LKML Archive on
help / color / mirror / Atom feed
From: Andi Kleen <>
Subject: [PATCH] [0/8] GB pages (PDP1GB) support for the kernel direct mapping
Date: Thu,  3 Jan 2008 18:26:56 +0100 (CET)	[thread overview]
Message-ID: <> (raw)

This patchkit implement GB pages support for AMD Fam10h CPUs. This patchkit only
implements it for the kernel direct mapping for now; support for hugetlbfs is upcomming.

This allows to map the kernel direct mapping using 1GB TLBs instead of 2MB 
TLBs and get hopefully less TLB misses for the kernel.

The GB pages are only implemented for 64bit (because the CPU only implements
them for long mode) and also only for data pages (because Fam10h doesn't have GB ITLBs
and AMD recommends against running code in them) 

There is an option to turn them off (direct_gbpages=off), although I hope that
won't be needed.

Also includes one generic bug fix for clear_page_kernel.


             reply	other threads:[~2008-01-03 17:27 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-01-03 17:26 Andi Kleen [this message]
2008-01-03 17:26 ` [PATCH] [1/8] GBPAGES: Handle kernel near memory hole in clear_kernel_mapping Andi Kleen
2008-01-03 18:29   ` Vivek Goyal
2008-01-03 18:43     ` Andi Kleen
2008-01-03 17:26 ` [PATCH] [2/8] GBPAGES: Add feature macros for the gbpages cpuid bit Andi Kleen
2008-01-03 17:26 ` [PATCH] [3/8] GBPAGES: Split LARGE_PAGE_SIZE/MASK into PUD_PAGE_SIZE/PMD_PAGE_SIZE Andi Kleen
2008-01-03 17:27 ` [PATCH] [4/8] GBPAGES: Add pgtable accessor functions for GB pages Andi Kleen
2008-01-03 17:27 ` [PATCH] [5/8] GBPAGES: Support gbpages in pagetable dump Andi Kleen
2008-01-03 17:27 ` [PATCH] [6/8] GBPAGES: Add an option to disable direct mapping gbpages and a global variable Andi Kleen
2008-01-03 19:03   ` Nish Aravamudan
2008-01-03 17:27 ` [PATCH] [7/8] GBPAGES: Implement GBpages support in change_page_attr() Andi Kleen
2008-01-03 17:27 ` [PATCH] [8/8] GBPAGES: Do kernel direct mapping at boot using GB pages Andi Kleen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).