@@ -539,31 +539,42 @@ static inline void put_signature(struct smmu_as *as,
/*
* Caller must lock/unlock as
*/
-static int alloc_pdir(struct smmu_as *as)
+static int alloc_pdir(struct smmu_as *as, unsigned long *flags)
{
unsigned long *pdir;
- int pdn;
+ int pdn, err = 0;
u32 val;
struct smmu_device *smmu = as->smmu;
+ struct page *page;
+ unsigned int *cnt;
if (as->pdir_page)
return 0;
- as->pte_count = devm_kzalloc(smmu->dev,
- sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_KERNEL);
- if (!as->pte_count) {
- dev_err(smmu->dev,
- "failed to allocate smmu_device PTE cunters\n");
- return -ENOMEM;
+ /*
+ * do the allocation outside the as lock
+ */
+ spin_unlock_irqrestore(&as->lock, *flags);
+ cnt = devm_kzalloc(smmu->dev,
+ sizeof(cnt[0]) * SMMU_PDIR_COUNT, GFP_KERNEL);
+ page = alloc_page(GFP_KERNEL | __GFP_DMA);
+ spin_lock_irqsave(&as->lock, *flags);
+
+ if (as->pdir_page) {
+ /* We raced, free the redundant */
+ err = -ENODEV;
+ goto err_out;
}
- as->pdir_page = alloc_page(GFP_KERNEL | __GFP_DMA);
- if (!as->pdir_page) {
- dev_err(smmu->dev,
- "failed to allocate smmu_device page directory\n");
- devm_kfree(smmu->dev, as->pte_count);
- as->pte_count = NULL;
- return -ENOMEM;
+
+ if (!page || !cnt) {
+ dev_err(smmu->dev, "failed to allocate at %s\n", __func__);
+ err = -ENOMEM;
+ goto err_out;
}
+
+ as->pdir_page = page;
+ as->pte_count = cnt;
+
SetPageReserved(as->pdir_page);
pdir = page_address(as->pdir_page);
@@ -580,6 +591,12 @@ static int alloc_pdir(struct smmu_as *as)
FLUSH_SMMU_REGS(as->smmu);
return 0;
+
+err_out:
+ devm_kfree(smmu->dev, cnt);
+ if (page)
+ __free_page(page);
+ return err;
}
static void __smmu_iommu_unmap(struct smmu_as *as, dma_addr_t iova)
@@ -791,7 +808,7 @@ static int smmu_iommu_domain_init(struct iommu_domain *domain)
return -ENODEV;
found:
- if (alloc_pdir(as) < 0)
+ if (alloc_pdir(as, &flags) < 0)
goto err_alloc_pdir;
spin_lock(&smmu->lock);
alloc_pdir() is called from smmu_iommu_domain_init() with spin_lock held. memory allocations in alloc_pdir() had to be atomic/unsleepable. Instead of converting into atomic allocation, this patch once releases a lock, do the allocation, hold the lock again and then see if it's raced or not in order to avoid introducing mutex. Signed-off-by: Hiroshi DOYU <hdoyu@nvidia.com> Reported-by: Chris Wright <chrisw@sous-sol.org> Cc: Chris Wright <chrisw@sous-sol.org> Cc: Stephen Warren <swarren@wwwdotorg.org> --- drivers/iommu/tegra-smmu.c | 49 +++++++++++++++++++++++++++++-------------- 1 files changed, 33 insertions(+), 16 deletions(-)