[PATCH 4/5] iommu/arm-smmu: add support for unmap a memory range with only one tlb sync
Zhen Lei
thunder.leizhen at huawei.com
Mon Jun 26 06:38:49 PDT 2017
1. remove tlb_sync operation in "unmap"
2. make sure each "unmap" will always be followed by tlb sync operation
The resultant effect is as below:
unmap memory page-1
tlb invalidate page-1
...
unmap memory page-n
tlb invalidate page-n
tlb sync
Signed-off-by: Zhen Lei <thunder.leizhen at huawei.com>
---
drivers/iommu/arm-smmu.c | 10 ++++++++++
drivers/iommu/io-pgtable-arm-v7s.c | 32 +++++++++++++++++++++-----------
2 files changed, 31 insertions(+), 11 deletions(-)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index b8d069a..74ca6eb 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1402,6 +1402,15 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
return ops->unmap(ops, iova, size);
}
+static void arm_smmu_unmap_tlb_sync(struct iommu_domain *domain)
+{
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
+
+ if (ops && ops->unmap_tlb_sync)
+ ops->unmap_tlb_sync(ops);
+}
+
static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
dma_addr_t iova)
{
@@ -1698,6 +1707,7 @@ static struct iommu_ops arm_smmu_ops = {
.attach_dev = arm_smmu_attach_dev,
.map = arm_smmu_map,
.unmap = arm_smmu_unmap,
+ .unmap_tlb_sync = arm_smmu_unmap_tlb_sync,
.map_sg = default_iommu_map_sg,
.iova_to_phys = arm_smmu_iova_to_phys,
.add_device = arm_smmu_add_device,
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index a55fd38..325c1c6 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -370,6 +370,8 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
for (i = 0; i < num_entries; i++)
if (ARM_V7S_PTE_IS_TABLE(ptep[i], lvl)) {
+ size_t unmapped;
+
/*
* We need to unmap and free the old table before
* overwriting it with a block entry.
@@ -378,8 +380,10 @@ static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
size_t sz = ARM_V7S_BLOCK_SIZE(lvl);
tblp = ptep - ARM_V7S_LVL_IDX(iova, lvl);
- if (WARN_ON(__arm_v7s_unmap(data, iova + i * sz,
- sz, lvl, tblp) != sz))
+ unmapped = __arm_v7s_unmap(data, iova + i * sz,
+ sz, lvl, tblp);
+ io_pgtable_tlb_sync(&data->iop);
+ if (WARN_ON(unmapped != sz))
return -EINVAL;
} else if (ptep[i]) {
/* We require an unmap first */
@@ -626,7 +630,6 @@ static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
/* Also flush any partial walks */
io_pgtable_tlb_add_flush(iop, iova, blk_size,
ARM_V7S_BLOCK_SIZE(lvl + 1), false);
- io_pgtable_tlb_sync(iop);
ptep = iopte_deref(pte[i], lvl);
__arm_v7s_free_table(ptep, lvl + 1, data);
} else {
@@ -653,13 +656,15 @@ static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
size_t size)
{
struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
- size_t unmapped;
- unmapped = __arm_v7s_unmap(data, iova, size, 1, data->pgd);
- if (unmapped)
- io_pgtable_tlb_sync(&data->iop);
+ return __arm_v7s_unmap(data, iova, size, 1, data->pgd);
+}
+
+static void arm_v7s_unmap_tlb_sync(struct io_pgtable_ops *ops)
+{
+ struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
- return unmapped;
+ io_pgtable_tlb_sync(&data->iop);
}
static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
@@ -724,6 +729,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
data->iop.ops = (struct io_pgtable_ops) {
.map = arm_v7s_map,
.unmap = arm_v7s_unmap,
+ .unmap_tlb_sync = arm_v7s_unmap_tlb_sync,
.iova_to_phys = arm_v7s_iova_to_phys,
};
@@ -822,7 +828,7 @@ static int __init arm_v7s_do_selftests(void)
.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;
+ unsigned int iova, size, unmapped, iova_start;
unsigned int i, loopnr = 0;
selftest_running = true;
@@ -877,7 +883,9 @@ static int __init arm_v7s_do_selftests(void)
size = 1UL << __ffs(cfg.pgsize_bitmap);
while (i < loopnr) {
iova_start = i * SZ_16M;
- if (ops->unmap(ops, iova_start + size, size) != size)
+ unmapped = ops->unmap(ops, iova_start + size, size);
+ ops->unmap_tlb_sync(ops);
+ if (unmapped != size)
return __FAIL(ops);
/* Remap of partial unmap */
@@ -896,7 +904,9 @@ static int __init arm_v7s_do_selftests(void)
while (i != BITS_PER_LONG) {
size = 1UL << i;
- if (ops->unmap(ops, iova, size) != size)
+ unmapped = ops->unmap(ops, iova, size);
+ ops->unmap_tlb_sync(ops);
+ if (unmapped != size)
return __FAIL(ops);
if (ops->iova_to_phys(ops, iova + 42))
--
2.5.0
More information about the linux-arm-kernel
mailing list