Re: [PATCH 3/7] RISC-V: Rework kernel's virtual address space mapping

[Palmer Dabbelt]

On Wed, 27 Mar 2019 14:36:39 PDT (-0700), logang@xxxxxxxxxxxx wrote:
> The motivation for this is to support P2P transactions. P2P requires
> having struct pages for IO memory which means the linear mapping must
> be able to cover all of the IO regions. Unfortunately with Sv39 we are
> not able to cover all the IO regions available on existing hardware,
> but we can do better than what we currently do (which only cover's
> physical memory).
>
> To this end, we restructure the kernel's virtual address space region.
> We position the vmemmap at the beginning of the region (based on how
> many virtual address bits we have) and the VMALLOC region comes
> immediately after. The linear mapping then takes up the remaining space.
> PAGE_OFFSET will need to be within the linear mapping but may not be
> the start of the mapping seeing many machines don't have RAM at address
> zero and we may still want to access lower addresses through the
> linear mapping.
>
> With these changes, on a 64-bit system the virtual memory map (with
> sparsemem enabled) will be:
>
> 32-bit:
>
> 00000000 - 7fffffff   user space, different per mm (2G)
> 80000000 - 81ffffff   virtual memory map (32MB)
> 82000000 - bfffffff   vmalloc/ioremap space (1GB - 32MB)
> c0000000 - ffffffff   direct mapping of all phys. memory (1GB)
>
> 64-bit, Sv39:
>
> 0000000000000000 - 0000003fffffffff  user space, different per mm (256GB)
> hole caused by [38:63] sign extension
> ffffffc000000000 - ffffffc0ffffffff  virtual memory map (4GB)
> ffffffc100000000 - ffffffd0ffffffff  vmalloc/ioremap spac (64GB)
> ffffffd100000000 - ffffffffffffffff  linear mapping of phys. space (188GB)
>
> On the Sifive hardware this allows us to provide struct pages for
> the lower I/O TileLink address ranges, the 32-bit and 34-bit DRAM areas
> and 172GB of 240GB of the high I/O TileLink region. Once we progress to
> Sv48 we should be able to cover all the available memory regions..
>
> For the MAXPHYSMEM_2GB case, the physical memory must be in the highest
> 2GB of address space, so we cannot cover the any of the I/O regions
> that are higher than it but we do cover the lower I/O TileLink range.

IIRC there was another patch floating around to fix an issue with overlapping 
regions in the 32-bit port, did you also fix that issue?  It's somewhere in my 
email queue...

> Signed-off-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
> Cc: Palmer Dabbelt <palmer@xxxxxxxxxx>
> Cc: Albert Ou <aou@xxxxxxxxxxxxxxxxx>
> Cc: Antony Pavlov <antonynpavlov@xxxxxxxxx>
> Cc: "Stefan O'Rear" <sorear2@xxxxxxxxx>
> Cc: Anup Patel <anup.patel@xxxxxxx>
> ---
>  arch/riscv/Kconfig               |  2 +-
>  arch/riscv/include/asm/page.h    |  2 --
>  arch/riscv/include/asm/pgtable.h | 27 ++++++++++++++++++---------
>  3 files changed, 19 insertions(+), 12 deletions(-)
>
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index 76fc340ae38e..d21e6a12e8b6 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -71,7 +71,7 @@ config PAGE_OFFSET
>  	hex
>  	default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
>  	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
> -	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
> +	default 0xffffffd200000000 if 64BIT && MAXPHYSMEM_128GB
>
>  config ARCH_FLATMEM_ENABLE
>  	def_bool y
> diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
> index 2a546a52f02a..fa0b8058a246 100644
> --- a/arch/riscv/include/asm/page.h
> +++ b/arch/riscv/include/asm/page.h
> @@ -31,8 +31,6 @@
>   */
>  #define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
>
> -#define KERN_VIRT_SIZE (-PAGE_OFFSET)
> -
>  #ifndef __ASSEMBLY__
>
>  #define PAGE_UP(addr)	(((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1)))
> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
> index 5a9fea00ba09..2a5070540996 100644
> --- a/arch/riscv/include/asm/pgtable.h
> +++ b/arch/riscv/include/asm/pgtable.h
> @@ -89,22 +89,31 @@ extern pgd_t swapper_pg_dir[];
>  #define __S110	PAGE_SHARED_EXEC
>  #define __S111	PAGE_SHARED_EXEC
>
> -#define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
> -#define VMALLOC_END      (PAGE_OFFSET - 1)
> -#define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
> +#define KERN_SPACE_START	(-1UL << (CONFIG_VA_BITS - 1))
>
>  /*
>   * Roughly size the vmemmap space to be large enough to fit enough
>   * struct pages to map half the virtual address space. Then
>   * position vmemmap directly below the VMALLOC region.
>   */
> -#define VMEMMAP_SHIFT \
> -	(CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
> -#define VMEMMAP_SIZE	(1UL << VMEMMAP_SHIFT)
> -#define VMEMMAP_END	(VMALLOC_START - 1)
> -#define VMEMMAP_START	(VMALLOC_START - VMEMMAP_SIZE)
> -
> +#ifdef CONFIG_SPARSEMEM
> +#define VMEMMAP_SIZE	(UL(1) << (CONFIG_VA_BITS - PAGE_SHIFT - 1 + \
> +				   STRUCT_PAGE_MAX_SHIFT))
> +#define VMEMMAP_START	(KERN_SPACE_START)
> +#define VMEMMAP_END	(VMEMMAP_START + VMEMMAP_SIZE - 1)
>  #define vmemmap		((struct page *)VMEMMAP_START)
> +#else
> +#define VMEMMAP_END	KERN_SPACE_START
> +#endif
> +
> +#ifdef CONFIG_32BIT
> +#define VMALLOC_SIZE	((1UL << 30) - VMEMMAP_SIZE)
> +#else
> +#define VMALLOC_SIZE	(64UL << 30)
> +#endif
> +
> +#define VMALLOC_START	(VMEMMAP_END + 1)
> +#define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE - 1)
>
>  /*
>   * ZERO_PAGE is a global shared page that is always zero,