linux-kernel - Re: [PATCH v2 3/5] mm: memory_hotplug: memblock to track partially removed vmemmap mem

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <f21d2b81-e0f5-b186-22e3-ded138505dc9@arm.com>
Date:   Mon, 27 Nov 2017 15:20:56 +0000
From:   Robin Murphy <robin.murphy@....com>
To:     Andrea Reale <ar@...ux.vnet.ibm.com>,
        linux-arm-kernel@...ts.infradead.org
Cc:     mark.rutland@....com, realean2@...ibm.com, mhocko@...e.com,
        m.bielski@...tualopensystems.com, scott.branden@...adcom.com,
        catalin.marinas@....com, will.deacon@....com,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        arunks@....qualcomm.com, qiuxishi@...wei.com
Subject: Re: [PATCH v2 3/5] mm: memory_hotplug: memblock to track partially
 removed vmemmap mem

On 23/11/17 11:14, Andrea Reale wrote:
> When hot-removing memory we need to free vmemmap memory.

What problems arise if we don't? Is it only for the sake of freeing up 
some pages here and there, or is there something more fundamental?

> However, depending on the memory is being removed, it might
> not be always possible to free a full vmemmap page / huge-page
> because part of it might still be used.
> 
> Commit ae9aae9eda2d ("memory-hotplug: common APIs to support page tables
> hot-remove") introduced a workaround for x86
> hot-remove, by which partially unused areas are filled with
> the 0xFD constant. Full pages are only removed when fully
> filled by 0xFDs.
> 
> This commit introduces a MEMBLOCK_UNUSED_VMEMMAP memblock flag, with
> the goal of using it in place of 0xFDs. For now, this will be used for
> the arm64 port of memory hot remove, but the idea is to eventually use
> the same mechanism for x86 as well.
> 
> Signed-off-by: Andrea Reale <ar@...ux.vnet.ibm.com>
> Signed-off-by: Maciej Bielski <m.bielski@...tualopensystems.com>
> ---
>   include/linux/memblock.h | 12 ++++++++++++
>   mm/memblock.c            | 32 ++++++++++++++++++++++++++++++++
>   2 files changed, 44 insertions(+)
> 
> diff --git a/include/linux/memblock.h b/include/linux/memblock.h
> index bae11c7..0daec05 100644
> --- a/include/linux/memblock.h
> +++ b/include/linux/memblock.h
> @@ -26,6 +26,9 @@ enum {
>   	MEMBLOCK_HOTPLUG	= 0x1,	/* hotpluggable region */
>   	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
>   	MEMBLOCK_NOMAP		= 0x4,	/* don't add to kernel direct mapping */
> +#ifdef CONFIG_MEMORY_HOTREMOVE
> +	MEMBLOCK_UNUSED_VMEMMAP	= 0x8,  /* Mark VMEMAP blocks as dirty */

I'm not sure I get what "dirty" is supposed to mean in this context. 
Also, this appears to be specific to CONFIG_SPARSEMEM_VMEMMAP, whilst 
only tangentially related to CONFIG_MEMORY_HOTREMOVE, so the 
dependencies look a bit off.

In fact, now that I think about it, why does this need to be in memblock 
at all? If it is specific to sparsemem, shouldn't the section map 
already be enough to tell us what's supposed to be present or not?

Robin.

> +#endif
>   };
>   
>   struct memblock_region {
> @@ -90,6 +93,10 @@ int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
>   int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
>   int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
>   ulong choose_memblock_flags(void);
> +#ifdef CONFIG_MEMORY_HOTREMOVE
> +int memblock_mark_unused_vmemmap(phys_addr_t base, phys_addr_t size);
> +int memblock_clear_unused_vmemmap(phys_addr_t base, phys_addr_t size);
> +#endif
>   
>   /* Low level functions */
>   int memblock_add_range(struct memblock_type *type,
> @@ -182,6 +189,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m)
>   	return m->flags & MEMBLOCK_NOMAP;
>   }
>   
> +#ifdef CONFIG_MEMORY_HOTREMOVE
> +bool memblock_is_vmemmap_unused_range(struct memblock_type *mt,
> +		phys_addr_t start, phys_addr_t end);
> +#endif
> +
>   #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
>   int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
>   			    unsigned long  *end_pfn);
> diff --git a/mm/memblock.c b/mm/memblock.c
> index 9120578..30d5aa4 100644
> --- a/mm/memblock.c
> +++ b/mm/memblock.c
> @@ -809,6 +809,18 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
>   	return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP);
>   }
>   
> +#ifdef CONFIG_MEMORY_HOTREMOVE
> +int __init_memblock memblock_mark_unused_vmemmap(phys_addr_t base,
> +		phys_addr_t size)
> +{
> +	return memblock_setclr_flag(base, size, 1, MEMBLOCK_UNUSED_VMEMMAP);
> +}
> +int __init_memblock memblock_clear_unused_vmemmap(phys_addr_t base,
> +		phys_addr_t size)
> +{
> +	return memblock_setclr_flag(base, size, 0, MEMBLOCK_UNUSED_VMEMMAP);
> +}
> +#endif
>   /**
>    * __next_reserved_mem_region - next function for for_each_reserved_region()
>    * @idx: pointer to u64 loop variable
> @@ -1696,6 +1708,26 @@ void __init_memblock memblock_trim_memory(phys_addr_t align)
>   	}
>   }
>   
> +#ifdef CONFIG_MEMORY_HOTREMOVE
> +bool __init_memblock memblock_is_vmemmap_unused_range(struct memblock_type *mt,
> +		phys_addr_t start, phys_addr_t end)
> +{
> +	u64 i;
> +	struct memblock_region *r;
> +
> +	i = memblock_search(mt, start);
> +	r = &(mt->regions[i]);
> +	while (r->base < end) {
> +		if (!(r->flags & MEMBLOCK_UNUSED_VMEMMAP))
> +			return 0;
> +
> +		r = &(memblock.memory.regions[++i]);
> +	}
> +
> +	return 1;
> +}
> +#endif
> +
>   void __init_memblock memblock_set_current_limit(phys_addr_t limit)
>   {
>   	memblock.current_limit = limit;
>