Tracing with kprobes while running a monolithic kernel is currently
impossible because CONFIG_KPROBES depends on CONFIG_MODULES because it uses
the kernel module allocator.
Introduce alloc_textmem() and free_textmem() for allocating executable
memory. If an arch implements these functions, it can mark this up with
the HAVE_ALLOC_EXECMEM kconfig flag.
At first this feature will be used for enabling kprobes without
modules support for arch/riscv.
Link: https://lore.kernel.org/all/[email protected]/
Suggested-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Jarkko Sakkinen <[email protected]>
---
v3:
- A new patch added.
- For IS_DEFINED() I need advice as I could not really find that many
locations where it would be applicable.
---
arch/Kconfig | 16 +++++++++++++++-
include/linux/execmem.h | 13 +++++++++++++
kernel/kprobes.c | 17 ++++++++++++++---
kernel/trace/trace_kprobe.c | 18 ++++++++++++++++--
4 files changed, 58 insertions(+), 6 deletions(-)
create mode 100644 include/linux/execmem.h
diff --git a/arch/Kconfig b/arch/Kconfig
index a5af0edd3eb8..33ba68b7168f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -52,8 +52,8 @@ config GENERIC_ENTRY
config KPROBES
bool "Kprobes"
- depends on MODULES
depends on HAVE_KPROBES
+ select ALLOC_EXECMEM
select KALLSYMS
select TASKS_RCU if PREEMPTION
help
@@ -215,6 +215,20 @@ config HAVE_OPTPROBES
config HAVE_KPROBES_ON_FTRACE
bool
+config HAVE_ALLOC_EXECMEM
+ bool
+ help
+ Architectures that select this option are capable of allocating executable
+ memory, which can be used by subsystems but is not dependent of any of its
+ clients.
+
+config ALLOC_EXECMEM
+ bool "Executable (trampoline) memory allocation"
+ depends on MODULES || HAVE_ALLOC_EXECMEM
+ help
+ Select this for executable (trampoline) memory. Can be enabled when either
+ module allocator or arch-specific allocator is available.
+
config ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
bool
help
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
new file mode 100644
index 000000000000..ae2ff151523a
--- /dev/null
+++ b/include/linux/execmem.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_EXECMEM_H
+#define _LINUX_EXECMEM_H
+
+#ifdef CONFIG_HAVE_ALLOC_EXECMEM
+void *alloc_execmem(unsigned long size, gfp_t gfp);
+void free_execmem(void *region);
+#else
+#define alloc_execmem(size, gfp) module_alloc(size)
+#define free_execmem(region) module_memfree(region)
+#endif
+
+#endif /* _LINUX_EXECMEM_H */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9d9095e81792..a1a547723c3c 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -44,6 +44,7 @@
#include <asm/cacheflush.h>
#include <asm/errno.h>
#include <linux/uaccess.h>
+#include <linux/execmem.h>
#define KPROBE_HASH_BITS 6
#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
@@ -113,17 +114,17 @@ enum kprobe_slot_state {
void __weak *alloc_insn_page(void)
{
/*
- * Use module_alloc() so this page is within +/- 2GB of where the
+ * Use alloc_execmem() so this page is within +/- 2GB of where the
* kernel image and loaded module images reside. This is required
* for most of the architectures.
* (e.g. x86-64 needs this to handle the %rip-relative fixups.)
