[PATCH v9 01/10] memblock: Introduce MEMBLOCK_LLMAP

[Mike Rapoport]

On Wed, Sep 02, 2026 at 11:47:03AM +0100, Vincent Donnefort wrote:
> Keeping last-level mappings is interesting on some architectures as it
> allows mapping/unmapping pages from the kernel direct map without the
> risk of splitting blocks which, under the break-before-make rule, may
> trigger page-faults the kernel can't handle.
> 
> However, mapping the entire direct map at PTE-level is costly. So
> instead, create a new memblock flag MEMBLOCK_LLMAP to enable the system

I believe MEMBLOCK_PTE_MAP sounds more descriptive.

> to decide which region must be covered by mappings up to the last-level.
> 
> Signed-off-by: Vincent Donnefort <vdonnefort at google.com>
> 
> diff --git a/include/linux/memblock.h b/include/linux/memblock.h
> index d62db9e776cf..d40a5ded188d 100644
> --- a/include/linux/memblock.h
> +++ b/include/linux/memblock.h
> @@ -52,6 +52,7 @@ extern unsigned long long max_possible_pfn;
>   * kernel that we know is good to use. It is the only memory that
>   * allocations may happen from in this phase.
>   * @MEMBLOCK_RSRV_HUGETLB: memory is reserved for hugetlb pages
> + * @MEMBLOCK_LLMAP: memory region to be mapped using last-level mapping
>   */
>  enum memblock_flags {
>  	MEMBLOCK_NONE		= 0x0,	/* No special request */
> @@ -63,6 +64,7 @@ enum memblock_flags {
>  	MEMBLOCK_RSRV_KERN	= 0x20,	/* memory reserved for kernel use */
>  	MEMBLOCK_KHO_SCRATCH	= 0x40,	/* scratch memory for kexec handover */
>  	MEMBLOCK_RSRV_HUGETLB	= 0x80, /* memory reserved for hugetlb pages */
> +	MEMBLOCK_LLMAP		= 0x100,/* last-level mapping */
>  };
>  
>  /**
> @@ -160,6 +162,8 @@ int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size);
>  int memblock_reserved_mark_kern(phys_addr_t base, phys_addr_t size);
>  int memblock_mark_kho_scratch(phys_addr_t base, phys_addr_t size);
>  int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size);
> +int memblock_mark_llmap(phys_addr_t base, phys_addr_t size);
> +int memblock_clear_llmap(phys_addr_t base, phys_addr_t size);
>  
>  void memblock_free(void *ptr, size_t size);
>  void reset_all_zones_managed_pages(void);
> @@ -306,6 +310,11 @@ static inline bool memblock_is_kho_scratch(struct memblock_region *m)
>  	return m->flags & MEMBLOCK_KHO_SCRATCH;
>  }
>  
> +static inline bool memblock_is_llmap(struct memblock_region *m)
> +{
> +	return m->flags & MEMBLOCK_LLMAP;
> +}
> +
>  int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
>  			    unsigned long  *end_pfn);
>  void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
> diff --git a/mm/memblock.c b/mm/memblock.c
> index 9ce86349a29f..1591b50503ed 100644
> --- a/mm/memblock.c
> +++ b/mm/memblock.c
> @@ -1119,6 +1119,16 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
>   */
>  int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
>  {
> +	struct memblock_region *r;
> +
> +	memblock_cap_size(base, &size);
> +
> +	for_each_mem_region(r) {
> +		if (memblock_is_llmap(r) &&
> +		    memblock_addrs_overlap(base, size, r->base, r->size))
> +			return -EINVAL;
> +	}

I'm not very fond of implicit skips here. memblock has no idea what's the
caller intention, maybe it actually wants to change the memory from nomap
to pte-mapped.

I'd rather warn in memblock_is_nomap() and memblock_is_llmap() if they both
are set and let the caller deal with making sure they are not.

> +
>  	return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP);
>  }
>  
> @@ -1204,6 +1214,45 @@ __init int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size)
>  				    MEMBLOCK_KHO_SCRATCH);
>  }
>  
> +/**
> + * memblock_mark_llmap - Mark a memory region with flag MEMBLOCK_LLMAP.
> + * @base: the base phys addr of the region
> + * @size: the size of the region
> + *
> + * If supported by the architecture, such region is mapped at the last-level in
> + * the kernel direct map.
> + *
> + * Return: 0 on success, -errno on failure.
> + */
> +int __init_memblock memblock_mark_llmap(phys_addr_t base, phys_addr_t size)
> +{
> +	struct memblock_region *r;
> +
> +	memblock_cap_size(base, &size);
> +
> +	for_each_mem_region(r) {
> +		if (memblock_is_nomap(r) &&
> +		    memblock_addrs_overlap(base, size, r->base, r->size))
> +			return -EINVAL;
> +	}

same here

> +
> +	return memblock_setclr_flag(&memblock.memory, base, size, 1,
> +				    MEMBLOCK_LLMAP);
> +}
> +
> +/**
> + * memblock_clear_llmap - Clear flag MEMBLOCK_LLMAP for a specified region.
> + * @base: the base phys addr of the region
> + * @size: the size of the region
> + *
> + * Return: 0 on success, -errno on failure.
> + */
> +int __init_memblock memblock_clear_llmap(phys_addr_t base, phys_addr_t size)
> +{
> +	return memblock_setclr_flag(&memblock.memory, base, size, 0,
> +				    MEMBLOCK_LLMAP);
> +}
> +
>  static bool should_skip_region(struct memblock_type *type,
>  			       struct memblock_region *m,
>  			       int nid, int flags)
> @@ -2886,6 +2935,7 @@ static const char * const flagname[] = {
>  	[ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT",
>  	[ilog2(MEMBLOCK_RSRV_KERN)] = "RSV_KERN",
>  	[ilog2(MEMBLOCK_KHO_SCRATCH)] = "KHO_SCRATCH",
> +	[ilog2(MEMBLOCK_LLMAP)] = "LLMAP",
>  };
>  
>  static int memblock_debug_show(struct seq_file *m, void *private)
> -- 
> 2.55.0.970.g62bdec98f9-goog
> 

-- 
Sincerely yours,
Mike.