Re: [PATCH V6 00/18] x86: Full support of PAT

[Juergen Gross <jgross@suse.com>]

Ingo,

could you take the patches, please?


Juergen

On 11/03/2014 02:01 PM, Juergen Gross wrote:
> The x86 architecture offers via the PAT (Page Attribute Table) a way to
> specify different caching modes in page table entries. The PAT MSR contains
> 8 entries each specifying one of 6 possible cache modes. A pte references one
> of those entries via 3 bits: _PAGE_PAT, _PAGE_PWT and _PAGE_PCD.
>
> The Linux kernel currently supports only 4 different cache modes. The PAT MSR
> is set up in a way that the setting of _PAGE_PAT in a pte doesn't matter: the
> top 4 entries in the PAT MSR are the same as the 4 lower entries.
>
> This results in the kernel not supporting e.g. write-through mode. Especially
> this cache mode would speed up drivers of video cards which now have to use
> uncached accesses.
>
> OTOH some old processors (Pentium) don't support PAT correctly and the Xen
> hypervisor has been using a different PAT MSR configuration for some time now
> and can't change that as this setting is part of the ABI.
>
> This patch set abstracts the cache mode from the pte and introduces tables to
> translate between cache mode and pte bits (the default cache mode "write back"
> is hard-wired to PAT entry 0). The tables are statically initialized with
> values being compatible to old processors and current usage. As soon as the
> PAT MSR is changed (or - in case of Xen - is read at boot time) the tables are
> changed accordingly. Requests of mappings with special cache modes are always
> possible now, in case they are not supported there will be a fallback to a
> compatible but slower mode.
>
> Summing it up, this patch set adds the following features:
> - capability to support WT and WP cache modes on processors with full PAT
>    support
> - processors with no or uncorrect PAT support are still working as today, even
>    if WT or WP cache mode are selected by drivers for some pages
> - reduction of Xen special handling regarding cache mode
>
> Changes in V6:
> - add new patch 10 (x86: Remove looking for setting of _PAGE_PAT_LARGE in
>    pageattr.c) as suggested by Thomas Gleixner
> - replaced SOB of Stefan Bader by "Based-on-patch-by:" as suggested by
>    Borislav Petkov
>
> Changes in V5:
> - split up first patch as requested by Ingo Molnar and Thomas Gleixner
> - add a helper function in pat_init_cache_modes() as requested by Ingo Molnar
>
> Changes in V4:
> - rebased to 3.18-rc2
>
> Changes in V3:
> - corrected two minor nits (UC_MINUS, again) detected by Toshi Kani
>
> Changes in V2:
> - simplified handling of PAT MSR write under Xen as suggested by David Vrabel
> - removed resetting of pat_enabled under Xen
> - two small corrections requested by Toshi Kani (UC_MINUS cache mode in
>    vermilion driver, fix 32 bit kernel build failure)
> - correct build error on non-x86 arch by moving definition of
>    update_cache_mode_entry() to x86 specific header
>
> Changes since RFC:
> - renamed functions and variables as suggested by Toshi Kani
> - corrected cache mode bits for WT and WP
> - modified handling of PAT MSR write under Xen as suggested by Jan Beulich
>
>
> Juergen Gross (18):
>    x86: Make page cache mode a real type
>    x86: Use new cache mode type in include/asm/fb.h
>    x86: Use new cache mode type in drivers/video/fbdev/gbefb.c
>    x86: Use new cache mode type in drivers/video/fbdev/vermilion
>    x86: Use new cache mode type in arch/x86/pci
>    x86: Use new cache mode type in arch/x86/mm/init_64.c
>    x86: Use new cache mode type in asm/pgtable.h
>    x86: Use new cache mode type in mm/iomap_32.c
>    x86: Use new cache mode type in track_pfn_remap() and
>      track_pfn_insert()
>    x86: Remove looking for setting of _PAGE_PAT_LARGE in pageattr.c
>    x86: Use new cache mode type in setting page attributes
>    x86: Use new cache mode type in mm/ioremap.c
>    x86: Use new cache mode type in memtype related functions
>    x86: Clean up pgtable_types.h
>    x86: Support PAT bit in pagetable dump for lower levels
>    x86: Respect PAT bit when copying pte values between large and normal
>      pages
>    x86: Enable PAT to use cache mode translation tables
>    xen: Support Xen pv-domains using PAT
>
>   arch/x86/include/asm/cacheflush.h         |  38 ++++---
>   arch/x86/include/asm/fb.h                 |   6 +-
>   arch/x86/include/asm/io.h                 |   2 +-
>   arch/x86/include/asm/pat.h                |   7 +-
>   arch/x86/include/asm/pgtable.h            |  19 ++--
>   arch/x86/include/asm/pgtable_types.h      |  96 ++++++++++++----
>   arch/x86/mm/dump_pagetables.c             |  24 ++--
>   arch/x86/mm/init.c                        |  37 +++++++
>   arch/x86/mm/init_64.c                     |   9 +-
>   arch/x86/mm/iomap_32.c                    |  12 +-
>   arch/x86/mm/ioremap.c                     |  63 ++++++-----
>   arch/x86/mm/mm_internal.h                 |   2 +
>   arch/x86/mm/pageattr.c                    |  84 ++++++++------
>   arch/x86/mm/pat.c                         | 176 +++++++++++++++++++-----------
>   arch/x86/mm/pat_internal.h                |  22 ++--
>   arch/x86/mm/pat_rbtree.c                  |   8 +-
>   arch/x86/pci/i386.c                       |   4 +-
>   arch/x86/xen/enlighten.c                  |  25 ++---
>   arch/x86/xen/mmu.c                        |  47 +-------
>   arch/x86/xen/xen-ops.h                    |   1 -
>   drivers/video/fbdev/gbefb.c               |   3 +-
>   drivers/video/fbdev/vermilion/vermilion.c |   6 +-
>   22 files changed, 412 insertions(+), 279 deletions(-)
>