aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/iommu/io-pgtable-arm.c
diff options
context:
space:
mode:
authorRobin Murphy <robin.murphy@arm.com>2017-06-22 16:53:53 +0100
committerWill Deacon <will.deacon@arm.com>2017-06-23 17:58:00 +0100
commit81b3c25218447c65f93adf08b099a322b6803536 (patch)
tree6ba8f9f78dfc2604da3885a1e08060f9bb5cbf09 /drivers/iommu/io-pgtable-arm.c
parentiommu/io-pgtable-arm-v7s: Refactor split_blk_unmap (diff)
downloadlinux-dev-81b3c25218447c65f93adf08b099a322b6803536.tar.xz
linux-dev-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.c')
-rw-r--r--drivers/iommu/io-pgtable-arm.c11
1 files changed, 6 insertions, 5 deletions
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index dd7477010291..6334f51912ea 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -217,7 +217,7 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
if (!pages)
return NULL;
- if (!selftest_running) {
+ if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
if (dma_mapping_error(dev, dma))
goto out_free;
@@ -243,7 +243,7 @@ out_free:
static void __arm_lpae_free_pages(void *pages, size_t size,
struct io_pgtable_cfg *cfg)
{
- if (!selftest_running)
+ if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
size, DMA_TO_DEVICE);
free_pages_exact(pages, size);
@@ -254,7 +254,7 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
{
*ptep = pte;
- if (!selftest_running)
+ if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
dma_sync_single_for_device(cfg->iommu_dev,
__arm_lpae_dma_addr(ptep),
sizeof(pte), DMA_TO_DEVICE);
@@ -693,7 +693,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
u64 reg;
struct arm_lpae_io_pgtable *data;
- if (cfg->quirks & ~IO_PGTABLE_QUIRK_ARM_NS)
+ if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA))
return NULL;
data = arm_lpae_alloc_pgtable(cfg);
@@ -782,7 +782,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
struct arm_lpae_io_pgtable *data;
/* The NS quirk doesn't apply at stage 2 */
- if (cfg->quirks)
+ if (cfg->quirks & ~IO_PGTABLE_QUIRK_NO_DMA)
return NULL;
data = arm_lpae_alloc_pgtable(cfg);
@@ -1086,6 +1086,7 @@ static int __init arm_lpae_do_selftests(void)
struct io_pgtable_cfg cfg = {
.tlb = &dummy_tlb_ops,
.oas = 48,
+ .quirks = IO_PGTABLE_QUIRK_NO_DMA,
};
for (i = 0; i < ARRAY_SIZE(pgsize); ++i) {