Re: [PATCH v2 6/6] RISC-V: Implement sparsemem

[Nick Kossifidis]

Hello Logan,

ÎÏÎÏ 2018-10-15 20:57, Logan Gunthorpe ÎÎÏÎÏÎ:
> This patch implements sparsemem support for risc-v which helps pave the
> way for memory hotplug and eventually P2P support.
>
> We introduce Kconfig options for virtual and physical address bits 
> which
> are used to calculate the size of the vmemmap and set the
> MAX_PHYSMEM_BITS.
>
> The vmemmap is located directly before the VMALLOC region and sized
> such that we can allocate enough pages to populate all the virtual
> address space in the system (similar to the way it's done in arm64).
>
> During initialization, call memblocks_present() and sparse_init(),
> and provide a stub for vmemmap_populate() (all of which is similar to
> arm64).
>
> Signed-off-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
> Reviewed-by: Palmer Dabbelt <palmer@xxxxxxxxxx>
> Cc: Albert Ou <aou@xxxxxxxxxxxxxxxxx>
> Cc: Andrew Waterman <andrew@xxxxxxxxxx>
> Cc: Olof Johansson <olof@xxxxxxxxx>
> Cc: Michael Clark <michaeljclark@xxxxxxx>
> Cc: Rob Herring <robh@xxxxxxxxxx>
> Cc: Zong Li <zong@xxxxxxxxxxxxx>
> ---
>  arch/riscv/Kconfig                 | 23 +++++++++++++++++++++++
>  arch/riscv/include/asm/pgtable.h   | 21 +++++++++++++++++----
>  arch/riscv/include/asm/sparsemem.h | 11 +++++++++++
>  arch/riscv/kernel/setup.c          |  4 +++-
>  arch/riscv/mm/init.c               |  8 ++++++++
>  5 files changed, 62 insertions(+), 5 deletions(-)
>  create mode 100644 arch/riscv/include/asm/sparsemem.h
>
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index a344980287a5..a1b5d758a542 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -52,12 +52,32 @@ config ZONE_DMA32
>  	bool
>  	default y if 64BIT
>
> +config VA_BITS
> +	int
> +	default 32 if 32BIT
> +	default 39 if 64BIT
> +
> +config PA_BITS
> +	int
> +	default 34 if 32BIT
> +	default 56 if 64BIT
> +
>  config PAGE_OFFSET
>  	hex
>  	default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
>  	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
>  	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
>
> +config ARCH_FLATMEM_ENABLE
> +	def_bool y
> +
> +config ARCH_SPARSEMEM_ENABLE
> +	def_bool y
> +	select SPARSEMEM_VMEMMAP_ENABLE
> +
> +config ARCH_SELECT_MEMORY_MODEL
> +	def_bool ARCH_SPARSEMEM_ENABLE
> +
>  config STACKTRACE_SUPPORT
>  	def_bool y
>
> @@ -92,6 +112,9 @@ config PGTABLE_LEVELS
>  config HAVE_KPROBES
>  	def_bool n
>
> +config HAVE_ARCH_PFN_VALID
> +	def_bool y
> +
>  menu "Platform type"
>
>  choice
> diff --git a/arch/riscv/include/asm/pgtable.h 
> b/arch/riscv/include/asm/pgtable.h
> index 16301966d65b..e1162336f5ea 100644
> --- a/arch/riscv/include/asm/pgtable.h
> +++ b/arch/riscv/include/asm/pgtable.h
> @@ -89,6 +89,23 @@ 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)
> +
> +/*
> + * 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)
> +
> +#define vmemmap		((struct page *)VMEMMAP_START)
> +
>  /*
>   * ZERO_PAGE is a global shared page that is always zero,
>   * used for zero-mapped memory areas, etc.
> @@ -411,10 +428,6 @@ static inline void pgtable_cache_init(void)
>  	/* No page table caches to initialize */
>  }
>
> -#define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
> -#define VMALLOC_END      (PAGE_OFFSET - 1)
> -#define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
> -
>  /*
>   * Task size is 0x40000000000 for RV64 or 0xb800000 for RV32.
>   * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
> diff --git a/arch/riscv/include/asm/sparsemem.h
> b/arch/riscv/include/asm/sparsemem.h
> new file mode 100644
> index 000000000000..215530b24336
> --- /dev/null
> +++ b/arch/riscv/include/asm/sparsemem.h
> @@ -0,0 +1,11 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +#ifndef __ASM_SPARSEMEM_H
> +#define __ASM_SPARSEMEM_H
> +
> +#ifdef CONFIG_SPARSEMEM
> +#define MAX_PHYSMEM_BITS	CONFIG_PA_BITS
> +#define SECTION_SIZE_BITS	30

Having memory blocks of a minimum size of 1GB doesn't make much sense. 
It makes it harder to implement hotplug on top of this since we'll only 
able to add/remove 1GB at a time. ARM used to do the same and they 
switched to 27bits (https://patchwork.kernel.org/patch/9172845/), ARM64 
still uses 1GB, x86 also uses 27bits and most archs also use something 
below 30. I believe we should go for 27bits as well or even better have 
this as a compile time option.

BTW memblocks_present is on master now (got merged 3 days ago).

Regards,
N.