (type == FGRAPH_TYPE_RESERVED)
+ ++current->curr_ret_depth;
+
+ trace.func = func;
+ trace.depth = current->curr_ret_depth;
+ if (gops->entryfunc(&trace, gops)) {
+ if (type == FGRAPH_TYPE_RESERVED)
+ set_bitmap(current, offset, BIT(gops->idx));
+ else
+ set_bitmap_bits(current, offset, BIT(gops->idx));
+ return 0;
+ }
+
+ if (type == FGRAPH_TYPE_RESERVED) {
+ current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1;
+ current->curr_ret_depth--;
+ }
+ return -EBUSY;
+}
+
/* Retrieve a function return address to the trace stack on thread info.*/
static struct ftrace_ret_stack *
ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
@@ -662,17 +703,25 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
}
#endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
-static struct ftrace_ops graph_ops = {
- .func = ftrace_graph_func,
- .flags = FTRACE_OPS_FL_INITIALIZED |
- FTRACE_OPS_FL_PID |
- FTRACE_OPS_GRAPH_STUB,
+void fgraph_init_ops(struct ftrace_ops *dst_ops,
+ struct ftrace_ops *src_ops)
+{
+ dst_ops->func = ftrace_graph_func;
+ dst_ops->flags = FTRACE_OPS_FL_PID | FTRACE_OPS_GRAPH_STUB;
+
#ifdef FTRACE_GRAPH_TRAMP_ADDR
- .trampoline = FTRACE_GRAPH_TRAMP_ADDR,
+ dst_ops->trampoline = FTRACE_GRAPH_TRAMP_ADDR;
/* trampoline_size is only needed for dynamically allocated tramps */
#endif
- ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash)
-};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ if (src_ops) {
+ dst_ops->func_hash = &src_ops->local_hash;
+ mutex_init(&dst_ops->local_hash.regex_lock);
+ dst_ops->flags |= FTRACE_OPS_FL_INITIALIZED;
+ }
+#endif
+}
void ftrace_graph_sleep_time_control(bool enable)
{
@@ -876,11 +925,20 @@ static int start_graph_tracing(void)
int register_ftrace_graph(struct fgraph_ops *gops)
{
+ int command = 0;
int ret = 0;
int i;
mutex_lock(&ftrace_lock);
+ if (!gops->ops.func) {
+ gops->ops.flags |= FTRACE_OPS_GRAPH_STUB;
+ gops->ops.func = ftrace_graph_func;
+#ifdef FTRACE_GRAPH_TRAMP_ADDR
+ gops->ops.trampoline = FTRACE_GRAPH_TRAMP_ADDR;
+#endif
+ }
+
if (!fgraph_array[0]) {
/* The array must always have real data on it */
for (i = 0; i < FGRAPH_ARRAY_SIZE; i++)
@@ -893,7 +951,7 @@ int register_ftrace_graph(struct fgraph_ops *gops)
break;
}
if (i >= FGRAPH_ARRAY_SIZE) {
- ret = -EBUSY;
+ ret = -ENOSPC;
goto out;
}
@@ -907,18 +965,22 @@ int register_ftrace_graph(struct fgraph_ops *gops)
if (ftrace_graph_active == 1) {
register_pm_notifier(&ftrace_suspend_notifier);
ret = start_graph_tracing();
- if (ret) {
- ftrace_graph_active--;
- goto out;
- }
+ if (ret)
+ goto error;
/*
* Some archs just test to see if these are not
* the default function
*/
ftrace_graph_return = return_run;
ftrace_graph_entry = entry_run;
+ command = FTRACE_START_FUNC_RET;
+ }
- ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET);
+ ret = ftrace_startup(&gops->ops, command);
+error:
+ if (ret) {
+ fgraph_array[i] = &fgraph_stub;
+ ftrace_graph_active--;
}
out:
mutex_unlock(&ftrace_lock);
@@ -927,6 +989,7 @@ int register_ftrace_graph(struct fgraph_ops *gops)
void unregister_ftrace_graph(struct fgraph_ops *gops)
{
+ int command = 0;
int i;
mutex_lock(&ftrace_lock);
@@ -934,25 +997,29 @@ void unregister_ftrace_graph(struct fgraph_ops *gops)
if (unlikely(!ftrace_graph_active))
goto out;
- for (i = 0; i < fgraph_array_cnt; i++)
- if (gops == fgraph_array[i])
- break;
- if (i >= fgraph_array_cnt)
+ if (unlikely(gops->idx < 0 || gops->idx >= fgraph_array_cnt))
goto out;
- fgraph_array[i] = &fgraph_stub;
- if (i + 1 == fgraph_array_cnt) {
- for (; i >= 0; i--)
- if (fgraph_array[i] != &fgraph_stub)
- break;
+ WARN_ON_ONCE(fgraph_array[gops->idx] != gops);
+
+ fgraph_array[gops->idx] = &fgraph_stub;
+ if (gops->idx + 1 == fgraph_array_cnt) {
+ i = gops->idx;
+ while (i >= 0 && fgraph_array[i] == &fgraph_stub)
+ i--;
fgraph_array_cnt = i + 1;
}
ftrace_graph_active--;
+
+ if (!ftrace_graph_active)
