drm/amdgpu: Implement Enforce Isolation Handler for KGD/KFD serialization

This commit introduces the Enforce Isolation Handler designed to enforce
shader isolation on AMD GPUs, which helps to prevent data leakage
between different processes.

The handler counts the number of emitted fences for each GFX and compute
ring. If there are any fences, it schedules the `enforce_isolation_work`
to be run after a delay of `GFX_SLICE_PERIOD`. If there are no fences,
it signals the Kernel Fusion Driver (KFD) to resume the runqueue.

The function is synchronized using the `enforce_isolation_mutex`.

This commit also introduces a reference count mechanism
(kfd_sch_req_count) to keep track of the number of requests to enable
the KFD scheduler. When a request to enable the KFD scheduler is made,
the reference count is decremented. When the reference count reaches
zero, a delayed work is scheduled to enforce isolation after a delay of
GFX_SLICE_PERIOD.

When a request to disable the KFD scheduler is made, the function first
checks if the reference count is zero. If it is, it cancels the delayed
work for enforcing isolation and checks if the KFD scheduler is active.
If the KFD scheduler is active, it sends a request to stop the KFD
scheduler and sets the KFD scheduler state to inactive. Then, it
increments the reference count.

The function is synchronized using the kfd_sch_mutex to ensure that the
KFD scheduler state and reference count are updated atomically.

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Suggested-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 15 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index f7b37c340e36..e28c1ebfa98f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -34,6 +34,7 @@
 #include "soc15.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_ring_mux.h"
+#include "amdgpu_xcp.h"
 
 /* GFX current status */
 #define AMDGPU_GFX_NORMAL_MODE			0x00000000L
@@ -343,6 +344,12 @@ struct amdgpu_me {
 	DECLARE_BITMAP(queue_bitmap, AMDGPU_MAX_GFX_QUEUES);
 };
 
+struct amdgpu_isolation_work {
+	struct amdgpu_device		*adev;
+	u32				xcp_id;
+	struct delayed_work		work;
+};
+
 struct amdgpu_gfx {
 	struct mutex			gpu_clock_mutex;
 	struct amdgpu_gfx_config	config;
@@ -454,6 +461,11 @@ struct amdgpu_gfx {
 	void				*cleaner_shader_cpu_ptr;
 	const void			*cleaner_shader_ptr;
 	bool				enable_cleaner_shader;
+	struct amdgpu_isolation_work	enforce_isolation[MAX_XCP];
+	/* Mutex for synchronizing KFD scheduler operations */
+	struct mutex                    kfd_sch_mutex;
+	u64				kfd_sch_req_count[MAX_XCP];
+	bool				kfd_sch_inactive[MAX_XCP];
 };
 
 struct amdgpu_gfx_ras_reg_entry {
@@ -563,6 +575,9 @@ void amdgpu_gfx_cleaner_shader_init(struct amdgpu_device *adev,
 				    const void *cleaner_shader_ptr);
 int amdgpu_gfx_sysfs_isolation_shader_init(struct amdgpu_device *adev);
 void amdgpu_gfx_sysfs_isolation_shader_fini(struct amdgpu_device *adev);
+void amdgpu_gfx_enforce_isolation_handler(struct work_struct *work);
+void amdgpu_gfx_enforce_isolation_ring_begin_use(struct amdgpu_ring *ring);
+void amdgpu_gfx_enforce_isolation_ring_end_use(struct amdgpu_ring *ring);
 
 static inline const char *amdgpu_gfx_compute_mode_desc(int mode)
 {