[PATCH] RISC-V: Add kernel image sections to the resource tree

[Palmer Dabbelt]

On Mon, 12 Oct 2020 07:24:10 PDT (-0700), mick at ics.forth.gr wrote:
> This patch (previously part of my kexec/kdump series) populates
> /proc/iomem with the various sections of the kernel image. We need
> this for kexec-tools to be able to prepare the crashkernel image
> for kdump to work. Since resource tree initialization is not
> related to memory initialization I added the code to kernel/setup.c
> and removed the original code (derived from the arm64 tree) from
> mm/init.c.
>
> Signed-off-by: Nick Kossifidis <mick at ics.forth.gr>
> ---
>  arch/riscv/kernel/setup.c | 160 ++++++++++++++++++++++++++++++++++++++
>  arch/riscv/mm/init.c      |  27 -------
>  2 files changed, 160 insertions(+), 27 deletions(-)
>
> diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> index 2c6dd3293..450f0142f 100644
> --- a/arch/riscv/kernel/setup.c
> +++ b/arch/riscv/kernel/setup.c
> @@ -4,6 +4,8 @@
>   *  Chen Liqin <liqin.chen at sunplusct.com>
>   *  Lennox Wu <lennox.wu at sunplusct.com>
>   * Copyright (C) 2012 Regents of the University of California
> + * Copyright (C) 2020 FORTH-ICS/CARV
> + *  Nick Kossifidis <mick at ics.forth.gr>
>   */
>
>  #include <linux/init.h>
> @@ -48,6 +50,163 @@ atomic_t hart_lottery __section(.sdata);
>  unsigned long boot_cpu_hartid;
>  static DEFINE_PER_CPU(struct cpu, cpu_devices);
>
> +/*
> + * Place kernel memory regions on the resource tree so that
> + * kexec-tools can retrieve them from /proc/iomem. While there
> + * also add "System RAM" regions for compatibility with other
> + * archs, and the rest of the known regions for completeness.
> + */
> +static struct resource code_res = { .name = "Kernel code", };
> +static struct resource data_res = { .name = "Kernel data", };
> +static struct resource rodata_res = { .name = "Kernel rodata", };
> +static struct resource bss_res = { .name = "Kernel bss", };
> +
> +static int __init add_resource(struct resource *parent,
> +				struct resource *res)
> +{
> +	int ret = 0;
> +
> +	ret = insert_resource(parent, res);
> +	if (ret < 0) {
> +		pr_err("Failed to add a %s resource at %llx\n",
> +			res->name, (unsigned long long) res->start);
> +		return ret;
> +	}
> +
> +	return 1;
> +}
> +
> +static int __init add_kernel_resources(struct resource *res)
> +{
> +	int ret = 0;
> +
> +	/*
> +	 * The memory region of the kernel image is continuous and
> +	 * was reserved on setup_bootmem, find it here and register
> +	 * it as a resource, then register the various segments of
> +	 * the image as child nodes
> +	 */
> +	if (!(res->start <= code_res.start && res->end >= data_res.end))
> +		return 0;
> +
> +	res->name = "Kernel image";
> +	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> +
> +	/*
> +	 * We removed a part of this region on setup_bootmem so
> +	 * we need to expand the resource for the bss to fit in.
> +	 */
> +	res->end = bss_res.end;
> +
> +	ret = add_resource(&iomem_resource, res);
> +	if (ret < 0)
> +		return ret;
> +
> +	ret = add_resource(res, &code_res);
> +	if (ret < 0)
> +		return ret;
> +
> +	ret = add_resource(res, &rodata_res);
> +	if (ret < 0)
> +		return ret;
> +
> +	ret = add_resource(res, &data_res);
> +	if (ret < 0)
> +		return ret;
> +
> +	ret = add_resource(res, &bss_res);
> +
> +	return ret;
> +}
> +
> +static void __init init_resources(void)
> +{
> +	struct memblock_region *region = NULL;
> +	struct resource *res = NULL;
> +	int ret = 0;
> +
> +	code_res.start = __pa_symbol(_text);
> +	code_res.end = __pa_symbol(_etext) - 1;
> +	code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> +
> +	rodata_res.start = __pa_symbol(__start_rodata);
> +	rodata_res.end = __pa_symbol(__end_rodata) - 1;
> +	rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> +
> +	data_res.start = __pa_symbol(_data);
> +	data_res.end = __pa_symbol(_edata) - 1;
> +	data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> +
> +	bss_res.start = __pa_symbol(__bss_start);
> +	bss_res.end = __pa_symbol(__bss_stop) - 1;
> +	bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> +
> +	/*
> +	 * Start by adding the reserved regions, if they overlap
> +	 * with /memory regions, insert_resource later on will take
> +	 * care of it.
> +	 */
> +	for_each_memblock(reserved, region) {
> +		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
> +		if (!res)
> +			panic("%s: Failed to allocate %zu bytes\n", __func__,
> +			      sizeof(struct resource));
> +
> +		res->name = "Reserved";
> +		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
> +		res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region));
> +		res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1;
> +
> +		ret = add_kernel_resources(res);
> +		if (ret < 0)
> +			goto error;
> +		else if (ret)
> +			continue;
> +
> +		/*
> +		 * Ignore any other reserved regions within
> +		 * system memory.
> +		 */
> +		if (memblock_is_memory(res->start))
> +			continue;
> +
> +		ret = add_resource(&iomem_resource, res);
> +		if (ret < 0)
> +			goto error;
> +	}
> +
> +	/* Add /memory regions to the resource tree */
> +	for_each_memblock(memory, region) {
> +		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
> +		if (!res)
> +			panic("%s: Failed to allocate %zu bytes\n", __func__,
> +			      sizeof(struct resource));
> +
> +		if (unlikely(memblock_is_nomap(region))) {
> +			res->name = "Reserved";
> +			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
> +		} else {
> +			res->name = "System RAM";
> +			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> +		}
> +
> +		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
> +		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
> +
> +		ret = add_resource(&iomem_resource, res);
> +		if (ret < 0)
> +			goto error;
> +	}
> +
> +	return;
> +
> + error:
> +	memblock_free((phys_addr_t) res, sizeof(struct resource));
> +	/* Better an empty resource tree than an inconsistent one */
> +	release_child_resources(&iomem_resource);
> +}
> +
> +
>  void __init parse_dtb(void)
>  {
>  	if (early_init_dt_scan(dtb_early_va))
> @@ -73,6 +232,7 @@ void __init setup_arch(char **cmdline_p)
>
>  	setup_bootmem();
>  	paging_init();
> +	init_resources();
>  #if IS_ENABLED(CONFIG_BUILTIN_DTB)
>  	unflatten_and_copy_device_tree();
>  #else
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index f750e012d..05d6cf0c2 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -541,39 +541,12 @@ void mark_rodata_ro(void)
>  }
>  #endif
>
> -static void __init resource_init(void)
> -{
> -	struct memblock_region *region;
> -
> -	for_each_memblock(memory, region) {
> -		struct resource *res;
> -
> -		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
> -		if (!res)
> -			panic("%s: Failed to allocate %zu bytes\n", __func__,
> -			      sizeof(struct resource));
> -
> -		if (memblock_is_nomap(region)) {
> -			res->name = "reserved";
> -			res->flags = IORESOURCE_MEM;
> -		} else {
> -			res->name = "System RAM";
> -			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> -		}
> -		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
> -		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
> -
> -		request_resource(&iomem_resource, res);
> -	}
> -}
> -
>  void __init paging_init(void)
>  {
>  	setup_vm_final();
>  	sparse_init();
>  	setup_zero_page();
>  	zone_sizes_init();
> -	resource_init();
>  }
>
>  #ifdef CONFIG_SPARSEMEM_VMEMMAP

Thanks, this is on for-next.  I had to fix up a few things, LMK if I screwed
anything up.