Hello Ard,
Thank you for sending the patch, but unfortunately it doesn't work for the issue...
After applied your patch, the LPI tables are marked as reserved in
/proc/iomem like as:
80300000-a1fdffff : System RAM
80480000-8134ffff : Kernel code
81350000-817bffff : reserved
817c0000-82acffff : Kernel data
830f0000-830fffff : reserved # Property table
83480000-83480fff : reserved # Pending table
83490000-8349ffff : reserved # Pending table
However, kexec tries to allocate memory from System RAM, it doesn't care
the reserved in System RAM.
Following example, kexec allocates memory 0x82ad0000-0x86640000 to locate
the initrd, and LPI tables are also in the memory region, so LPI tables
will be destroyed by kexec reboot.
# kexec -d -l /boot/vmlinuz-5.4.1+ --initrd=/boot/initramfs-5.4.1+.img
...
initrd: base 82ad0000, size 3b67c6fh (62291055)
...
segment[1].mem = 0x82ad0000
segment[1].memsz = 0x3b70000 # 0x86640000 (== 0x82ad0000 + 0x3b70000)
...
I'm not sure why kexec doesn't care the reserved in System RAM, however,
if the kexec behaivor is right, the LPI tables should not belong to
System RAM.
Like as:
80300000-830effff : System RAM
80480000-8134ffff : Kernel code
81350000-817bffff : reserved
817c0000-82acffff : Kernel data
830f0000-830fffff : reserved # Property table
83480000-83480fff : reserved # Pending table
83490000-8349ffff : reserved # Pending table
834a0000-a1fdffff : System RAM
I don't have ideas to separete LPI tables from System RAM... so I tried
to add a new file to inform the LPI tables to userspace.
Thanks,
Masa
On Wed, Dec 04, 2019 at 02:52:33PM +0000, Ard Biesheuvel wrote:
> Memory regions that are reserved using efi_mem_reserve_persistent()
> are recorded in a special EFI config table which survives kexec,
> allowing the incoming kernel to honour them as well. However,
> such reservations are not visible in /proc/iomem, and so the kexec
> tools that load the incoming kernel and its initrd into memory may
> overwrite these reserved regions before the incoming kernel has a
> chance to reserve them from further use.
>
> So add these reservations to /proc/iomem as they are created. Note
> that reservations that are inherited from a previous kernel are
> memblock_reserve()'d early on, so they are already visible in
> /proc/iomem.
>
> Cc: Masayoshi Mizuma <m.mizuma@xxxxxxxxxxxxxx>
> Cc: d.hatayama@xxxxxxxxxxx
> Cc: kexec@xxxxxxxxxxxxxxxxxxx
> Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx>
> ---
> drivers/firmware/efi/efi.c | 29 ++++++++++++++++++--
> 1 file changed, 26 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
> index d101f072c8f8..fcd82dde23c8 100644
> --- a/drivers/firmware/efi/efi.c
> +++ b/drivers/firmware/efi/efi.c
> @@ -979,6 +979,24 @@ static int __init efi_memreserve_map_root(void)
> return 0;
> }
>
> +static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size)
> +{
> + struct resource *res, *parent;
> +
> + res = kzalloc(sizeof(struct resource), GFP_ATOMIC);
> + if (!res)
> + return -ENOMEM;
> +
> + res->name = "reserved";
> + res->flags = IORESOURCE_MEM;
> + res->start = addr;
> + res->end = addr + size - 1;
> +
> + /* we expect a conflict with a 'System RAM' region */
> + parent = request_resource_conflict(&iomem_resource, res);
> + return parent ? request_resource(parent, res) : 0;
> +}
> +
> int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
> {
> struct linux_efi_memreserve *rsv;
> @@ -1001,9 +1019,8 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
> if (index < rsv->size) {
> rsv->entry[index].base = addr;
> rsv->entry[index].size = size;
> -
> memunmap(rsv);
> - return 0;
> + return efi_mem_reserve_iomem(addr, size);
> }
> memunmap(rsv);
> }
> @@ -1013,6 +1030,12 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
> if (!rsv)
> return -ENOMEM;
>
> + rc = efi_mem_reserve_iomem(__pa(rsv), SZ_4K);
> + if (rc) {
> + free_page(rsv);
> + return rc;
> + }
> +
> /*
> * The memremap() call above assumes that a linux_efi_memreserve entry
> * never crosses a page boundary, so let's ensure that this remains true
> @@ -1029,7 +1052,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
> efi_memreserve_root->next = __pa(rsv);
> spin_unlock(&efi_mem_reserve_persistent_lock);
>
> - return 0;
> + return efi_mem_reserve_iomem(addr, size);
> }
>
> static int __init efi_memreserve_root_init(void)
> --
> 2.17.1
>
>
>
