Re: [PATCH 5/8] powerpc: add real mode support for dma operations on powernv

[Benjamin Herrenschmidt <benh@kernel.crashing.org>]

On Tue, 2013-07-09 at 18:02 +0200, Alexander Graf wrote:
> On 07/06/2013 05:07 PM, Alexey Kardashevskiy wrote:
> > The existing TCE machine calls (tce_build and tce_free) only support
> > virtual mode as they call __raw_writeq for TCE invalidation what
> > fails in real mode.
> >
> > This introduces tce_build_rm and tce_free_rm real mode versions
> > which do mostly the same but use "Store Doubleword Caching Inhibited
> > Indexed" instruction for TCE invalidation.
> 
> So would always using stdcix have any bad side effects?

Yes. Those instructions are only supposed to be used in hypervisor real
mode as per the architecture spec.

Cheers,
Ben.

> 
> Alex
> 
> >
> > This new feature is going to be utilized by real mode support of VFIO.
> >
> > Signed-off-by: Alexey Kardashevskiy<aik@ozlabs.ru>
> > ---
> >   arch/powerpc/include/asm/machdep.h        | 12 ++++++++++
> >   arch/powerpc/platforms/powernv/pci-ioda.c | 26 +++++++++++++++------
> >   arch/powerpc/platforms/powernv/pci.c      | 38 ++++++++++++++++++++++++++-----
> >   arch/powerpc/platforms/powernv/pci.h      |  2 +-
> >   4 files changed, 64 insertions(+), 14 deletions(-)
> >
> > diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
> > index 92386fc..0c19eef 100644
> > --- a/arch/powerpc/include/asm/machdep.h
> > +++ b/arch/powerpc/include/asm/machdep.h
> > @@ -75,6 +75,18 @@ struct machdep_calls {
> >   				    long index);
> >   	void		(*tce_flush)(struct iommu_table *tbl);
> >
> > +	/* _rm versions are for real mode use only */
> > +	int		(*tce_build_rm)(struct iommu_table *tbl,
> > +				     long index,
> > +				     long npages,
> > +				     unsigned long uaddr,
> > +				     enum dma_data_direction direction,
> > +				     struct dma_attrs *attrs);
> > +	void		(*tce_free_rm)(struct iommu_table *tbl,
> > +				    long index,
> > +				    long npages);
> > +	void		(*tce_flush_rm)(struct iommu_table *tbl);
> > +
> >   	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
> >   				   unsigned long flags, void *caller);
> >   	void		(*iounmap)(volatile void __iomem *token);
> > diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> > index 2931d97..2797dec 100644
> > --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> > +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> > @@ -68,6 +68,12 @@ define_pe_printk_level(pe_err, KERN_ERR);
> >   define_pe_printk_level(pe_warn, KERN_WARNING);
> >   define_pe_printk_level(pe_info, KERN_INFO);
> >
> > +static inline void rm_writed(unsigned long paddr, u64 val)
> > +{
> > +	__asm__ __volatile__("sync; stdcix %0,0,%1"
> > +		: : "r" (val), "r" (paddr) : "memory");
> > +}
> > +
> >   static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
> >   {
> >   	unsigned long pe;
> > @@ -442,7 +448,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
> >   }
> >
> >   static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
> > -					 u64 *startp, u64 *endp)
> > +					 u64 *startp, u64 *endp, bool rm)
> >   {
> >   	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
> >   	unsigned long start, end, inc;
> > @@ -471,7 +477,10 @@ static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
> >
> >           mb(); /* Ensure above stores are visible */
> >           while (start<= end) {
> > -                __raw_writeq(start, invalidate);
> > +		if (rm)
> > +			rm_writed((unsigned long) invalidate, start);
> > +		else
> > +			__raw_writeq(start, invalidate);
> >                   start += inc;
> >           }
> >
> > @@ -483,7 +492,7 @@ static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
> >
> >   static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
> >   					 struct iommu_table *tbl,
> > -					 u64 *startp, u64 *endp)
> > +					 u64 *startp, u64 *endp, bool rm)
> >   {
> >   	unsigned long start, end, inc;
> >   	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
> > @@ -502,22 +511,25 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
> >   	mb();
> >
> >   	while (start<= end) {
> > -		__raw_writeq(start, invalidate);
> > +		if (rm)
> > +			rm_writed((unsigned long) invalidate, start);
> > +		else
> > +			__raw_writeq(start, invalidate);
> >   		start += inc;
> >   	}
> >   }
> >