*/
- return module_alloc(PAGE_SIZE);
+ return alloc_execmem(PAGE_SIZE);
}
static void free_insn_page(void *page)
{
- module_memfree(page);
+ free_execmem(page);
}
struct kprobe_insn_cache kprobe_insn_slots = {
@@ -1580,6 +1581,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
goto out;
}
+#ifdef CONFIG_MODULES
/* Check if 'p' is probing a module. */
*probed_mod = __module_text_address((unsigned long) p->addr);
if (*probed_mod) {
@@ -1603,6 +1605,8 @@ static int check_kprobe_address_safe(struct kprobe *p,
ret = -ENOENT;
}
}
+#endif
+
out:
preempt_enable();
jump_label_unlock();
@@ -2482,6 +2486,7 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
return 0;
}
+#ifdef CONFIG_MODULES
/* Remove all symbols in given area from kprobe blacklist */
static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
{
@@ -2499,6 +2504,7 @@ static void kprobe_remove_ksym_blacklist(unsigned long entry)
{
kprobe_remove_area_blacklist(entry, entry + 1);
}
+#endif /* CONFIG_MODULES */
int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
char *type, char *sym)
@@ -2564,6 +2570,7 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
return ret ? : arch_populate_kprobe_blacklist();
}
+#ifdef CONFIG_MODULES
static void add_module_kprobe_blacklist(struct module *mod)
{
unsigned long start, end;
@@ -2665,6 +2672,7 @@ static struct notifier_block kprobe_module_nb = {
.notifier_call = kprobes_module_callback,
.priority = 0
};
+#endif /* CONFIG_MODULES */
void kprobe_free_init_mem(void)
{
@@ -2724,8 +2732,11 @@ static int __init init_kprobes(void)
err = arch_init_kprobes();
if (!err)
err = register_die_notifier(&kprobe_exceptions_nb);
+
+#ifdef CONFIG_MODULES
if (!err)
err = register_module_notifier(&kprobe_module_nb);
+#endif
kprobes_initialized = (err == 0);
kprobe_sysctls_init();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c4c6e0e0068b..f8fbd5e76dda 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -111,6 +111,7 @@ static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk,
return strncmp(module_name(mod), name, len) == 0 && name[len] == ':';
}
+#ifdef CONFIG_MODULES
static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
{
char *p;
@@ -129,6 +130,7 @@ static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
return ret;
}
+#endif /* CONFIG_MODULES */
static bool trace_kprobe_is_busy(struct dyn_event *ev)
{
@@ -608,7 +610,11 @@ static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to)
/* Register k*probe */
ret = __register_trace_kprobe(tk);
- if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
+#ifdef CONFIG_MODULES
+ if (ret == -ENOENT && trace_kprobe_module_exist(tk))
+ ret = 0;
+#endif /* CONFIG_MODULES */
+ if (ret == -ENOENT) {
pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;
}
@@ -655,7 +661,11 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
/* Register k*probe */
ret = __register_trace_kprobe(tk);
- if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
+#ifdef CONFIG_MODULES
+ if (ret == -ENOENT && trace_kprobe_module_exist(tk))
+ ret = 0;
+#endif /* CONFIG_MODULES */
+ if (ret == -ENOENT) {
pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;
}
@@ -670,6 +680,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
return ret;
}
+#ifdef CONFIG_MODULES
/* Module notifier call back, checking event on the module */
static int trace_kprobe_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
@@ -704,6 +715,7 @@ static struct notifier_block trace_kprobe_module_nb = {
.notifier_call = trace_kprobe_module_callback,
.priority = 1 /* Invoked after kprobe module callback */
};
+#endif /* CONFIG_MODULES */
static int count_symbols(void *data, unsigned long unused)
{
@@ -1897,8 +1909,10 @@ static __init int init_kprobe_trace_early(void)
if (ret)
return ret;
+#ifdef CONFIG_MODULES
if (register_module_notifier(&trace_kprobe_module_nb))
return -EINVAL;
+#endif /* CONFIG_MODULES */
return 0;
}
--
2.44.0
Tacing with kprobes while running a monolithic kernel is currently
impossible due the kernel module allocator dependency.
Address the issue by implementing textmem API for RISC-V.
Link: https://www.sochub.fi # for power on testing new SoC's with a minimal stack
Link: https://lore.kernel.org/all/[email protected]/ # continuation
Signed-off-by: Jarkko Sakkinen <[email protected]>
---
v3:
- Architecture independent parts have been split to separate patches.
- Do not change arch/riscv/kernel/module.c as it is out of scope for
this patch set now.
v2:
- Better late than never right? :-)
- Focus only to RISC-V for now to make the patch more digestable. This
is the arch where I use the patch on a daily basis to help with QA.
