| Message ID | 1412941908-5850-6-git-send-email-stefano.stabellini@eu.citrix.com |
|---|---|
| State | New |
| Headers | show |
On Fri, Oct 10, 2014 at 12:51:47PM +0100, Stefano Stabellini wrote: > Introduce an arch specific function to find out whether a particular dma > mapping operation needs to bounce on the swiotlb buffer. > > On ARM and ARM64, if the page involved is a foreign page and the device > is not coherent, we need to bounce because at unmap time we cannot > execute any required cache maintenance operations (we don't know how to > find the pfn from the mfn). > > No change of behaviour for x86. > > Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> > --- > arch/arm/include/asm/xen/page.h | 4 ++++ > arch/arm/xen/mm.c | 7 +++++++ > arch/x86/include/asm/xen/page.h | 7 +++++++ > drivers/xen/swiotlb-xen.c | 5 ++++- > 4 files changed, 22 insertions(+), 1 deletion(-) > > diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h > index 135c24a..fb7839d 100644 > --- a/arch/arm/include/asm/xen/page.h > +++ b/arch/arm/include/asm/xen/page.h > @@ -107,4 +107,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) > #define xen_remap(cookie, size) ioremap_cache((cookie), (size)) > #define xen_unmap(cookie) iounmap((cookie)) > > +bool xen_arch_need_swiotlb(struct device *dev, > + unsigned long pfn, > + unsigned long mfn); > + > #endif /* _ASM_ARM_XEN_PAGE_H */ > diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c > index 9d460e0..0c2a75a 100644 > --- a/arch/arm/xen/mm.c > +++ b/arch/arm/xen/mm.c > @@ -139,6 +139,13 @@ void xen_dma_sync_single_for_device(struct device *hwdev, > __xen_dma_page_cpu_to_dev(hwdev, handle, size, dir); > } > > +bool xen_arch_need_swiotlb(struct device *dev, > + unsigned long pfn, > + unsigned long mfn) > +{ > + return ((pfn != mfn) && !is_dma_coherent(dev)); > +} > + > int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, > unsigned int address_bits, > dma_addr_t *dma_handle) > diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h > index c949923..0a45242 100644 > --- a/arch/x86/include/asm/xen/page.h > +++ b/arch/x86/include/asm/xen/page.h > @@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *vaddr); > #define xen_remap(cookie, size) ioremap((cookie), (size)); > #define xen_unmap(cookie) iounmap((cookie)) > > +static inline bool xen_arch_need_swiotlb(struct device *dev, > + unsigned long pfn, > + unsigned long mfn) Something funny happend here. > +{ > + return false; > +} Why not make this an macro? The xen_unmap and xen_remap are that. > + > #endif /* _ASM_X86_XEN_PAGE_H */ > diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c > index ebd8f21..ac0bd60 100644 > --- a/drivers/xen/swiotlb-xen.c > +++ b/drivers/xen/swiotlb-xen.c > @@ -399,7 +399,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, > * buffering it. > */ > if (dma_capable(dev, dev_addr, size) && > - !range_straddles_page_boundary(phys, size) && !swiotlb_force) { > + !range_straddles_page_boundary(phys, size) && > + !xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) && > + !swiotlb_force) { > /* we are not interested in the dma_addr returned by > * xen_dma_map_page, only in the potential cache flushes executed > * by the function. */ > @@ -557,6 +559,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, > dma_addr_t dev_addr = xen_phys_to_bus(paddr); > > if (swiotlb_force || > + xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) || > !dma_capable(hwdev, dev_addr, sg->length) || > range_straddles_page_boundary(paddr, sg->length)) { > phys_addr_t map = swiotlb_tbl_map_single(hwdev, > -- > 1.7.10.4 > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
On 14/10/14 17:03, Konrad Rzeszutek Wilk wrote: > On Fri, Oct 10, 2014 at 12:51:47PM +0100, Stefano Stabellini wrote: >> Introduce an arch specific function to find out whether a particular dma >> mapping operation needs to bounce on the swiotlb buffer. >> >> On ARM and ARM64, if the page involved is a foreign page and the device >> is not coherent, we need to bounce because at unmap time we cannot >> execute any required cache maintenance operations (we don't know how to >> find the pfn from the mfn). ... >> --- a/arch/x86/include/asm/xen/page.h >> +++ b/arch/x86/include/asm/xen/page.h >> @@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *vaddr); >> #define xen_remap(cookie, size) ioremap((cookie), (size)); >> #define xen_unmap(cookie) iounmap((cookie)) >> >> +static inline bool xen_arch_need_swiotlb(struct device *dev, >> + unsigned long pfn, >> + unsigned long mfn) >> +{ >> + return false; >> +} > > Why not make this an macro? Because macros are evil and inline functions are preferred. David -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
