Re: [PATCH kernel v10 20/34] powerpc/powernv/ioda2: Move TCE kill register address to PE

[Gavin Shan]

On Tue, May 12, 2015 at 01:39:09AM +1000, Alexey Kardashevskiy wrote:
>At the moment the DMA setup code looks for the "ibm,opal-tce-kill" property
>which contains the TCE kill register address. Writes to this register
>invalidates TCE cache on IODA/IODA2 hub.
>
>This moves the register address from iommu_table to pnv_ioda_pe as:
>1) When we get 2 tables per PE, this register will be used for both tables;
>2) When we get TCE tables sharing, we will need to invalidate every
>IOMMU group (i.e. PE) which is using this table and each PE has
>its own invalidate register.
>

Actually, it's the virtual address of IO remapped PHB hardware register.
So it would be a property of PHB (struct pnv_phb). As the PE is connecting
with IOMMU table group. The virtual address can be retrieved by the path:
iommu_table -> iommu_table_group -> pnv_ioda_pe -> pnv_phb. However, I
don't insist and you have the best judge on it :-)

>This moves the property reading/remapping code to a helper to reduce
>code duplication. Although this change is not required for IODA1, this
>changes it as well to reduce code duplication.
>
>This adds a new pnv_pci_ioda2_tvt_invalidate() helper which invalidates
>the entire table. It should be called after every call to
>opal_pci_map_pe_dma_window(). It was not required before because
>there is just a single TCE table and 64bit DMA is handled via bypass
>window (which has no table so no chache is used) but this is going
>to change with Dynamic DMA windows (DDW).
>
>Signed-off-by: Alexey Kardashevskiy <aik@xxxxxxxxx>

Reviewed-by: Gavin Shan <gwshan@xxxxxxxxxxxxxxxxxx>

Thanks,
Gavin

>---
>Changes:
>v10:
>* fixed error from checkpatch.pl
>* removed comment at "ibm,opal-tce-kill" parsing as irrelevant
>* s/addr/val/ in pnv_pci_ioda2_tvt_invalidate() as it was not a kernel address
>
>v9:
>* new in the series
>---
> arch/powerpc/platforms/powernv/pci-ioda.c | 64 ++++++++++++++++++-------------
> arch/powerpc/platforms/powernv/pci.h      |  1 +
> 2 files changed, 39 insertions(+), 26 deletions(-)
>
>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
>index 35ab19c8..f972e40 100644
>--- a/arch/powerpc/platforms/powernv/pci-ioda.c
>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
>@@ -1680,7 +1680,7 @@ static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
> 			struct pnv_ioda_pe, table_group);
> 	__be64 __iomem *invalidate = rm ?
> 		(__be64 __iomem *)pe->tce_inval_reg_phys :
>-		(__be64 __iomem *)tbl->it_index;
>+		pe->tce_inval_reg;
> 	unsigned long start, end, inc;
> 	const unsigned shift = tbl->it_page_shift;
>
>@@ -1751,6 +1751,18 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
> 	.get = pnv_tce_get,
> };
>
>+static inline void pnv_pci_ioda2_tvt_invalidate(struct pnv_ioda_pe *pe)
>+{
>+	/* 01xb - invalidate TCEs that match the specified PE# */
>+	unsigned long val = (0x4ull << 60) | (pe->pe_number & 0xFF);
>+
>+	if (!pe->tce_inval_reg)
>+		return;
>+
>+	mb(); /* Ensure above stores are visible */
>+	__raw_writeq(cpu_to_be64(val), pe->tce_inval_reg);
>+}
>+

The function name sounds it's to invalidate TVE cache. Actually, it's invalidting
TCE cache. So I guess the function name pnv_pci_ioda2_tce_invalidate() would be
more accurate.

