Re: [PATCH v7 2/2] arch/riscv: Enable kprobes when CONFIG_MODULES=n

[Christophe Leroy]

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/20220608000014.3054333-1-jarkko@xxxxxxxxxxx/ # continuation
> Signed-off-by: Jarkko Sakkinen <jarkko@xxxxxxxxxx>
> ---
> 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);
> +}