drm/amdgpu: Track pending retry faults in IH and VM (v2)

IH tracks pending retry faults in a hash table for fast lookup in
interrupt context. Each VM has a short FIFO of pending VM faults for
processing in a bottom half.

The IH prescreening stage adds retry faults and filters out repeated
retry interrupts to minimize the impact of interrupt storms.

It's the VM's responsibility remove pending faults once they are
handled. For now this is only done when the VM is destroyed.

v2:
- Made the hash table smaller and the FIFO longer. I never want the
  FIFO to fill up, because that would make prescreen take longer.
  128 pending page faults should be enough to keep migrations busy.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com> (v1)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 12 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
index 3de8e74..ada89358 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
@@ -24,6 +24,8 @@
 #ifndef __AMDGPU_IH_H__
 #define __AMDGPU_IH_H__
 
+#include <linux/chash.h>
+
 struct amdgpu_device;
  /*
   * vega10+ IH clients
@@ -69,6 +71,13 @@ enum amdgpu_ih_clientid
 
 #define AMDGPU_IH_CLIENTID_LEGACY 0
 
+#define AMDGPU_PAGEFAULT_HASH_BITS 8
+struct amdgpu_retryfault_hashtable {
+	DECLARE_CHASH_TABLE(hash, AMDGPU_PAGEFAULT_HASH_BITS, 8, 0);
+	spinlock_t	lock;
+	int		count;
+};
+
 /*
  * R6xx+ IH ring
  */
@@ -87,6 +96,7 @@ struct amdgpu_ih_ring {
 	bool			use_doorbell;
 	bool			use_bus_addr;
 	dma_addr_t		rb_dma_addr; /* only used when use_bus_addr = true */
+	struct amdgpu_retryfault_hashtable *faults;
 };
 
 #define AMDGPU_IH_SRC_DATA_MAX_SIZE_DW 4
@@ -109,5 +119,7 @@ int amdgpu_ih_ring_init(struct amdgpu_device *adev, unsigned ring_size,
 			bool use_bus_addr);
 void amdgpu_ih_ring_fini(struct amdgpu_device *adev);
 int amdgpu_ih_process(struct amdgpu_device *adev);
+int amdgpu_ih_add_fault(struct amdgpu_device *adev, u64 key);
+void amdgpu_ih_clear_fault(struct amdgpu_device *adev, u64 key);
 
 #endif