From 84b1cec4fac5889b6d138d4b5ff6f2d5ef126c5e Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Thu, 4 Apr 2024 10:27:17 +0000 Subject: iommu/amd: Fix possible irq lock inversion dependency issue LOCKDEP detector reported below warning: ---------------------------------------- [ 23.796949] ======================================================== [ 23.796950] WARNING: possible irq lock inversion dependency detected [ 23.796952] 6.8.0fix+ #811 Not tainted [ 23.796954] -------------------------------------------------------- [ 23.796954] kworker/0:1/8 just changed the state of lock: [ 23.796956] ff365325e084a9b8 (&domain->lock){..-.}-{3:3}, at: amd_iommu_flush_iotlb_all+0x1f/0x50 [ 23.796969] but this lock took another, SOFTIRQ-unsafe lock in the past: [ 23.796970] (pd_bitmap_lock){+.+.}-{3:3} [ 23.796972] and interrupts could create inverse lock ordering between them. [ 23.796973] other info that might help us debug this: [ 23.796974] Chain exists of: &domain->lock --> &dev_data->lock --> pd_bitmap_lock [ 23.796980] Possible interrupt unsafe locking scenario: [ 23.796981] CPU0 CPU1 [ 23.796982] ---- ---- [ 23.796983] lock(pd_bitmap_lock); [ 23.796985] local_irq_disable(); [ 23.796985] lock(&domain->lock); [ 23.796988] lock(&dev_data->lock); [ 23.796990] [ 23.796991] lock(&domain->lock); Fix this issue by disabling interrupt when acquiring pd_bitmap_lock. Note that this is temporary fix. We have a plan to replace custom bitmap allocator with IDA allocator. Fixes: 87a6f1f22c97 ("iommu/amd: Introduce per-device domain ID to fix potential TLB aliasing issue") Reviewed-by: Suravee Suthikulpanit Signed-off-by: Vasant Hegde Link: https://lore.kernel.org/r/20240404102717.6705-1-vasant.hegde@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/iommu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index d35c1b8c8e65c..e692217fcb280 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1692,26 +1692,29 @@ int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid, static u16 domain_id_alloc(void) { + unsigned long flags; int id; - spin_lock(&pd_bitmap_lock); + spin_lock_irqsave(&pd_bitmap_lock, flags); id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID); BUG_ON(id == 0); if (id > 0 && id < MAX_DOMAIN_ID) __set_bit(id, amd_iommu_pd_alloc_bitmap); else id = 0; - spin_unlock(&pd_bitmap_lock); + spin_unlock_irqrestore(&pd_bitmap_lock, flags); return id; } static void domain_id_free(int id) { - spin_lock(&pd_bitmap_lock); + unsigned long flags; + + spin_lock_irqsave(&pd_bitmap_lock, flags); if (id > 0 && id < MAX_DOMAIN_ID) __clear_bit(id, amd_iommu_pd_alloc_bitmap); - spin_unlock(&pd_bitmap_lock); + spin_unlock_irqrestore(&pd_bitmap_lock, flags); } static void free_gcr3_tbl_level1(u64 *tbl) -- cgit 1.2.3-korg