+ command = FTRACE_STOP_FUNC_RET;
+
+ ftrace_shutdown(&gops->ops, command);
+
if (!ftrace_graph_active) {
ftrace_graph_return = ftrace_stub_graph;
ftrace_graph_entry = ftrace_graph_entry_stub;
- ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET);
unregister_pm_notifier(&ftrace_suspend_notifier);
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b85f00b0ffe7..fa6a686726db 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3016,6 +3016,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
if (unlikely(ftrace_disabled))
return -ENODEV;
+ ftrace_ops_init(ops);
+
ret = __register_ftrace_function(ops);
if (ret)
return ret;
@@ -7327,7 +7329,7 @@ __init void ftrace_init_global_array_ops(struct trace_array *tr)
tr->ops = &global_ops;
tr->ops->private = tr;
ftrace_init_trace_array(tr);
- init_array_fgraph_ops(tr);
+ init_array_fgraph_ops(tr, tr->ops);
}
void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index a5070f9b977b..ced61eacf40f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -894,8 +894,8 @@ extern int __trace_graph_entry(struct trace_array *tr,
extern void __trace_graph_return(struct trace_array *tr,
struct ftrace_graph_ret *trace,
unsigned int trace_ctx);
-extern void init_array_fgraph_ops(struct trace_array *tr);
-extern int allocate_fgraph_ops(struct trace_array *tr);
+extern void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops);
+extern int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops);
extern void free_fgraph_ops(struct trace_array *tr);
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -978,6 +978,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr)
preempt_enable_notrace();
return ret;
}
+
#else
static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
{
@@ -1003,18 +1004,19 @@ static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace)
(fgraph_max_depth && trace->depth >= fgraph_max_depth);
}
+void fgraph_init_ops(struct ftrace_ops *dst_ops,
+ struct ftrace_ops *src_ops);
+
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
static inline enum print_line_t
print_graph_function_flags(struct trace_iterator *iter, u32 flags)
{
return TRACE_TYPE_UNHANDLED;
}
-static inline void init_array_fgraph_ops(struct trace_array *tr) { }
-static inline int allocate_fgraph_ops(struct trace_array *tr)
-{
- return 0;
-}
static inline void free_fgraph_ops(struct trace_array *tr) { }
+/* ftrace_ops may not be defined */
+#define init_array_fgraph_ops(tr, ops) do { } while (0)
+#define allocate_fgraph_ops(tr, ops) ({ 0; })
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
extern struct list_head ftrace_pids;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8e8da0d0ee52..13bf2415245d 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -91,7 +91,7 @@ int ftrace_create_function_files(struct trace_array *tr,
if (!tr->ops)
return -EINVAL;
- ret = allocate_fgraph_ops(tr);
+ ret = allocate_fgraph_ops(tr, tr->ops);
if (ret) {
kfree(tr->ops);
return ret;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9ccc904a7703..7f30652f0e97 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -288,7 +288,7 @@ static struct fgraph_ops funcgraph_ops = {
.retfunc = &trace_graph_return,
};
-int allocate_fgraph_ops(struct trace_array *tr)
+int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops)
{
struct fgraph_ops *gops;
@@ -301,6 +301,9 @@ int allocate_fgraph_ops(struct trace_array *tr)
tr->gops = gops;
gops->private = tr;
+
+ fgraph_init_ops(&gops->ops, ops);
+
return 0;
}
@@ -309,10 +312,11 @@ void free_fgraph_ops(struct trace_array *tr)
kfree(tr->gops);
}
-__init void init_array_fgraph_ops(struct trace_array *tr)
+__init void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops)
{
tr->gops = &funcgraph_ops;
funcgraph_ops.private = tr;
+ fgraph_init_ops(&tr->gops->ops, ops);
}
static int graph_trace_init(struct trace_array *tr)
--
2.43.0
Powered by blists - more mailing lists