Tracing with kprobes while running a monolithic kernel is currently
impossible because CONFIG_KPROBES depends on CONFIG_MODULES.
Introduce alloc_execmem() and free_execmem() for allocating executable
memory. If an arch implements these functions, it can mark this up with
the HAVE_ALLOC_EXECMEM kconfig flag.
The second new kconfig flag is ALLOC_EXECMEM, which can be selected if
either MODULES is selected or HAVE_ALLOC_EXECMEM is support by the arch. If
HAVE_ALLOC_EXECMEM is not supported by an arch, module_alloc() and
module_memfree() are used as a fallback, thus retaining backwards
compatibility to earlier kernel versions.
This will allow architecture to enable kprobes traces without requiring
to enable module.
The support can be implemented with four easy steps:
1. Implement alloc_execmem().
2. Implement free_execmem().
3. Edit arch/<arch>/Makefile.
4. Set HAVE_ALLOC_EXECMEM in arch/<arch>/Kconfig.
Link: https://lore.kernel.org/all/[email protected]/
Suggested-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Jarkko Sakkinen <[email protected]>
---
v7:
- Use "depends on" for ALLOC_EXECMEM instead of "select"
- Reduced and narrowed CONFIG_MODULES checks further in kprobes.c.
v6:
- Use null pointer for notifiers and register the module notifier only if
IS_ENABLED(CONFIG_MODULES) is set.
- Fixed typo in the commit message and wrote more verbose description
of the feature.
v5:
- alloc_execmem() was missing GFP_KERNEL parameter. The patch set did
compile because 2/2 had the fixup (leaked there when rebasing the
patch set).
v4:
- Squashed a couple of unrequired CONFIG_MODULES checks.
- See https://lore.kernel.org/all/[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 | 17 +++++++++++-
include/linux/execmem.h | 13 +++++++++
kernel/kprobes.c | 53 ++++++++++++++++++++++---------------
kernel/trace/trace_kprobe.c | 15 +++++++++--
4 files changed, 73 insertions(+), 25 deletions(-)
create mode 100644 include/linux/execmem.h
diff --git a/arch/Kconfig b/arch/Kconfig
index a5af0edd3eb8..5e9735f60f3c 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
+ depends on ALLOC_EXECMEM
select KALLSYMS
select TASKS_RCU if PREEMPTION
help
@@ -215,6 +215,21 @@ config HAVE_OPTPROBES
config HAVE_KPROBES_ON_FTRACE
bool
+config HAVE_ALLOC_EXECMEM
+ bool
+ help
+ Architectures that select this option are capable of allocating trampoline
+ executable memory for tracing subsystems, indepedently of the kernel module
+ subsystem.
+
+config ALLOC_EXECMEM
+ bool "Executable (trampoline) memory allocation"
+ default y
+ 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..13bef5de315c 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, GFP_KERNEL);
}
static void free_insn_page(void *page)
{
- module_memfree(page);
+ free_execmem(page);
}
struct kprobe_insn_cache kprobe_insn_slots = {
@@ -1592,6 +1593,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
goto out;
}
+#ifdef CONFIG_MODULES
/*
* If the module freed '.init.text', we couldn't insert
* kprobes in there.
@@ -1602,7 +1604,9 @@ static int check_kprobe_address_safe(struct kprobe *p,
*probed_mod = NULL;
ret = -ENOENT;
}
+#endif /* CONFIG_MODULES */
}
+
out:
preempt_enable();
jump_label_unlock();
@@ -2482,24 +2486,6 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
return 0;
}
-/* Remove all symbols in given area from kprobe blacklist */
-static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
-{
- struct kprobe_blacklist_entry *ent, *n;
-
- list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
- if (ent->start_addr < start || ent->start_addr >= end)
- continue;
- list_del(&ent->list);
- kfree(ent);
- }
-}
-
-static void kprobe_remove_ksym_blacklist(unsigned long entry)
-{
- kprobe_remove_area_blacklist(entry, entry + 1);
-}
-
int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
char *type, char *sym)
{
@@ -2564,6 +2550,25 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
return ret ? : arch_populate_kprobe_blacklist();
}
+#ifdef CONFIG_MODULES
+/* Remove all symbols in given area from kprobe blacklist */
+static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
+{
+ struct kprobe_blacklist_entry *ent, *n;
+
+ list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
+ if (ent->start_addr < start || ent->start_addr >= end)
+ continue;
+ list_del(&ent->list);
+ kfree(ent);
+ }
+}
+
+static void kprobe_remove_ksym_blacklist(unsigned long entry)
+{
+ kprobe_remove_area_blacklist(entry, entry + 1);
+}
+
static void add_module_kprobe_blacklist(struct module *mod)
