Re: [PATCH - resend] Memory-Hotplug: Fix the bug on interface/dev/mem for 64-bit kernel(v1)

[Wu Fengguang]

On Fri, Jan 08, 2010 at 11:32:07AM +0800, Zheng, Shaohui wrote:
> Resend the patch to the mailing-list, the original patch URL is 
> http://patchwork.kernel.org/patch/69075/, it is not accepted without comments,
> sent it again to review.
> 
> Memory-Hotplug: Fix the bug on interface /dev/mem for 64-bit kernel
> 
> The new added memory can not be access by interface /dev/mem, because we do not
>  update the variable high_memory. This patch add a new e820 entry in e820 table,
>  and update max_pfn, max_low_pfn and high_memory.
> 
> We add a function update_pfn in file arch/x86/mm/init.c to udpate these
>  varibles. Memory hotplug does not make sense on 32-bit kernel, so we did not
>  concern it in this function.
> 
> Signed-off-by: Shaohui Zheng <shaohui.zheng@xxxxxxxxx>
> CC: Andi Kleen <ak@xxxxxxxxxxxxxxx>
> CC: Wu Fengguang <fengguang.wu@xxxxxxxxx>
> CC: Li Haicheng <Haicheng.li@xxxxxxxxx>
> 
> ---
> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
> index f50447d..b986246 100644
> --- a/arch/x86/kernel/e820.c
> +++ b/arch/x86/kernel/e820.c
> @@ -110,8 +110,8 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type)
>  /*
>   * Add a memory region to the kernel e820 map.
>   */
> -static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
> -					 int type)
> +static void __meminit __e820_add_region(struct e820map *e820x, u64 start,
> +					 u64 size, int type)
>  {
>  	int x = e820x->nr_map;
>  
> @@ -126,7 +126,7 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
>  	e820x->nr_map++;
>  }
>  
> -void __init e820_add_region(u64 start, u64 size, int type)
> +void __meminit e820_add_region(u64 start, u64 size, int type)
>  {
>  	__e820_add_region(&e820, start, size, type);
>  }
> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
> index d406c52..0474459 100644
> --- a/arch/x86/mm/init.c
> +++ b/arch/x86/mm/init.c
> @@ -1,6 +1,7 @@
>  #include <linux/initrd.h>
>  #include <linux/ioport.h>
>  #include <linux/swap.h>
> +#include <linux/bootmem.h>
>  
>  #include <asm/cacheflush.h>
>  #include <asm/e820.h>
> @@ -386,3 +387,30 @@ void free_initrd_mem(unsigned long start, unsigned long end)
>  	free_init_pages("initrd memory", start, end);
>  }
>  #endif
> +
> +/**
> + * After memory hotplug, the variable max_pfn, max_low_pfn and high_memory will
> + * be affected, it will be updated in this function. Memory hotplug does not
> + * make sense on 32-bit kernel, so we do did not concern it in this function.
> + */
> +void __meminit __attribute__((weak)) update_pfn(u64 start, u64 size)
> +{
> +#ifdef CONFIG_X86_64
> +	unsigned long limit_low_pfn = 1UL<<(32 - PAGE_SHIFT);
> +	unsigned long start_pfn = start >> PAGE_SHIFT;
> +	unsigned long end_pfn = (start + size) >> PAGE_SHIFT;

Strictly speaking, should use "end_pfn = PFN_UP(start + size);".

> +	if (end_pfn > max_pfn) {
> +		max_pfn = end_pfn;
> +		high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
> +	}
> +
> +	/* if add to low memory, update max_low_pfn */
> +	if (unlikely(start_pfn < limit_low_pfn)) {
> +		if (end_pfn <= limit_low_pfn)
> +			max_low_pfn = end_pfn;
> +		else
> +			max_low_pfn = limit_low_pfn;

X86_64 actually always set max_low_pfn=max_pfn, in setup_arch():

 899 #ifdef CONFIG_X86_64
 900         if (max_pfn > max_low_pfn) {
 901                 max_pfn_mapped = init_memory_mapping(1UL<<32,
 902                                                      max_pfn<<PAGE_SHIFT);
 903                 /* can we preseve max_low_pfn ?*/
 904                 max_low_pfn = max_pfn;
 905         }
 906 #endif

max_low_pfn is used in

- e820_mark_nosave_regions(max_low_pfn);
- dump_pagetable()
- blk_queue_bounce_limit()
- increase_reservation()

and _seems_ to mean "end of direct addressable pfn".

> +	}
> +#endif /* CONFIG_X86_64 */
> +}
> diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
> index b10ec49..6693414 100644
> --- a/include/linux/bootmem.h
> +++ b/include/linux/bootmem.h
> @@ -13,6 +13,7 @@
>  
>  extern unsigned long max_low_pfn;
>  extern unsigned long min_low_pfn;
> +extern void update_pfn(u64 start, u64 size);
>  
>  /*
>   * highest page
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 030ce8a..ee7b2d6 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -523,6 +523,14 @@ int __ref add_memory(int nid, u64 start, u64 size)
>  		BUG_ON(ret);
>  	}
>  
> +	/* update e820 table */

This comment can be eliminated - you already have the very readable printk :)

> +	printk(KERN_INFO "Adding memory region to e820 table (start:%016Lx, size:%016Lx).\n",
> +			 (unsigned long long)start, (unsigned long long)size);
> +	e820_add_region(start, size, E820_RAM);

> +	/* update max_pfn, max_low_pfn and high_memory */
> +	update_pfn(start, size);

How about renaming function to update_end_of_memory_vars()?

Thanks,
Fengguang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/