On Fri, 2015-06-19 at 15:08 -0700, Luis R. Rodriguez wrote:
> From: "Luis R. Rodriguez" <mcg...@suse.com>
>
> PCI BARs tell us whether prefetching is safe, but they don't say anything
> about write combining (WC). WC changes ordering rules and allows writes to
> be collapsed, so it's not safe in general to use it on a prefetchable
> region.
Well, the PCIe spec at least specifies that a prefetchable BAR also
tolerates write merging...
> Add pci_iomap_wc() and pci_iomap_wc_range() so drivers can take advantage
> of write combining when they know it's safe.
>
> On architectures that don't fully support WC, e.g., x86 without PAT,
> drivers for legacy framebuffers may get some of the benefit by using
> arch_phys_wc_add() in addition to pci_iomap_wc(). But arch_phys_wc_add()
> is unreliable and should be avoided in general. On x86, it uses MTRRs,
> which are limited in number and size, so the results will vary based on
> driver loading order.
>
> The goals of adding pci_iomap_wc() are to:
>
> - Give drivers an architecture-independent way to use WC so they can stop
> using interfaces like mtrr_add() (on x86, pci_iomap_wc() uses
> PAT when available)
>
> - Move toward using _PAGE_CACHE_MODE_UC, not _PAGE_CACHE_MODE_UC_MINUS,
> on x86 on ioremap_nocache() (see de33c442ed2a ("x86 PAT: fix
> performance drop for glx, use UC minus for ioremap(), ioremap_nocache()
> and pci_mmap_page_range()")
>
> Link:
> http://lkml.kernel.org/r/1426893517-2511-6-git-send-email-mcg...@do-not-panic.com
> Original-posting:
> http://lkml.kernel.org/r/1432163293-20965-1-git-send-email-mcg...@do-not-panic.com
> Cc: Toshi Kani <toshi.k...@hp.com>
> Cc: Andy Lutomirski <l...@amacapital.net>
> Cc: Suresh Siddha <sbsid...@gmail.com>
> Cc: Ingo Molnar <mi...@elte.hu>
> Cc: Thomas Gleixner <t...@linutronix.de>
> Cc: Juergen Gross <jgr...@suse.com>
> Cc: Daniel Vetter <daniel.vet...@ffwll.ch>
> Cc: Dave Airlie <airl...@redhat.com>
> Cc: Bjorn Helgaas <bhelg...@google.com>
> Cc: Antonino Daplas <adap...@gmail.com>
> Cc: Jean-Christophe Plagniol-Villard <plagn...@jcrosoft.com>
> Cc: Tomi Valkeinen <tomi.valkei...@ti.com>
> Cc: Dave Hansen <dave.han...@linux.intel.com>
> Cc: Arnd Bergmann <a...@arndb.de>
> Cc: Michael S. Tsirkin <m...@redhat.com>
> Cc: venkatesh.pallip...@intel.com
> Cc: Stefan Bader <stefan.ba...@canonical.com>
> Cc: Ville Syrjälä <syrj...@sci.fi>
> Cc: Mel Gorman <mgor...@suse.de>
> Cc: Vlastimil Babka <vba...@suse.cz>
> Cc: Borislav Petkov <b...@suse.de>
> Cc: Davidlohr Bueso <dbu...@suse.de>
> Cc: konrad.w...@oracle.com
> Cc: ville.syrj...@linux.intel.com
> Cc: david.vra...@citrix.com
> Cc: jbeul...@suse.com
> Cc: Roger Pau Monné <roger....@citrix.com>
> Cc: linux-fb...@vger.kernel.org
> Cc: linux-ker...@vger.kernel.org
> Cc: xen-de...@lists.xensource.com
> Signed-off-by: Luis R. Rodriguez <mcg...@suse.com>
> ---
> include/asm-generic/pci_iomap.h | 14 ++++++++++
> lib/pci_iomap.c | 61
> +++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 75 insertions(+)
>
> diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
> index 7389c87..b1e17fc 100644
> --- a/include/asm-generic/pci_iomap.h
> +++ b/include/asm-generic/pci_iomap.h
> @@ -15,9 +15,13 @@ struct pci_dev;
> #ifdef CONFIG_PCI
> /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
> extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long
> max);
> +extern void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned
> long max);
> extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
> unsigned long offset,
> unsigned long maxlen);
> +extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
> + unsigned long offset,
> + unsigned long maxlen);
> /* Create a virtual mapping cookie for a port on a given PCI device.