{
unsigned long start, end;
@@ -2660,6 +2665,9 @@ static int kprobes_module_callback(struct notifier_block *nb,
mutex_unlock(&kprobe_mutex);
return NOTIFY_DONE;
}
+#else
+#define kprobes_module_callback (NULL)
+#endif /* CONFIG_MODULES */
static struct notifier_block kprobe_module_nb = {
.notifier_call = kprobes_module_callback,
@@ -2724,7 +2732,8 @@ static int __init init_kprobes(void)
err = arch_init_kprobes();
if (!err)
err = register_die_notifier(&kprobe_exceptions_nb);
- if (!err)
+
+ if (!err && IS_ENABLED(CONFIG_MODULES))
err = register_module_notifier(&kprobe_module_nb);
kprobes_initialized = (err == 0);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c4c6e0e0068b..13ea0d0994d5 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 +130,9 @@ static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
return ret;
}
+#else
+#define trace_kprobe_module_exist(tk) false /* aka a module never exists */
+#endif /* CONFIG_MODULES */
static bool trace_kprobe_is_busy(struct dyn_event *ev)
{
@@ -670,6 +674,7 @@ 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)
@@ -699,6 +704,9 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
return NOTIFY_DONE;
}
+#else
+#define trace_kprobe_module_callback (NULL)
+#endif /* CONFIG_MODULES */
static struct notifier_block trace_kprobe_module_nb = {
.notifier_call = trace_kprobe_module_callback,
@@ -1897,8 +1905,11 @@ static __init int init_kprobe_trace_early(void)
if (ret)
return ret;
- if (register_module_notifier(&trace_kprobe_module_nb))
- return -EINVAL;
+ if (IS_ENABLED(CONFIG_MODULES)) {
+ ret = register_module_notifier(&trace_kprobe_module_nb);
+ if (ret)
+ return -EINVAL;
+ }
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]>
---
v5-v7:
- No changes.
v4:
- Include linux/execmem.h.
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 ++++++++++++++++++++++
3 files changed, 26 insertions(+)
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..3e52522ead32
--- /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/execmem.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);
+}
--
2.44.0
On Tue, Mar 26, 2024 at 03:46:16PM +0200, 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.
This doesn't compile for nommu:
/build/tmp.3xucsBhqDV/arch/riscv/kernel/execmem.c:10:46: error: 'MODULES_VADDR' undeclared (first use in this function)
/build/tmp.3xucsBhqDV/arch/riscv/kernel/execmem.c:11:37: error: 'MODULES_END' undeclared (first use in this function)
/build/tmp.3xucsBhqDV/arch/riscv/kernel/execmem.c:14:1: error: control reaches end of non-void function [-Werror=return-type]
Clang builds also report:
../arch/riscv/kernel/execmem.c:8:56: warning: omitting the parameter name in a function definition is a C2x extension [-Wc2x-extensions]
>
> 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]>
> ---
> v5-v7:
> - No changes.
> v4:
> - Include linux/execmem.h.
> 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.
Meta comment. I dunno when v1 was sent, but versions can you please
relax with submitting new versions of your patches? There's conversations
ongoing on v5 at the moment, while this is a more recent version. v2
seems to have been sent on the 23rd and there's been 5 versions in the
last day:
https://patchwork.kernel.org/project/linux-riscv/list/?submitter=195059&state=*
Could you please also try and use a cover letter for patchsets, ideally
with a consistent subject? Otherwise I have to manually mark stuff as
superseded.
Thanks,
Conor.
> 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.
On Tue Mar 26, 2024 at 8:42 PM EET, Conor Dooley wrote:
> On Tue, Mar 26, 2024 at 03:46:16PM +0200, 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.
>
> This doesn't compile for nommu:
> /build/tmp.3xucsBhqDV/arch/riscv/kernel/execmem.c:10:46: error: 'MODULES_VADDR' undeclared (first use in this function)
> /build/tmp.3xucsBhqDV/arch/riscv/kernel/execmem.c:11:37: error: 'MODULES_END' undeclared (first use in this function)
> /build/tmp.3xucsBhqDV/arch/riscv/kernel/execmem.c:14:1: error: control reaches end of non-void function [-Werror=return-type]
> Clang builds also report:
> ../arch/riscv/kernel/execmem.c:8:56: warning: omitting the parameter name in a function definition is a C2x extension [-Wc2x-extensions]
>
> >
> > 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]>
> > ---
> > v5-v7:
> > - No changes.
> > v4:
> > - Include linux/execmem.h.
> > 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.