- Introduce HAVE_KPROBES_ALLOC flag to help with more gradual migration.
---
arch/riscv/Kconfig | 1 +
arch/riscv/kernel/Makefile | 3 +++
arch/riscv/kernel/execmem.c | 22 ++++++++++++++++++++++
kernel/kprobes.c | 2 +-
4 files changed, 27 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/kernel/execmem.c
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index e3142ce531a0..499512fb17ff 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -132,6 +132,7 @@ config RISCV
select HAVE_KPROBES if !XIP_KERNEL
select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL
select HAVE_KRETPROBES if !XIP_KERNEL
+ select HAVE_ALLOC_EXECMEM if !XIP_KERNEL
# https://github.com/ClangBuiltLinux/linux/issues/1881
select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if !LD_IS_LLD
select HAVE_MOVE_PMD
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 604d6bf7e476..337797f10d3e 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -73,6 +73,9 @@ obj-$(CONFIG_SMP) += cpu_ops.o
obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o
obj-$(CONFIG_MODULES) += module.o
+ifeq ($(CONFIG_ALLOC_EXECMEM),y)
+obj-y += execmem.o
+endif
obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o
obj-$(CONFIG_CPU_PM) += suspend_entry.o suspend.o
diff --git a/arch/riscv/kernel/execmem.c b/arch/riscv/kernel/execmem.c
new file mode 100644
index 000000000000..4191251476d0
--- /dev/null
+++ b/arch/riscv/kernel/execmem.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/mm.h>
+#include <linux/moduleloader.h>
+#include <linux/vmalloc.h>
+#include <asm/sections.h>
+
+void *alloc_execmem(unsigned long size, gfp_t /* gfp */)
+{
+ return __vmalloc_node_range(size, 1, MODULES_VADDR,
+ MODULES_END, GFP_KERNEL,
+ PAGE_KERNEL, 0, NUMA_NO_NODE,
+ __builtin_return_address(0));
+}
+
+void free_execmem(void *region)
+{
+ if (in_interrupt())
+ pr_warn("In interrupt context: vmalloc may not work.\n");
+
+ vfree(region);
+}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index a1a547723c3c..87fd8c14a938 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -119,7 +119,7 @@ void __weak *alloc_insn_page(void)
* for most of the architectures.
* (e.g. x86-64 needs this to handle the %rip-relative fixups.)
*/
- return alloc_execmem(PAGE_SIZE);
+ return alloc_execmem(PAGE_SIZE, GFP_KERNEL);
}
static void free_insn_page(void *page)
--
2.44.0
On Mon Mar 25, 2024 at 10:37 PM EET, Jarkko Sakkinen wrote:
> Tacing with kprobes while running a monolithic kernel is currently
> impossible due the kernel module allocator dependency.
>
> Address the issue by implementing textmem API for RISC-V.
>
> Link: https://www.sochub.fi # for power on testing new SoC's with a minimal stack
> Link: https://lore.kernel.org/all/20220608000014.3054333-1-jarkko@profiancom/ # continuation
> Signed-off-by: Jarkko Sakkinen <[email protected]>
I think that for any use case it is best for overall good to realize it
like this. I.e. only create patch sets related to the topic that change
behavior for arch's that are in your heavy use. For me that mean x86
and RISC-V.
That is why I shrinked this from to focus into more narrow scope.
For microarch's more alien to one, it is just too easy to make sloppy
mistakes, which could cause unwanted harm. E.g. it is for best of
arch/sh that someone involved with that microarchitecture does later
on the shenanigans.
BR, Jarkko
On Mon Mar 25, 2024 at 10:37 PM EET, Jarkko Sakkinen wrote:
> - if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
> +#ifdef CONFIG_MODULES
> + if (ret == -ENOENT && trace_kprobe_module_exist(tk))
> + ret = 0;
> +#endif /* CONFIG_MODULES */
For this we could have
#ifndef CONFIG_MODULES
#define trace_kprobe_module_exist(tk) false
#endif
That would clean up at least two locations requiring no changes. Should
I go forward this or not?
BR, Jarkko