> static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
> 		unsigned long index, unsigned long npages, bool rm)
> {
>@@ -1762,7 +1774,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
> 	unsigned long start, end, inc;
> 	__be64 __iomem *invalidate = rm ?
> 		(__be64 __iomem *)pe->tce_inval_reg_phys :
>-		(__be64 __iomem *)tbl->it_index;
>+		pe->tce_inval_reg;
> 	const unsigned shift = tbl->it_page_shift;
>
> 	/* We'll invalidate DMA address in PE scope */
>@@ -1814,13 +1826,26 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = {
> 	.get = pnv_tce_get,
> };
>
>+static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb,
>+		struct pnv_ioda_pe *pe)
>+{
>+	const __be64 *swinvp;
>+
>+	/* OPAL variant of PHB3 invalidated TCEs */
>+	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
>+	if (!swinvp)
>+		return;
>+
>+	pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
>+	pe->tce_inval_reg = ioremap(pe->tce_inval_reg_phys, 8);
>+}
>+

Yeah, nice to have the helper function to initialize it :)

> static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
> 				      struct pnv_ioda_pe *pe, unsigned int base,
> 				      unsigned int segs)
> {
>
> 	struct page *tce_mem = NULL;
>-	const __be64 *swinvp;
> 	struct iommu_table *tbl;
> 	unsigned int i;
> 	int64_t rc;
>@@ -1839,6 +1864,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
> 			pe->pe_number);
> 	pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
>
>+	pnv_pci_ioda_setup_opal_tce_kill(phb, pe);
>+
> 	/* Grab a 32-bit TCE table */
> 	pe->tce32_seg = base;
> 	pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
>@@ -1877,20 +1904,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
> 				  base << 28, IOMMU_PAGE_SHIFT_4K);
>
> 	/* OPAL variant of P7IOC SW invalidated TCEs */
>-	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
>-	if (swinvp) {
>-		/* We need a couple more fields -- an address and a data
>-		 * to or.  Since the bus is only printed out on table free
>-		 * errors, and on the first pass the data will be a relative
>-		 * bus number, print that out instead.
>-		 */
>-		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
>-		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
>-				8);
>+	if (pe->tce_inval_reg)
> 		tbl->it_type |= (TCE_PCI_SWINV_CREATE |
> 				 TCE_PCI_SWINV_FREE   |
> 				 TCE_PCI_SWINV_PAIR);
>-	}
>+
> 	tbl->it_ops = &pnv_ioda1_iommu_ops;
> 	iommu_init_table(tbl, phb->hose->node);
>
>@@ -1976,7 +1994,6 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
> {
> 	struct page *tce_mem = NULL;
> 	void *addr;
>-	const __be64 *swinvp;
> 	struct iommu_table *tbl;
> 	unsigned int tce_table_size, end;
> 	int64_t rc;
>@@ -1993,6 +2010,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
> 			pe->pe_number);
> 	pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
>
>+	pnv_pci_ioda_setup_opal_tce_kill(phb, pe);
>+
> 	/* The PE will reserve all possible 32-bits space */
> 	pe->tce32_seg = 0;
> 	end = (1 << ilog2(phb->ioda.m32_pci_base));
>@@ -2023,23 +2042,16 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
> 		goto fail;
> 	}
>
>+	pnv_pci_ioda2_tvt_invalidate(pe);
>+
> 	/* Setup linux iommu table */
> 	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
> 			IOMMU_PAGE_SHIFT_4K);
>
> 	/* OPAL variant of PHB3 invalidated TCEs */
>-	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
>-	if (swinvp) {
>-		/* We need a couple more fields -- an address and a data
>-		 * to or.  Since the bus is only printed out on table free
>-		 * errors, and on the first pass the data will be a relative
>-		 * bus number, print that out instead.
>-		 */
>-		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
>-		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
>-				8);
>+	if (pe->tce_inval_reg)
> 		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
>-	}
>+
> 	tbl->it_ops = &pnv_ioda2_iommu_ops;
> 	iommu_init_table(tbl, phb->hose->node);
> #ifdef CONFIG_IOMMU_API
>diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
>index 87bdd4f..ea97de5 100644
>--- a/arch/powerpc/platforms/powernv/pci.h
>+++ b/arch/powerpc/platforms/powernv/pci.h
>@@ -59,6 +59,7 @@ struct pnv_ioda_pe {
> 	int			tce32_segcount;
> 	struct iommu_table_group table_group;
> 	phys_addr_t		tce_inval_reg_phys;
>+	__be64 __iomem		*tce_inval_reg;
>
> 	/* 64-bit TCE bypass region */
> 	bool			tce_bypass_enabled;
>-- 
>2.4.0.rc3.8.gfb3e7d5
>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/