>
> Meta comment. I dunno when v1 was sent, but versions can you please
> relax with submitting new versions of your patches? There's conversations
> ongoing on v5 at the moment, while this is a more recent version. v2
> seems to have been sent on the 23rd and there's been 5 versions in the
> last day:
> https://patchwork.kernel.org/project/linux-riscv/list/?submitter=195059&state=*
>
> Could you please also try and use a cover letter for patchsets, ideally
> with a consistent subject? Otherwise I have to manually mark stuff as
> superseded.
Point taken but the work has been taken over by Mark and relevant
changes are now sucked into that patch set.
> Thanks,
> Conor.
BR, Jarkko
Le 26/03/2024 à 14:46, Jarkko Sakkinen a écrit :
> Tracing with kprobes while running a monolithic kernel is currently
> impossible because CONFIG_KPROBES depends on CONFIG_MODULES.
>
> Introduce alloc_execmem() and free_execmem() for allocating executable
> memory. If an arch implements these functions, it can mark this up with
> the HAVE_ALLOC_EXECMEM kconfig flag.
>
> The second new kconfig flag is ALLOC_EXECMEM, which can be selected if
> either MODULES is selected or HAVE_ALLOC_EXECMEM is support by the arch. If
> HAVE_ALLOC_EXECMEM is not supported by an arch, module_alloc() and
> module_memfree() are used as a fallback, thus retaining backwards
> compatibility to earlier kernel versions.
>
> This will allow architecture to enable kprobes traces without requiring
> to enable module.
>
> The support can be implemented with four easy steps:
>
> 1. Implement alloc_execmem().
> 2. Implement free_execmem().
> 3. Edit arch/<arch>/Makefile.
> 4. Set HAVE_ALLOC_EXECMEM in arch/<arch>/Kconfig.
>
> Link: https://lore.kernel.org/all/[email protected]/
> Suggested-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Jarkko Sakkinen <[email protected]>
> ---
> v7:
> - Use "depends on" for ALLOC_EXECMEM instead of "select"
> - Reduced and narrowed CONFIG_MODULES checks further in kprobes.c.
> v6:
> - Use null pointer for notifiers and register the module notifier only if
> IS_ENABLED(CONFIG_MODULES) is set.
> - Fixed typo in the commit message and wrote more verbose description
> of the feature.
> v5:
> - alloc_execmem() was missing GFP_KERNEL parameter. The patch set did
> compile because 2/2 had the fixup (leaked there when rebasing the
> patch set).
> v4:
> - Squashed a couple of unrequired CONFIG_MODULES checks.
> - See https://lore.kernel.org/all/[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 | 17 +++++++++++-
> include/linux/execmem.h | 13 +++++++++
> kernel/kprobes.c | 53 ++++++++++++++++++++++---------------
> kernel/trace/trace_kprobe.c | 15 +++++++++--
> 4 files changed, 73 insertions(+), 25 deletions(-)
> create mode 100644 include/linux/execmem.h
>
> diff --git a/arch/Kconfig b/arch/Kconfig
> index a5af0edd3eb8..5e9735f60f3c 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
> + depends on ALLOC_EXECMEM
> select KALLSYMS
> select TASKS_RCU if PREEMPTION
> help
> @@ -215,6 +215,21 @@ config HAVE_OPTPROBES
> config HAVE_KPROBES_ON_FTRACE
> bool
>
> +config HAVE_ALLOC_EXECMEM
> + bool
> + help
> + Architectures that select this option are capable of allocating trampoline
> + executable memory for tracing subsystems, indepedently of the kernel module
> + subsystem.
> +
> +config ALLOC_EXECMEM
> + bool "Executable (trampoline) memory allocation"
Why make it user selectable ? Previously I was able to select KPROBES as
soon as MODULES was selected. Now I will have to first select
ALLOC_EXECMEM in addition ? What is the added value of allowing the user
to disable it ?
> + default y
> + 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
> +
It should include moduleloader.h otherwise the user of alloc_execmem()
must include both this header and moduleloader.h to use alloc_execmem()
> +#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)
Then gfp is silently ignored in the case. Is that expected ?
> +#define free_execmem(region) module_memfree(region)
> +#endif
> +
> +#endif /* _LINUX_EXECMEM_H */
> diff --git a/kernel/kprobes.c b/kernel/kprobes.c
> index 9d9095e81792..13bef5de315c 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
This 2G stuff is x86 specific, might be different value on other arches.
Can we remove ?
> * 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, GFP_KERNEL);
> }
>
> static void free_insn_page(void *page)
> {
> - module_memfree(page);
> + free_execmem(page);
> }
>
> struct kprobe_insn_cache kprobe_insn_slots = {
> @@ -1592,6 +1593,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
> goto out;
> }
>
> +#ifdef CONFIG_MODULES
> /*
> * If the module freed '.init.text', we couldn't insert
> * kprobes in there.
