Re: [patch 2/2] mm: Reimplementation of alloc_percpu

[Rusty Russell <rusty@rustcorp.com.au>]

On Tue, 2005-01-18 at 00:06 +0530, Ravikiran G Thirumalai wrote:
> Here's the alloc_percpu reimplementation changed to
> - Use qsort 
> - Use GFP_KERNEL|__GFP_HIGHMEM|__GFP_ZERO for BLOCK_MANAGEMENT_PAGES
>   (GFP_HIGHZERO would have been ideal)
> - Changed currency size to sizeof (int) from sizeof (void *) for better
>   utilization for small objects
> 
> The allocator can be easily modified to use __per_cpu_offset[] table at a later
> stage by: 
> 1. Allocating ALIGN(__per_cpu_end - __per_cpu_start, PAGE_SIZE) for the
>    static percpu areas and populating __per_cpu_offset[] offset table
> 2. Making PCPU_BLKSIZE same as the static per cpu area size above
> 3. Serving dynamic percpu requests from modules etc from blocks by
>    returning ret -= __per_cpu_offset[0] from a percpu block.  This way
>    modules need not have a limit on static percpu areas.

Unfortunately ia64 breaks (3).  They have pinned TLB entries covering
64k, which they put the static per-cpu data into.  This is used for
local_inc, etc, and David Mosberger loved that trick (this is why my
version allocated from that first reserved block for modules' static
per-cpu vars).

Hope that clarifies,
Rusty.
-- 
A bad analogy is like a leaky screwdriver -- Richard Braakman