drm/amdgpu: replace PASID IDR with XArray

Replace the PASID IDR + spinlock with XArray as noted in the TODO
left by commit ea56aa262570 ("drm/amdgpu: fix the idr allocation
flags").

The IDR conversion still has an IRQ safety issue:
amdgpu_pasid_free() can be called from hardirq context via the fence
signal path, but amdgpu_pasid_idr_lock is taken with plain spin_lock()
in process context, creating a potential deadlock:

     CPU0
     ----
     spin_lock(&amdgpu_pasid_idr_lock)   // process context, IRQs on
     <Interrupt>
       spin_lock(&amdgpu_pasid_idr_lock) // deadlock

   The hardirq call chain is:

     sdma_v6_0_process_trap_irq
      -> amdgpu_fence_process
       -> dma_fence_signal
        -> drm_sched_job_done
         -> dma_fence_signal
          -> amdgpu_pasid_free_cb
           -> amdgpu_pasid_free

Use XArray with XA_FLAGS_LOCK_IRQ (all xa operations use IRQ-safe
locking internally) and XA_FLAGS_ALLOC1 (zero is not a valid PASID).
Both xa_alloc_cyclic() and xa_erase() then handle locking
consistently, fixing the IRQ safety issue and removing the need for
an explicit spinlock.

v8: squash in irq safe fix

Reviewed-by: Christian König <christian.koenig@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Fixes: ea56aa262570 ("drm/amdgpu: fix the idr allocation flags")
Fixes: 8f1de51f49be ("drm/amdgpu: prevent immediate PASID reuse case")
Signed-off-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 19 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 569c5a89ff10..124fb38eb465 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -22,7 +22,7 @@
  */
 #include "amdgpu_ids.h"
 
-#include <linux/idr.h>
+#include <linux/xarray.h>
 #include <linux/dma-fence-array.h>
 
 
@@ -40,8 +40,8 @@
  * VMs are looked up from the PASID per amdgpu_device.
  */
 
-static DEFINE_IDR(amdgpu_pasid_idr);
-static DEFINE_SPINLOCK(amdgpu_pasid_idr_lock);
+static DEFINE_XARRAY_FLAGS(amdgpu_pasid_xa, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC1);
+static u32 amdgpu_pasid_xa_next;
 
 /* Helper to free pasid from a fence callback */
 struct amdgpu_pasid_cb {
@@ -62,36 +62,37 @@ struct amdgpu_pasid_cb {
  */
 int amdgpu_pasid_alloc(unsigned int bits)
 {
-	int pasid;
+	u32 pasid;
+	int r;
 
 	if (bits == 0)
 		return -EINVAL;
 
-	spin_lock(&amdgpu_pasid_idr_lock);
-	/* TODO: Need to replace the idr with an xarry, and then
-	 * handle the internal locking with ATOMIC safe paths.
-	 */
-	pasid = idr_alloc_cyclic(&amdgpu_pasid_idr, NULL, 1,
-				 1U << bits, GFP_ATOMIC);
-	spin_unlock(&amdgpu_pasid_idr_lock);
-
-	if (pasid >= 0)
-		trace_amdgpu_pasid_allocated(pasid);
+	r = xa_alloc_cyclic_irq(&amdgpu_pasid_xa, &pasid, xa_mk_value(0),
+			    XA_LIMIT(1, (1U << bits) - 1),
+			    &amdgpu_pasid_xa_next, GFP_KERNEL);
+	if (r < 0)
+		return r;
 
+	trace_amdgpu_pasid_allocated(pasid);
 	return pasid;
 }
 
 /**
  * amdgpu_pasid_free - Free a PASID
  * @pasid: PASID to free
+ *
+ * Called in IRQ context.
  */
 void amdgpu_pasid_free(u32 pasid)
 {
+	unsigned long flags;
+
 	trace_amdgpu_pasid_freed(pasid);
 
-	spin_lock(&amdgpu_pasid_idr_lock);
-	idr_remove(&amdgpu_pasid_idr, pasid);
-	spin_unlock(&amdgpu_pasid_idr_lock);
+	xa_lock_irqsave(&amdgpu_pasid_xa, flags);
+	__xa_erase(&amdgpu_pasid_xa, pasid);
+	xa_unlock_irqrestore(&amdgpu_pasid_xa, flags);
 }
 
 static void amdgpu_pasid_free_cb(struct dma_fence *fence,
@@ -634,7 +635,5 @@ void amdgpu_vmid_mgr_fini(struct amdgpu_device *adev)
  */
 void amdgpu_pasid_mgr_cleanup(void)
 {
-	spin_lock(&amdgpu_pasid_idr_lock);
-	idr_destroy(&amdgpu_pasid_idr);
-	spin_unlock(&amdgpu_pasid_idr_lock);
+	xa_destroy(&amdgpu_pasid_xa);
 }