> * Do not call this directly, it exists to make it easier for architectures
> * to override */
> @@ -34,12 +38,22 @@ static inline void __iomem *pci_iomap(struct pci_dev
> *dev, int bar, unsigned lon
> return NULL;
> }
>
> +static inline void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar,
> unsigned long max)
> +{
> + return NULL;
> +}
> static inline void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
> unsigned long offset,
> unsigned long maxlen)
> {
> return NULL;
> }
> +static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
> + unsigned long offset,
> + unsigned long maxlen)
> +{
> + return NULL;
> +}
> #endif
>
> #endif /* __ASM_GENERIC_IO_H */
> diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
> index bcce5f1..9604dcb 100644
> --- a/lib/pci_iomap.c
> +++ b/lib/pci_iomap.c
> @@ -52,6 +52,46 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
> EXPORT_SYMBOL(pci_iomap_range);
>
> /**
> + * pci_iomap_wc_range - create a virtual WC mapping cookie for a PCI BAR
> + * @dev: PCI device that owns the BAR
> + * @bar: BAR number
> + * @offset: map memory at the given offset in BAR
> + * @maxlen: max length of the memory to map
> + *
> + * Using this function you will get a __iomem address to your device BAR.
> + * You can access it using ioread*() and iowrite*(). These functions hide
> + * the details if this is a MMIO or PIO address space and will just do what
> + * you expect from them in the correct way. When possible write combining
> + * is used.
> + *
> + * @maxlen specifies the maximum length to map. If you want to get access to
> + * the complete BAR from offset to the end, pass %0 here.
> + * */
> +void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
> + int bar,
> + unsigned long offset,
> + unsigned long maxlen)
> +{
> + resource_size_t start = pci_resource_start(dev, bar);
> + resource_size_t len = pci_resource_len(dev, bar);
> + unsigned long flags = pci_resource_flags(dev, bar);
> +
> + if (len <= offset || !start)
> + return NULL;
> + len -= offset;
> + start += offset;
> + if (maxlen && len > maxlen)
> + len = maxlen;
> + if (flags & IORESOURCE_IO)
> + return NULL;
> + if (flags & IORESOURCE_MEM)
> + return ioremap_wc(start, len);
> + /* What? */
> + return NULL;
> +}
> +EXPORT_SYMBOL_GPL(pci_iomap_wc_range);
> +
> +/**
> * pci_iomap - create a virtual mapping cookie for a PCI BAR
> * @dev: PCI device that owns the BAR
> * @bar: BAR number
> @@ -70,4 +110,25 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar,
> unsigned long maxlen)
> return pci_iomap_range(dev, bar, 0, maxlen);
> }
> EXPORT_SYMBOL(pci_iomap);
> +
> +/**
> + * pci_iomap_wc - create a virtual WC mapping cookie for a PCI BAR
> + * @dev: PCI device that owns the BAR
> + * @bar: BAR number
> + * @maxlen: length of the memory to map
> + *
> + * Using this function you will get a __iomem address to your device BAR.
> + * You can access it using ioread*() and iowrite*(). These functions hide
> + * the details if this is a MMIO or PIO address space and will just do what
> + * you expect from them in the correct way. When possible write combining
> + * is used.
> + *
> + * @maxlen specifies the maximum length to map. If you want to get access to
> + * the complete BAR without checking for its length first, pass %0 here.
> + * */
> +void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long
> maxlen)
> +{
> + return pci_iomap_wc_range(dev, bar, 0, maxlen);
> +}
> +EXPORT_SYMBOL_GPL(pci_iomap_wc);
> #endif /* CONFIG_PCI */
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
