iommu/amd: Fix Invalid wait context issue

With commit c4cb23111103 ("iommu/amd: Add support for enable/disable IOPF")
we are hitting below issue. This happens because in IOPF enablement path
it holds spin lock with irq disable and then tries to take mutex lock.

dmesg:
-----
[    0.938739] =============================
[    0.938740] [ BUG: Invalid wait context ]
[    0.938742] 6.10.0-rc1+ #1 Not tainted
[    0.938745] -----------------------------
[    0.938746] swapper/0/1 is trying to lock:
[    0.938748] ffffffff8c9f01d8 (&port_lock_key){....}-{3:3}, at: serial8250_console_write+0x78/0x4a0
[    0.938767] other info that might help us debug this:
[    0.938768] context-{5:5}
[    0.938769] 7 locks held by swapper/0/1:
[    0.938772]  #0: ffff888101a91310 (&group->mutex){+.+.}-{4:4}, at: bus_iommu_probe+0x70/0x160
[    0.938790]  #1: ffff888101d1f1b8 (&domain->lock){....}-{3:3}, at: amd_iommu_attach_device+0xa5/0x700
[    0.938799]  #2: ffff888101cc3d18 (&dev_data->lock){....}-{3:3}, at: amd_iommu_attach_device+0xc5/0x700
[    0.938806]  #3: ffff888100052830 (&iommu->lock){....}-{2:2}, at: amd_iommu_iopf_add_device+0x3f/0xa0
[    0.938813]  #4: ffffffff8945a340 (console_lock){+.+.}-{0:0}, at: _printk+0x48/0x50
[    0.938822]  #5: ffffffff8945a390 (console_srcu){....}-{0:0}, at: console_flush_all+0x58/0x4e0
[    0.938867]  #6: ffffffff82459f80 (console_owner){....}-{0:0}, at: console_flush_all+0x1f0/0x4e0
[    0.938872] stack backtrace:
[    0.938874] CPU: 2 PID: 1 Comm: swapper/0 Not tainted 6.10.0-rc1+ #1
[    0.938877] Hardware name: HP HP EliteBook 745 G3/807E, BIOS N73 Ver. 01.39 04/16/2019

Fix above issue by re-arranging code in attach device path:
  - move device PASID/IOPF enablement outside lock in AMD IOMMU driver.
    This is safe as core layer holds group->mutex lock before calling
    iommu_ops->attach_dev.

Reported-by: Borislav Petkov <bp@alien8.de>
Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Reported-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Fixes: c4cb23111103 ("iommu/amd: Add support for enable/disable IOPF")
Tested-by: Borislav Petkov <bp@alien8.de>
Tested-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20240530084801.10758-1-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

1 files changed, 4 insertions, 18 deletions

diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c
index 31d98a2a11a6..7c67d69f0b8c 100644
--- a/drivers/iommu/amd/ppr.c
+++ b/drivers/iommu/amd/ppr.c
@@ -248,40 +248,26 @@ void amd_iommu_page_response(struct device *dev, struct iopf_fault *evt,
 int amd_iommu_iopf_add_device(struct amd_iommu *iommu,
 			      struct iommu_dev_data *dev_data)
 {
-	unsigned long flags;
 	int ret = 0;
 
 	if (!dev_data->pri_enabled)
 		return ret;
 
-	raw_spin_lock_irqsave(&iommu->lock, flags);
-
-	if (!iommu->iopf_queue) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
+	if (!iommu->iopf_queue)
+		return -EINVAL;
 
 	ret = iopf_queue_add_device(iommu->iopf_queue, dev_data->dev);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	dev_data->ppr = true;
-
-out_unlock:
-	raw_spin_unlock_irqrestore(&iommu->lock, flags);
-	return ret;
+	return 0;
 }
 
 /* Its assumed that caller has verified that device was added to iopf queue */
 void amd_iommu_iopf_remove_device(struct amd_iommu *iommu,
 				  struct iommu_dev_data *dev_data)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&iommu->lock, flags);
-
 	iopf_queue_remove_device(iommu->iopf_queue, dev_data->dev);
 	dev_data->ppr = false;
-
-	raw_spin_unlock_irqrestore(&iommu->lock, flags);
 }