On 6/14/22 05:02, Kirill A. Shutemov wrote:
...
> +/*
> + * The accepted memory bitmap only works at PMD_SIZE granularity. If a request
> + * comes in to mark memory as unaccepted which is not PMD_SIZE-aligned, simply
> + * accept the memory now since it can not be *marked* as unaccepted.
> + */
/*
* The accepted memory bitmap only works at PMD_SIZE granularity. This
* function takes unaligned start/end addresses and either:
* 1. Accepts the memory immediately and in its entirety
* 2. Accepts unaligned parts, and marks *some* aligned part unaccepted
*
* The function will never reach the bitmap_set() with zero bits to set.
*/
> +void process_unaccepted_memory(struct boot_params *params, u64 start, u64 end)
> +{
> + /*
> + * Accept small regions that might not be able to be represented
> + * in the bitmap. This is a bit imprecise and may accept some
> + * areas that could have been represented in the bitmap instead.
/*
* Ensure that at least one bit will be set in the bitmap by
* immediately accepting all regions under 2*PMD_SIZE. This is
* imprecise and may immediately accept some areas that could
* have been represented in the bitmap. But, results in simpler
* code below.
> + * Consider case like this:
> + *
> + * | 4k | 2044k | 2048k |
> + * ^ 0x0 ^ 2MB ^ 4MB
> + *
> + * all memory in the range is unaccepted, except for the first 4k.
> + * The second 2M can be represented in the bitmap, but kernel accept it
> + * right away. The imprecision makes the code simpler by ensuring that
> + * at least one bit will be set int the bitmap below.
> + */
...
* Only the first 4k has been accepted. The 0MB->2MB region can
* not be represented in the bitmap. The 2MB->4MB region can be
* represented in the bitmap. But, the 0MB->4MB region is
* <2*PMD_SIZE and will be immediately accepted in its entirety.
*/
> + if (end - start < 2 * PMD_SIZE) {
> + __accept_memory(start, end);
> + return;
> + }
> +
> + /*
> + * No matter how the start and end are aligned, at least one unaccepted
> + * PMD_SIZE area will remain.
> + */
I'd probably add:
... to be marked in the bitmap
<snip>
> @@ -607,6 +608,17 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s
> e820_type = E820_TYPE_PMEM;
> break;
>
> + case EFI_UNACCEPTED_MEMORY:
> + if (!IS_ENABLED(CONFIG_UNACCEPTED_MEMORY)) {
> + efi_warn_once("The system has unaccepted memory,"
> + " but kernel does not support it\n");
> + efi_warn_once("Consider enabling CONFIG_UNACCEPTED_MEMORY\n");
> + continue;
> + }
> + e820_type = E820_TYPE_RAM;
> + process_unaccepted_memory(params, d->phys_addr,
> + d->phys_addr + PAGE_SIZE * d->num_pages);
> + break;
> default:
> continue;
> }
> @@ -671,6 +683,59 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
> return status;
> }
>
> +static efi_status_t allocate_unaccepted_memory(struct boot_params *params,
> + __u32 nr_desc,
> + struct efi_boot_memmap *map)
I think this is misnamed. This function is allocating a bitmap, not
"unaccepted_memory" itself. Right?
> +{
> + unsigned long *mem = NULL;
> + u64 size, max_addr = 0;
> + efi_status_t status;
> + bool found = false;
> + int i;
> +
> + /* Check if there's any unaccepted memory and find the max address */
> + for (i = 0; i < nr_desc; i++) {
> + efi_memory_desc_t *d;
> +
> + d = efi_early_memdesc_ptr(*map->map, *map->desc_size, i);
> + if (d->type == EFI_UNACCEPTED_MEMORY)
> + found = true;
> + if (d->phys_addr + d->num_pages * PAGE_SIZE > max_addr)
> + max_addr = d->phys_addr + d->num_pages * PAGE_SIZE;
> + }
> +
> + if (!found) {
> + params->unaccepted_memory = 0;
> + return EFI_SUCCESS;
> + }
> +
> + /*
> + * If unaccepted memory is present allocate a bitmap to track what
^ comma
> + * memory has to be accepted before access.
> + *
> + * One bit in the bitmap represents 2MiB in the address space:
> + * A 4k bitmap can track 64GiB of physical address space.
> + *
> + * In the worst case scenario -- a huge hole in the middle of the
> + * address space -- It needs 256MiB to handle 4PiB of the address
> + * space.
> + *
> + * TODO: handle situation if params->unaccepted_memory is already set.
> + * It's required to deal with kexec.
> + *
> + * The bitmap will be populated in setup_e820() according to the memory
> + * map after efi_exit_boot_services().
> + */
> + size = DIV_ROUND_UP(max_addr, PMD_SIZE * BITS_PER_BYTE);
> + status = efi_allocate_pages(size, (unsigned long *)&mem, ULONG_MAX);
> + if (status == EFI_SUCCESS) {
> + memset(mem, 0, size);
> + params->unaccepted_memory = (unsigned long)mem;
> + }
> +
> + return status;
> +}
> +
> static efi_status_t allocate_e820(struct boot_params *params,
> struct efi_boot_memmap *map,
> struct setup_data **e820ext,
> @@ -691,6 +756,9 @@ static efi_status_t allocate_e820(struct boot_params *params,
> status = alloc_e820ext(nr_e820ext, e820ext, e820ext_size);
> }
>
> + if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) && status == EFI_SUCCESS)
> + status = allocate_unaccepted_memory(params, nr_desc, map);
> +
> efi_bs_call(free_pool, *map->map);
> return status;
> }
> diff --git a/include/linux/efi.h b/include/linux/efi.h
> index 7d9b0bb47eb3..9c2fa94f2f93 100644
> --- a/include/linux/efi.h
> +++ b/include/linux/efi.h
> @@ -108,7 +108,8 @@ typedef struct {
> #define EFI_MEMORY_MAPPED_IO_PORT_SPACE 12
> #define EFI_PAL_CODE 13
> #define EFI_PERSISTENT_MEMORY 14
> -#define EFI_MAX_MEMORY_TYPE 15
> +#define EFI_UNACCEPTED_MEMORY 15
> +#define EFI_MAX_MEMORY_TYPE 16
>
> /* Attribute values: */
> #define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */
