Patchwork [v2] powerpc: add real mode support for dma operations on powernv

login
register
mail settings
Submitter Alexey Kardashevskiy
Date July 8, 2013, 4:44 a.m.
Message ID <1373258669-3130-1-git-send-email-aik@ozlabs.ru>
Download mbox | patch
Permalink /patch/257463/
State Superseded
Headers show

Comments

Alexey Kardashevskiy - July 8, 2013, 4:44 a.m.
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.

This new feature is going to be utilized by real mode support of VFIO.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
2013/08/07:
* tested on p7ioc and fixed a bug with realmode addresses

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/include/asm/machdep.h        | 12 +++++++++
 arch/powerpc/platforms/powernv/pci-ioda.c | 43 ++++++++++++++++++++++---------
 arch/powerpc/platforms/powernv/pci.c      | 38 ++++++++++++++++++++++-----
 arch/powerpc/platforms/powernv/pci.h      |  3 ++-
 4 files changed, 77 insertions(+), 19 deletions(-)
Benjamin Herrenschmidt - July 8, 2013, 7:20 a.m.
On Mon, 2013-07-08 at 14:44 +1000, Alexey Kardashevskiy wrote:

> diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
> index 25d76c4..7ea82c1 100644
> --- a/arch/powerpc/platforms/powernv/pci.h
> +++ b/arch/powerpc/platforms/powernv/pci.h
> @@ -52,6 +52,7 @@ struct pnv_ioda_pe {
>  	int			tce32_seg;
>  	int			tce32_segcount;
>  	struct iommu_table	tce32_table;
> +	phys_addr_t		it_index_rm;

Please ....

The fact that we hijack the it_index field of the iommu table
for the virtual address is bad enough, but really don't need
to perpetuate this :-)

Call the field something decent such as "tce_inval_reg_phys"

Cheers,
Ben.
Alexey Kardashevskiy - July 8, 2013, 7:31 a.m.
On 07/08/2013 05:20 PM, Benjamin Herrenschmidt wrote:
> On Mon, 2013-07-08 at 14:44 +1000, Alexey Kardashevskiy wrote:
> 
>> diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
>> index 25d76c4..7ea82c1 100644
>> --- a/arch/powerpc/platforms/powernv/pci.h
>> +++ b/arch/powerpc/platforms/powernv/pci.h
>> @@ -52,6 +52,7 @@ struct pnv_ioda_pe {
>>  	int			tce32_seg;
>>  	int			tce32_segcount;
>>  	struct iommu_table	tce32_table;
>> +	phys_addr_t		it_index_rm;
> 
> Please ....
> 
> The fact that we hijack the it_index field of the iommu table
> for the virtual address is bad enough, but really don't need
> to perpetuate this :-)
> 
> Call the field something decent such as "tce_inval_reg_phys"


Yes we can. I just find it veeeeeeery attractive when I can grep "\<it_"
and get all users of iommu_table.

btw is phys_addr_t correct here?
Benjamin Herrenschmidt - July 8, 2013, 7:40 a.m.
On Mon, 2013-07-08 at 17:31 +1000, Alexey Kardashevskiy wrote:

> btw is phys_addr_t correct here?

Yes.

Cheers,
Ben.

Patch

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 d200594..8a70003 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 __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
+{
+	__asm__ __volatile__("stdcix %0,0,%1"
+		: : "r" (val), "r" (paddr) : "memory");
+}
+
 static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
@@ -452,10 +458,13 @@  static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 	}
 }
 
-static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
-					 u64 *startp, u64 *endp)
+static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
+					 struct iommu_table *tbl,
+					 u64 *startp, u64 *endp, bool rm)
 {
-	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
+	u64 __iomem *invalidate = rm?
+		(u64 __iomem *)pe->it_index_rm:
+		(u64 __iomem *)tbl->it_index;
 	unsigned long start, end, inc;
 
 	start = __pa(startp);
@@ -482,7 +491,10 @@  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)
+			__raw_rm_writeq(start, invalidate);
+		else
+			__raw_writeq(start, invalidate);
                 start += inc;
         }
 
@@ -494,10 +506,12 @@  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;
+	u64 __iomem *invalidate = rm?
+		(u64 __iomem *)pe->it_index_rm:
+		(u64 __iomem *)tbl->it_index;
 
 	/* We'll invalidate DMA address in PE scope */
 	start = 0x2ul << 60;
@@ -513,22 +527,25 @@  static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 	mb();
 
 	while (start <= end) {
-		__raw_writeq(start, invalidate);
+		if (rm)
+			__raw_rm_writeq(start, invalidate);
+		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(pe, 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,
@@ -601,7 +618,8 @@  static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 		 * bus number, print that out instead.
 		 */
 		tbl->it_busno = 0;
-		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+		pe->it_index_rm = be64_to_cpup(swinvp);
+		tbl->it_index = (unsigned long)ioremap(pe->it_index_rm, 8);
 		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE |
 			       TCE_PCI_SWINV_PAIR;
 	}
@@ -679,7 +697,8 @@  static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		 * bus number, print that out instead.
 		 */
 		tbl->it_busno = 0;
-		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+		pe->it_index_rm = be64_to_cpup(swinvp);
+		tbl->it_index = (unsigned long)ioremap(pe->it_index_rm, 8);
 		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
 	}
 	iommu_init_table(tbl, phb->hose->node);
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..7ea82c1 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -52,6 +52,7 @@  struct pnv_ioda_pe {
 	int			tce32_seg;
 	int			tce32_segcount;
 	struct iommu_table	tce32_table;
+	phys_addr_t		it_index_rm;
 
 	/* XXX TODO: Add support for additional 64-bit iommus */
 
@@ -158,6 +159,6 @@  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 */