On Tue, Oct 14, 2014 at 05:12:12PM +0100, David Vrabel wrote: > On 14/10/14 17:03, Konrad Rzeszutek Wilk wrote: > > On Fri, Oct 10, 2014 at 12:51:47PM +0100, Stefano Stabellini wrote: > >> Introduce an arch specific function to find out whether a particular dma > >> mapping operation needs to bounce on the swiotlb buffer. > >> > >> On ARM and ARM64, if the page involved is a foreign page and the device > >> is not coherent, we need to bounce because at unmap time we cannot > >> execute any required cache maintenance operations (we don't know how to > >> find the pfn from the mfn). > ... > >> --- a/arch/x86/include/asm/xen/page.h > >> +++ b/arch/x86/include/asm/xen/page.h > >> @@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *vaddr); > >> #define xen_remap(cookie, size) ioremap((cookie), (size)); > >> #define xen_unmap(cookie) iounmap((cookie)) > >> > >> +static inline bool xen_arch_need_swiotlb(struct device *dev, > >> + unsigned long pfn, > >> + unsigned long mfn) > >> +{ > >> + return false; > >> +} > > > > Why not make this an macro? > > Because macros are evil and inline functions are preferred. <laughs> Fair enough. > > David
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 135c24a..fb7839d 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -107,4 +107,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) #define xen_remap(cookie, size) ioremap_cache((cookie), (size)) #define xen_unmap(cookie) iounmap((cookie)) +bool xen_arch_need_swiotlb(struct device *dev, + unsigned long pfn, + unsigned long mfn); + #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 9d460e0..0c2a75a 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -139,6 +139,13 @@ void xen_dma_sync_single_for_device(struct device *hwdev, __xen_dma_page_cpu_to_dev(hwdev, handle, size, dir); } +bool xen_arch_need_swiotlb(struct device *dev, + unsigned long pfn, + unsigned long mfn) +{ + return ((pfn != mfn) && !is_dma_coherent(dev)); +} + int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index c949923..0a45242 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *vaddr); #define xen_remap(cookie, size) ioremap((cookie), (size)); #define xen_unmap(cookie) iounmap((cookie)) +static inline bool xen_arch_need_swiotlb(struct device *dev, + unsigned long pfn, + unsigned long mfn) +{ + return false; +} + #endif /* _ASM_X86_XEN_PAGE_H */ diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index ebd8f21..ac0bd60 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -399,7 +399,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * buffering it. */ if (dma_capable(dev, dev_addr, size) && - !range_straddles_page_boundary(phys, size) && !swiotlb_force) { + !range_straddles_page_boundary(phys, size) && + !xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) && + !swiotlb_force) { /* we are not interested in the dma_addr returned by * xen_dma_map_page, only in the potential cache flushes executed * by the function. */ @@ -557,6 +559,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, dma_addr_t dev_addr = xen_phys_to_bus(paddr); if (swiotlb_force || + xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) || !dma_capable(hwdev, dev_addr, sg->length) || range_straddles_page_boundary(paddr, sg->length)) { phys_addr_t map = swiotlb_tbl_map_single(hwdev,
Introduce an arch specific function to find out whether a particular dma mapping operation needs to bounce on the swiotlb buffer. On ARM and ARM64, if the page involved is a foreign page and the device is not coherent, we need to bounce because at unmap time we cannot execute any required cache maintenance operations (we don't know how to find the pfn from the mfn). No change of behaviour for x86. Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> --- arch/arm/include/asm/xen/page.h | 4 ++++ arch/arm/xen/mm.c | 7 +++++++ arch/x86/include/asm/xen/page.h | 7 +++++++ drivers/xen/swiotlb-xen.c | 5 ++++- 4 files changed, 22 insertions(+), 1 deletion(-)