[PATCH 3/5] iommu/arm-smmu-v3: add support for unmap an iova range with only one tlb sync
Zhen Lei
thunder.leizhen at huawei.com
Mon Jun 26 06:38:48 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-v3.c | 10 ++++++++++
drivers/iommu/io-pgtable-arm.c | 30 ++++++++++++++++++++----------
drivers/iommu/io-pgtable.h | 1 +
3 files changed, 31 insertions(+), 10 deletions(-)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4481123..328b9d7 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1724,6 +1724,15 @@ arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
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(struct iommu_domain *domain, dma_addr_t iova)
{
@@ -1943,6 +1952,7 @@ 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.c b/drivers/iommu/io-pgtable-arm.c
index 52700fa..8137e62 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -304,6 +304,8 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
WARN_ON(!selftest_running);
return -EEXIST;
} else if (iopte_type(pte, lvl) == ARM_LPAE_PTE_TYPE_TABLE) {
+ size_t unmapped;
+
/*
* We need to unmap and free the old table before
* overwriting it with a block entry.
@@ -312,7 +314,9 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
- if (WARN_ON(__arm_lpae_unmap(data, iova, sz, lvl, tblp) != sz))
+ unmapped = __arm_lpae_unmap(data, iova, sz, lvl, tblp);
+ io_pgtable_tlb_sync(&data->iop);
+ if (WARN_ON(unmapped != sz))
return -EINVAL;
}
@@ -576,7 +580,6 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
/* Also flush any partial walks */
io_pgtable_tlb_add_flush(iop, iova, size,
ARM_LPAE_GRANULE(data), false);
- io_pgtable_tlb_sync(iop);
ptep = iopte_deref(pte, data);
__arm_lpae_free_pgtable(data, lvl + 1, ptep);
} else {
@@ -601,16 +604,18 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
size_t size)
{
- size_t unmapped;
struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
arm_lpae_iopte *ptep = data->pgd;
int lvl = ARM_LPAE_START_LVL(data);
- unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep);
- if (unmapped)
- io_pgtable_tlb_sync(&data->iop);
+ return __arm_lpae_unmap(data, iova, size, lvl, ptep);
+}
+
+static void arm_lpae_unmap_tlb_sync(struct io_pgtable_ops *ops)
+{
+ struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
- return unmapped;
+ io_pgtable_tlb_sync(&data->iop);
}
static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
@@ -723,6 +728,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
data->iop.ops = (struct io_pgtable_ops) {
.map = arm_lpae_map,
.unmap = arm_lpae_unmap,
+ .unmap_tlb_sync = arm_lpae_unmap_tlb_sync,
.iova_to_phys = arm_lpae_iova_to_phys,
};
@@ -1019,7 +1025,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
int i, j;
unsigned long iova;
- size_t size;
+ size_t size, unmapped;
struct io_pgtable_ops *ops;
selftest_running = true;
@@ -1071,7 +1077,9 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
/* Partial unmap */
size = 1UL << __ffs(cfg->pgsize_bitmap);
- if (ops->unmap(ops, SZ_1G + size, size) != size)
+ unmapped = ops->unmap(ops, SZ_1G + size, size);
+ ops->unmap_tlb_sync(ops);
+ if (unmapped != size)
return __FAIL(ops, i);
/* Remap of partial unmap */
@@ -1087,7 +1095,9 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
while (j != BITS_PER_LONG) {
size = 1UL << j;
- if (ops->unmap(ops, iova, size) != size)
+ unmapped = ops->unmap(ops, iova, size);
+ ops->unmap_tlb_sync(ops);
+ if (unmapped != size)
return __FAIL(ops, i);
if (ops->iova_to_phys(ops, iova + 42))
diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h
index 524263a..7b3fc04 100644
--- a/drivers/iommu/io-pgtable.h
+++ b/drivers/iommu/io-pgtable.h
@@ -120,6 +120,7 @@ struct io_pgtable_ops {
phys_addr_t paddr, size_t size, int prot);
int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
size_t size);
+ void (*unmap_tlb_sync)(struct io_pgtable_ops *ops);
phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
unsigned long iova);
};
--
2.5.0
More information about the linux-arm-kernel
mailing list