> >   void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
> > -				 u64 *startp, u64 *endp)
> > +				 u64 *startp, u64 *endp, bool rm)
> >   {
> >   	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
> >   					      tce32_table);
> >   	struct pnv_phb *phb = pe->phb;
> >
> >   	if (phb->type == PNV_PHB_IODA1)
> > -		pnv_pci_ioda1_tce_invalidate(tbl, startp, endp);
> > +		pnv_pci_ioda1_tce_invalidate(tbl, startp, endp, rm);
> >   	else
> > -		pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp);
> > +		pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp, rm);
> >   }
> >
> >   static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
> > diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
> > index e16b729..280f614 100644
> > --- a/arch/powerpc/platforms/powernv/pci.c
> > +++ b/arch/powerpc/platforms/powernv/pci.c
> > @@ -336,7 +336,7 @@ struct pci_ops pnv_pci_ops = {
> >
> >   static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
> >   			 unsigned long uaddr, enum dma_data_direction direction,
> > -			 struct dma_attrs *attrs)
> > +			 struct dma_attrs *attrs, bool rm)
> >   {
> >   	u64 proto_tce;
> >   	u64 *tcep, *tces;
> > @@ -358,12 +358,19 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
> >   	 * of flags if that becomes the case
> >   	 */
> >   	if (tbl->it_type&  TCE_PCI_SWINV_CREATE)
> > -		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
> > +		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
> >
> >   	return 0;
> >   }
> >
> > -static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
> > +static int pnv_tce_build_vm(struct iommu_table *tbl, long index, long npages,
> > +			    unsigned long uaddr, enum dma_data_direction direction,
> > +			    struct dma_attrs *attrs)
> > +{
> > +	return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, false);
> > +}
> > +
> > +static void pnv_tce_free(struct iommu_table *tbl, long index, long npages, bool rm)
> >   {
> >   	u64 *tcep, *tces;
> >
> > @@ -373,7 +380,12 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
> >   		*(tcep++) = 0;
> >
> >   	if (tbl->it_type&  TCE_PCI_SWINV_FREE)
> > -		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
> > +		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
> > +}
> > +
> > +static void pnv_tce_free_vm(struct iommu_table *tbl, long index, long npages)
> > +{
> > +	pnv_tce_free(tbl, index, npages, false);
> >   }
> >
> >   static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
> > @@ -381,6 +393,18 @@ static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
> >   	return ((u64 *)tbl->it_base)[index - tbl->it_offset];
> >   }
> >
> > +static int pnv_tce_build_rm(struct iommu_table *tbl, long index, long npages,
> > +			    unsigned long uaddr, enum dma_data_direction direction,
> > +			    struct dma_attrs *attrs)
> > +{
> > +	return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, true);
> > +}
> > +
> > +static void pnv_tce_free_rm(struct iommu_table *tbl, long index, long npages)
> > +{
> > +	pnv_tce_free(tbl, index, npages, true);
> > +}
> > +
> >   void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
> >   			       void *tce_mem, u64 tce_size,
> >   			       u64 dma_offset)
> > @@ -545,8 +569,10 @@ void __init pnv_pci_init(void)
> >
> >   	/* Configure IOMMU DMA hooks */
> >   	ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup;
> > -	ppc_md.tce_build = pnv_tce_build;
> > -	ppc_md.tce_free = pnv_tce_free;
> > +	ppc_md.tce_build = pnv_tce_build_vm;
> > +	ppc_md.tce_free = pnv_tce_free_vm;
> > +	ppc_md.tce_build_rm = pnv_tce_build_rm;
> > +	ppc_md.tce_free_rm = pnv_tce_free_rm;
> >   	ppc_md.tce_get = pnv_tce_get;
> >   	ppc_md.pci_probe_mode = pnv_pci_probe_mode;
> >   	set_pci_dma_ops(&dma_iommu_ops);
> > diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
> > index 25d76c4..6799374 100644
> > --- a/arch/powerpc/platforms/powernv/pci.h
> > +++ b/arch/powerpc/platforms/powernv/pci.h
> > @@ -158,6 +158,6 @@ extern void pnv_pci_init_p5ioc2_hub(struct device_node *np);
> >   extern void pnv_pci_init_ioda_hub(struct device_node *np);
> >   extern void pnv_pci_init_ioda2_phb(struct device_node *np);
> >   extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
> > -					u64 *startp, u64 *endp);
> > +					u64 *startp, u64 *endp, bool rm);
> >
> >   #endif /* __POWERNV_PCI_H */