Hi Akashi,
On 25/04/18 07:26, AKASHI Takahiro wrote:
> Enabling crash dump (kdump) includes
> * prepare contents of ELF header of a core dump file, /proc/vmcore,
> using crash_prepare_elf64_headers(), and
> * add two device tree properties, "linux,usable-memory-range" and
> "linux,elfcorehdr", which represent repsectively a memory range
(Nit: respectively)
> to be used by crash dump kernel and the header's location
> arch/arm64/include/asm/kexec.h | 4 +
> arch/arm64/kernel/kexec_image.c | 9 +-
> arch/arm64/kernel/machine_kexec_file.c | 202 +++++++++++++++++++++++++
In this patch, machine_kexec_file.c gains its own private fdt array encoder.
> diff --git a/arch/arm64/kernel/machine_kexec_file.c
> b/arch/arm64/kernel/machine_kexec_file.c
> index 37c0a9dc2e47..ec674f4d267c 100644
> --- a/arch/arm64/kernel/machine_kexec_file.c
> +++ b/arch/arm64/kernel/machine_kexec_file.c
> @@ -76,6 +81,78 @@ int arch_kexec_walk_mem(struct kexec_buf *kbuf,
> return ret;
> }
>
> +static int __init arch_kexec_file_init(void)
> +{
> + /* Those values are used later on loading the kernel */
> + __dt_root_addr_cells = dt_root_addr_cells;
> + __dt_root_size_cells = dt_root_size_cells;
> +
> + return 0;
> +}
> +late_initcall(arch_kexec_file_init);
If we need these is it worth taking them out of __initdata? I note they've been
'temporary' for quite a long time.
> +
> +#define FDT_ALIGN(x, a) (((x) + (a) - 1) & ~((a) - 1))
> +#define FDT_TAGALIGN(x) (FDT_ALIGN((x), FDT_TAGSIZE))
> +
> +static int fdt_prop_len(const char *prop_name, int len)
> +{
> + return (strlen(prop_name) + 1) +
> + sizeof(struct fdt_property) +
> + FDT_TAGALIGN(len);
> +}
This stuff should really be in libfdt.h Those macros come from
libfdt_internal.h, so we're probably doing something wrong here.
> +static bool cells_size_fitted(unsigned long base, unsigned long size)
> +{
> + /* if *_cells >= 2, cells can hold 64-bit values anyway */
> + if ((__dt_root_addr_cells == 1) && (base >= (1ULL << 32)))
> + return false;
> +
> + if ((__dt_root_size_cells == 1) && (size >= (1ULL << 32)))
> + return false;
Using '> U32_MAX' here may be more readable.
> + return true;
> +}
> +
> +static void fill_property(void *buf, u64 val64, int cells)
> +{
> + u32 val32;
> +
> + if (cells == 1) {
> + val32 = cpu_to_fdt32((u32)val64);
> + memcpy(buf, &val32, sizeof(val32));
> + } else {
> + memset(buf, 0, cells * sizeof(u32) - sizeof(u64));
> + buf += cells * sizeof(u32) - sizeof(u64);
Is this trying to clear the 'top' cells and shuffle the pointer to point at the
'bottom' 2? I'm pretty sure this isn't endian safe.
Do we really expect a system to have #address-cells > 2?
> + val64 = cpu_to_fdt64(val64);
> + memcpy(buf, &val64, sizeof(val64));
> + }
> +}
> +
> +static int fdt_setprop_range(void *fdt, int nodeoffset, const char *name,
> + unsigned long addr, unsigned long size)
(the device-tree spec describes a 'ranges' property, which had me confused. This
is encoding a prop-encoded-array)
> +{
> + void *buf, *prop;
> + size_t buf_size;
> + int result;
> +
> + buf_size = (__dt_root_addr_cells + __dt_root_size_cells) * sizeof(u32);
> + prop = buf = vmalloc(buf_size);
virtual memory allocation for something less than PAGE_SIZE?
> + if (!buf)
> + return -ENOMEM;
> +
> + fill_property(prop, addr, __dt_root_addr_cells);
> + prop += __dt_root_addr_cells * sizeof(u32);
> +
> + fill_property(prop, size, __dt_root_size_cells);
> +
> + result = fdt_setprop(fdt, nodeoffset, name, buf, buf_size);
> +
> + vfree(buf);
> +
> + return result;
> +}
Doesn't this stuff belong in libfdt? I guess there is no 'add array element' api
because this the first time we've wanted to create a node with more than
key=fixed-size-value.
I don't think this belongs in arch C code. Do we have a plan for getting libfdt
to support encoding prop-arrays? Can we put it somewhere anyone else duplicating
this will find it, until we can (re)move it?
