From 35872480da47ec714fd9c4f2f3d2d83daf304851 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Thu, 29 Aug 2019 18:52:48 +1000 Subject: powerpc/powernv/ioda: Split out TCE invalidation from TCE updates At the moment updates in a TCE table are made by iommu_table_ops::exchange which update one TCE and invalidates an entry in the PHB/NPU TCE cache via set of registers called "TCE Kill" (hence the naming). Writing a TCE is a simple xchg() but invalidating the TCE cache is a relatively expensive OPAL call. Mapping a 100GB guest with PCI+NPU passed through devices takes about 20s. Thankfully we can do better. Since such big mappings happen at the boot time and when memory is plugged/onlined (i.e. not often), these requests come in 512 pages so we call call OPAL 512 times less which brings 20s from the above to less than 10s. Also, since TCE caches can be flushed entirely, calling OPAL for 512 TCEs helps skiboot [1] to decide whether to flush the entire cache or not. This implements 2 new iommu_table_ops callbacks: - xchg_no_kill() to update a single TCE with no TCE invalidation; - tce_kill() to invalidate multiple TCEs. This uses the same xchg_no_kill() callback for IODA1/2. This implements 2 new wrappers on top of the new callbacks similar to the existing iommu_tce_xchg(). This does not use the new callbacks yet, the next patches will; so this should not cause any behavioral change. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190829085252.72370-2-aik@ozlabs.ru --- arch/powerpc/kernel/iommu.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'arch/powerpc/kernel/iommu.c') diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0a67ce9f827e..145f29cf7e4c 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1005,6 +1005,33 @@ long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, } EXPORT_SYMBOL_GPL(iommu_tce_xchg); +extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, + struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction) +{ + long ret; + unsigned long size = 0; + + ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false); + if (!ret && ((*direction == DMA_FROM_DEVICE) || + (*direction == DMA_BIDIRECTIONAL)) && + !mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift, + &size)) + SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT)); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_tce_xchg_no_kill); + +void iommu_tce_kill(struct iommu_table *tbl, + unsigned long entry, unsigned long pages) +{ + if (tbl->it_ops->tce_kill) + tbl->it_ops->tce_kill(tbl, entry, pages, false); +} +EXPORT_SYMBOL_GPL(iommu_tce_kill); + int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; -- cgit v1.2.3-59-g8ed1b