> @@ -1602,7 +1604,9 @@ static int check_kprobe_address_safe(struct kprobe *p,
> *probed_mod = NULL;
> ret = -ENOENT;
> }
> +#endif /* CONFIG_MODULES */
> }
> +
> out:
> preempt_enable();
> jump_label_unlock();
> @@ -2482,24 +2486,6 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
> return 0;
> }
>
> -/* Remove all symbols in given area from kprobe blacklist */
> -static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
> -{
> - struct kprobe_blacklist_entry *ent, *n;
> -
> - list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
> - if (ent->start_addr < start || ent->start_addr >= end)
> - continue;
> - list_del(&ent->list);
> - kfree(ent);
> - }
> -}
> -
> -static void kprobe_remove_ksym_blacklist(unsigned long entry)
> -{
> - kprobe_remove_area_blacklist(entry, entry + 1);
> -}
> -
> int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
> char *type, char *sym)
> {
> @@ -2564,6 +2550,25 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
> return ret ? : arch_populate_kprobe_blacklist();
> }
>
> +#ifdef CONFIG_MODULES
> +/* Remove all symbols in given area from kprobe blacklist */
> +static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
> +{
> + struct kprobe_blacklist_entry *ent, *n;
> +
> + list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
> + if (ent->start_addr < start || ent->start_addr >= end)
> + continue;
> + list_del(&ent->list);
> + kfree(ent);
> + }
> +}
> +
> +static void kprobe_remove_ksym_blacklist(unsigned long entry)
> +{
> + kprobe_remove_area_blacklist(entry, entry + 1);
> +}
> +
> static void add_module_kprobe_blacklist(struct module *mod)
> {
> unsigned long start, end;
> @@ -2660,6 +2665,9 @@ static int kprobes_module_callback(struct notifier_block *nb,
> mutex_unlock(&kprobe_mutex);
> return NOTIFY_DONE;
> }
> +#else
> +#define kprobes_module_callback (NULL)
Can you use a static inline instead ? It allows typechecking at build.
> +#endif /* CONFIG_MODULES */
>
> static struct notifier_block kprobe_module_nb = {
> .notifier_call = kprobes_module_callback,
> @@ -2724,7 +2732,8 @@ static int __init init_kprobes(void)
> err = arch_init_kprobes();
> if (!err)
> err = register_die_notifier(&kprobe_exceptions_nb);
> - if (!err)
> +
> + if (!err && IS_ENABLED(CONFIG_MODULES))
> err = register_module_notifier(&kprobe_module_nb);
>
> kprobes_initialized = (err == 0);
> diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
> index c4c6e0e0068b..13ea0d0994d5 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 +130,9 @@ static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
>
> return ret;
> }
> +#else
> +#define trace_kprobe_module_exist(tk) false /* aka a module never exists */
same, can it be a static inline instead ?
> +#endif /* CONFIG_MODULES */
>
> static bool trace_kprobe_is_busy(struct dyn_event *ev)
> {
> @@ -670,6 +674,7 @@ 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)
> @@ -699,6 +704,9 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
>
> return NOTIFY_DONE;
> }
> +#else
> +#define trace_kprobe_module_callback (NULL)
Same
> +#endif /* CONFIG_MODULES */
>
> static struct notifier_block trace_kprobe_module_nb = {
> .notifier_call = trace_kprobe_module_callback,
> @@ -1897,8 +1905,11 @@ static __init int init_kprobe_trace_early(void)
> if (ret)
> return ret;
>
> - if (register_module_notifier(&trace_kprobe_module_nb))
> - return -EINVAL;
> + if (IS_ENABLED(CONFIG_MODULES)) {
> + ret = register_module_notifier(&trace_kprobe_module_nb);
> + if (ret)
> + return -EINVAL;
> + }
No need for that, register_module_notifier() returns 0 when
CONFIG_MODULES is not set.
>
> return 0;
> }
Le 26/03/2024 à 14:46, Jarkko Sakkinen a écrit :
> 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]>
> ---
> v5-v7:
> - No changes.
> v4:
> - Include linux/execmem.h.
> 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 ++++++++++++++++++++++
> 3 files changed, 26 insertions(+)
> 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
Why not just :
obj-$(CONFIG_ALLOC_EXECMEM) += execmem.o
> +endif
> obj-$(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..3e52522ead32
> --- /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/execmem.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,
Why not use gfp argument ?
> + 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");
Do you expect that to happen ? module_memfree() has a WARN_ON() meaning
this should never happen and if it really does it is not just a poor
dmesg warning.
> +
> + vfree(region);
> +}