I have no idea how that happens... it looks like the devicetree list is the
place to ask.
> static int setup_dtb(struct kimage *image,
> unsigned long initrd_load_addr, unsigned long initrd_len,
> char *cmdline, unsigned long cmdline_len,
> @@ -88,10 +165,26 @@ static int setup_dtb(struct kimage *image,
> int range_len;
> int ret;
>
> + /* check ranges against root's #address-cells and #size-cells */
> + if (image->type == KEXEC_TYPE_CRASH &&
> + (!cells_size_fitted(image->arch.elf_load_addr,
> + image->arch.elf_headers_sz) ||
> + !cells_size_fitted(crashk_res.start,
> + crashk_res.end - crashk_res.start + 1))) {
> + pr_err("Crash memory region doesn't fit into DT's root cell
> sizes.\n");
> + ret = -EINVAL;
> + goto out_err;
> + }
To check I've understood this properly: This can happen if the firmware provided
a DTB with 32bit address/size cells, but at least some of the memory requires 64
bit address/size cells. This could only happen on a UEFI system where the
firmware-DTB doesn't describe memory. ACPI-only systems would have the EFIstub
DT.
> /* duplicate dt blob */
> buf_size = fdt_totalsize(initial_boot_params);
> range_len = (__dt_root_addr_cells + __dt_root_size_cells) * sizeof(u32);
>
> + if (image->type == KEXEC_TYPE_CRASH)
> + buf_size += fdt_prop_len("linux,elfcorehdr", range_len)
> + + fdt_prop_len("linux,usable-memory-range",
> + range_len);
> +
> if (initrd_load_addr)
> buf_size += fdt_prop_len("linux,initrd-start", sizeof(u64))
> + fdt_prop_len("linux,initrd-end", sizeof(u64));
> @@ -113,6 +206,23 @@ static int setup_dtb(struct kimage *image,
> if (nodeoffset < 0)
> goto out_err;
>
> + if (image->type == KEXEC_TYPE_CRASH) {
> + /* add linux,elfcorehdr */
> + ret = fdt_setprop_range(buf, nodeoffset, "linux,elfcorehdr",
> + image->arch.elf_load_addr,
> + image->arch.elf_headers_sz);
> + if (ret)
> + goto out_err;
> +
> + /* add linux,usable-memory-range */
> + ret = fdt_setprop_range(buf, nodeoffset,
> + "linux,usable-memory-range",
> + crashk_res.start,
> + crashk_res.end - crashk_res.start + 1);
Don't you need to add "linux,usable-memory-range" to the buf_size estimate?
> + if (ret)
> + goto out_err;
> + }
> @@ -148,17 +258,109 @@ static int setup_dtb(struct kimage *image,
> +static struct crash_mem *get_crash_memory_ranges(void)
> +{
> + unsigned int nr_ranges;
> + struct crash_mem *cmem;
> +
> + nr_ranges = 1; /* for exclusion of crashkernel region */
> + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ranges_callback);
> +
> + cmem = vmalloc(sizeof(struct crash_mem) +
> + sizeof(struct crash_mem_range) * nr_ranges);
> + if (!cmem)
> + return NULL;
> +
> + cmem->max_nr_ranges = nr_ranges;
> + cmem->nr_ranges = 0;
> + walk_system_ram_res(0, -1, cmem, add_mem_range_callback);
> +
> + /* Exclude crashkernel region */
> + if (crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end)) {
> + vfree(cmem);
> + return NULL;
> + }
> +
> + return cmem;
> +}
Could this function be included in prepare_elf_headers() so that the alloc() and
free() occur together.
> +static int prepare_elf_headers(void **addr, unsigned long *sz)
> +{
> + struct crash_mem *cmem;
> + int ret = 0;
> +
> + cmem = get_crash_memory_ranges();
> + if (!cmem)
> + return -ENOMEM;
> +
> + ret = crash_prepare_elf64_headers(cmem, true, addr, sz);
> +
> + vfree(cmem);
> + return ret;
> +}
All this is moving memory-range information from core-code's
walk_system_ram_res() into core-code's struct crash_mem, and excluding
crashk_res, which again is accessible to the core code.
It looks like this is duplicated in arch/x86 and arch/arm64 because arm64
doesn't have a second 'crashk_low_res' region, and always wants elf64, instead
of when IS_ENABLED(CONFIG_X86_64).
If we can abstract just those two, more of this could be moved to core code
where powerpc can make use of it if they want to support kdump with
kexec_file_load().
But, its getting late for cross-architecture dependencies, lets put that on the
for-later list. (assuming there isn't a powerpc-kdump series out there adding a
third copy of this)
Thanks,
James
_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec
