From da004c3600f52e4f05017f60970e5010978006bc Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Fri, 5 Jun 2015 16:35:06 +1000 Subject: powerpc/iommu: Move tce_xxx callbacks from ppc_md to iommu_table This adds a iommu_table_ops struct and puts pointer to it into the iommu_table struct. This moves tce_build/tce_free/tce_get/tce_flush callbacks from ppc_md to the new struct where they really belong to. This adds the requirement for @it_ops to be initialized before calling iommu_init_table() to make sure that we do not leave any IOMMU table with iommu_table_ops uninitialized. This is not a parameter of iommu_init_table() though as there will be cases when iommu_init_table() will not be called on TCE tables, for example - VFIO. This does s/tce_build/set/, s/tce_free/clear/ and removes "tce_" redundant prefixes. This removes tce_xxx_rm handlers from ppc_md but does not add them to iommu_table_ops as this will be done later if we decide to support TCE hypercalls in real mode. This removes _vm callbacks as only virtual mode is supported by now so this also removes @rm parameter. For pSeries, this always uses tce_buildmulti_pSeriesLP/ tce_buildmulti_pSeriesLP. This changes multi callback to fall back to tce_build_pSeriesLP/tce_free_pSeriesLP if FW_FEATURE_MULTITCE is not present. The reason for this is we still have to support "multitce=off" boot parameter in disable_multitce() and we do not want to walk through all IOMMU tables in the system and replace "multi" callbacks with single ones. For powernv, this defines _ops per PHB type which are P5IOC2/IODA1/IODA2. This makes the callbacks for them public. Later patches will extend callbacks for IODA1/2. No change in behaviour is expected. Signed-off-by: Alexey Kardashevskiy Reviewed-by: David Gibson Reviewed-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/iommu.c | 46 +++++++++++++++++++++++---------------------- arch/powerpc/kernel/vio.c | 5 +++++ 2 files changed, 29 insertions(+), 22 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index ac2f959adf9a..c0e67e945c95 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -322,11 +322,11 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, ret = entry << tbl->it_page_shift; /* Set the return dma address */ /* Put the TCEs in the HW table */ - build_fail = ppc_md.tce_build(tbl, entry, npages, + build_fail = tbl->it_ops->set(tbl, entry, npages, (unsigned long)page & IOMMU_PAGE_MASK(tbl), direction, attrs); - /* ppc_md.tce_build() only returns non-zero for transient errors. + /* tbl->it_ops->set() only returns non-zero for transient errors. * Clean up the table bitmap in this case and return * DMA_ERROR_CODE. For all other errors the functionality is * not altered. @@ -337,8 +337,8 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, } /* Flush/invalidate TLB caches if necessary */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); + if (tbl->it_ops->flush) + tbl->it_ops->flush(tbl); /* Make sure updates are seen by hardware */ mb(); @@ -408,7 +408,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, if (!iommu_free_check(tbl, dma_addr, npages)) return; - ppc_md.tce_free(tbl, entry, npages); + tbl->it_ops->clear(tbl, entry, npages); spin_lock_irqsave(&(pool->lock), flags); bitmap_clear(tbl->it_map, free_entry, npages); @@ -424,8 +424,8 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, * not do an mb() here on purpose, it is not needed on any of * the current platforms. */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); + if (tbl->it_ops->flush) + tbl->it_ops->flush(tbl); } int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, @@ -495,7 +495,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, npages, entry, dma_addr); /* Insert into HW table */ - build_fail = ppc_md.tce_build(tbl, entry, npages, + build_fail = tbl->it_ops->set(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK(tbl), direction, attrs); if(unlikely(build_fail)) @@ -534,8 +534,8 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Flush/invalidate TLB caches if necessary */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); + if (tbl->it_ops->flush) + tbl->it_ops->flush(tbl); DBG("mapped %d elements:\n", outcount); @@ -600,8 +600,8 @@ void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, * do not do an mb() here, the affected platforms do not need it * when freeing. */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); + if (tbl->it_ops->flush) + tbl->it_ops->flush(tbl); } static void iommu_table_clear(struct iommu_table *tbl) @@ -613,17 +613,17 @@ static void iommu_table_clear(struct iommu_table *tbl) */ if (!is_kdump_kernel() || is_fadump_active()) { /* Clear the table in case firmware left allocations in it */ - ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size); + tbl->it_ops->clear(tbl, tbl->it_offset, tbl->it_size); return; } #ifdef CONFIG_CRASH_DUMP - if (ppc_md.tce_get) { + if (tbl->it_ops->get) { unsigned long index, tceval, tcecount = 0; /* Reserve the existing mappings left by the first kernel. */ for (index = 0; index < tbl->it_size; index++) { - tceval = ppc_md.tce_get(tbl, index + tbl->it_offset); + tceval = tbl->it_ops->get(tbl, index + tbl->it_offset); /* * Freed TCE entry contains 0x7fffffffffffffff on JS20 */ @@ -657,6 +657,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) unsigned int i; struct iommu_pool *p; + BUG_ON(!tbl->it_ops); + /* number of bytes needed for the bitmap */ sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long); @@ -929,8 +931,8 @@ EXPORT_SYMBOL_GPL(iommu_tce_direction); void iommu_flush_tce(struct iommu_table *tbl) { /* Flush/invalidate TLB caches if necessary */ - if (ppc_md.tce_flush) - ppc_md.tce_flush(tbl); + if (tbl->it_ops->flush) + tbl->it_ops->flush(tbl); /* Make sure updates are seen by hardware */ mb(); @@ -941,7 +943,7 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl, unsigned long ioba, unsigned long tce_value, unsigned long npages) { - /* ppc_md.tce_free() does not support any value but 0 */ + /* tbl->it_ops->clear() does not support any value but 0 */ if (tce_value) return -EINVAL; @@ -989,9 +991,9 @@ unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry) spin_lock(&(pool->lock)); - oldtce = ppc_md.tce_get(tbl, entry); + oldtce = tbl->it_ops->get(tbl, entry); if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)) - ppc_md.tce_free(tbl, entry, 1); + tbl->it_ops->clear(tbl, entry, 1); else oldtce = 0; @@ -1014,10 +1016,10 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, spin_lock(&(pool->lock)); - oldtce = ppc_md.tce_get(tbl, entry); + oldtce = tbl->it_ops->get(tbl, entry); /* Add new entry if it is not busy */ if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))) - ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL); + ret = tbl->it_ops->set(tbl, entry, 1, hwaddr, direction, NULL); spin_unlock(&(pool->lock)); diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 5bfdab9047be..b41426c60ef6 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1196,6 +1196,11 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) tbl->it_type = TCE_VB; tbl->it_blocksize = 16; + if (firmware_has_feature(FW_FEATURE_LPAR)) + tbl->it_ops = &iommu_table_lpar_multi_ops; + else + tbl->it_ops = &iommu_table_pseries_ops; + return iommu_init_table(tbl, -1); } -- cgit v1.2.3