diff options
author | Robin Murphy <robin.murphy@arm.com> | 2017-06-22 16:53:53 +0100 |
---|---|---|
committer | Will Deacon <will.deacon@arm.com> | 2017-06-23 17:58:00 +0100 |
commit | 81b3c25218447c65f93adf08b099a322b6803536 (patch) | |
tree | 6ba8f9f78dfc2604da3885a1e08060f9bb5cbf09 /drivers/iommu/io-pgtable-arm-v7s.c | |
parent | b9f1ef30ac2e9942b8628d551f4a21e8cec1415c (diff) | |
download | blackbird-obmc-linux-81b3c25218447c65f93adf08b099a322b6803536.tar.gz blackbird-obmc-linux-81b3c25218447c65f93adf08b099a322b6803536.zip |
iommu/io-pgtable: Introduce explicit coherency
Once we remove the serialising spinlock, a potential race opens up for
non-coherent IOMMUs whereby a caller of .map() can be sure that cache
maintenance has been performed on their new PTE, but will have no
guarantee that such maintenance for table entries above it has actually
completed (e.g. if another CPU took an interrupt immediately after
writing the table entry, but before initiating the DMA sync).
Handling this race safely will add some potentially non-trivial overhead
to installing a table entry, which we would much rather avoid on
coherent systems where it will be unnecessary, and where we are stirivng
to minimise latency by removing the locking in the first place.
To that end, let's introduce an explicit notion of cache-coherency to
io-pgtable, such that we will be able to avoid penalising IOMMUs which
know enough to know when they are coherent.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Diffstat (limited to 'drivers/iommu/io-pgtable-arm-v7s.c')
-rw-r--r-- | drivers/iommu/io-pgtable-arm-v7s.c | 17 |
1 files changed, 10 insertions, 7 deletions
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index dc74631322e4..ec024c75a09e 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -187,7 +187,8 @@ static arm_v7s_iopte *iopte_deref(arm_v7s_iopte pte, int lvl) static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, struct arm_v7s_io_pgtable *data) { - struct device *dev = data->iop.cfg.iommu_dev; + struct io_pgtable_cfg *cfg = &data->iop.cfg; + struct device *dev = cfg->iommu_dev; dma_addr_t dma; size_t size = ARM_V7S_TABLE_SIZE(lvl); void *table = NULL; @@ -196,7 +197,7 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, table = (void *)__get_dma_pages(__GFP_ZERO, get_order(size)); else if (lvl == 2) table = kmem_cache_zalloc(data->l2_tables, gfp | GFP_DMA); - if (table && !selftest_running) { + if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) { dma = dma_map_single(dev, table, size, DMA_TO_DEVICE); if (dma_mapping_error(dev, dma)) goto out_free; @@ -225,10 +226,11 @@ out_free: static void __arm_v7s_free_table(void *table, int lvl, struct arm_v7s_io_pgtable *data) { - struct device *dev = data->iop.cfg.iommu_dev; + struct io_pgtable_cfg *cfg = &data->iop.cfg; + struct device *dev = cfg->iommu_dev; size_t size = ARM_V7S_TABLE_SIZE(lvl); - if (!selftest_running) + if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) dma_unmap_single(dev, __arm_v7s_dma_addr(table), size, DMA_TO_DEVICE); if (lvl == 1) @@ -240,7 +242,7 @@ static void __arm_v7s_free_table(void *table, int lvl, static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries, struct io_pgtable_cfg *cfg) { - if (selftest_running) + if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) return; dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep), @@ -657,7 +659,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_PERMS | IO_PGTABLE_QUIRK_TLBI_ON_MAP | - IO_PGTABLE_QUIRK_ARM_MTK_4GB)) + IO_PGTABLE_QUIRK_ARM_MTK_4GB | + IO_PGTABLE_QUIRK_NO_DMA)) return NULL; /* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */ @@ -774,7 +777,7 @@ static int __init arm_v7s_do_selftests(void) .tlb = &dummy_tlb_ops, .oas = 32, .ias = 32, - .quirks = IO_PGTABLE_QUIRK_ARM_NS, + .quirks = IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA, .pgsize_bitmap = SZ_4K | SZ_64K | SZ_1M | SZ_16M, }; unsigned int iova, size, iova_start; |