gpu: nvgpu: gv11b: add mmu fault handling

HUB reports following memory sub-system interrupts:
a) ACCESS_COUNTER_NOTIFY:
   GET != PUT for access counter notify buffer
b) ACCESS_COUNTER_ERROR:
   HUB received a NACK (BAR2 fault) when writing the
   notify buffer out to memory
c) MMU_ECC_UNCORRECTED_ERROR_NOTIFY:
   Uncorrected ECC error detected by HUB MMU
d) MMU_REPLAYABLE_FAULT_NOTIFY:
   GET != PUT for replayable fault buffer
e) MMU_REPLAYABLE_FAULT_OVERFLOW:
   Overflow when writing to the replayable fault buffer
f) MMU_NONREPLAYABLE_FAULT_NOTIFY:
   GET != PUT for non-replayable fault buffer
g) MMU_NONREPLAYABLE_FAULT_OVERFLOW:
   Overflow when writing to the non-replayable fault buffer
h) MMU_OTHER_FAULT_NOTIFY: All other fault notifications from MMU

This change is to :
-Detect other fault notify
-Copy fault info from fault snap register for other fault notify
 interrupt
-Detect and handle nonreplay/replay fault notify and fault overflow
-Copy fault info from fault buffer for nonreplay/replay fault
-Print fault info

JIRA GPUT19X-7
JIRA GPUT19X-12

Change-Id: Ifa08a4ebcd119a7d81c2eae3f52dc825d1ce3898
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master/r/1493394
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
GVS: Gerrit_Virtual_Submit

1 files changed, 9 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gv11b/mm_gv11b.c b/drivers/gpu/nvgpu/gv11b/mm_gv11b.c
index d6184cee..f4fc4db4 100644
--- a/drivers/gpu/nvgpu/gv11b/mm_gv11b.c
+++ b/drivers/gpu/nvgpu/gv11b/mm_gv11b.c
@@ -59,6 +59,8 @@ static bool gv11b_mm_mmu_fault_pending(struct gk20a *g)
 
 static void gv11b_mm_fault_info_mem_destroy(struct gk20a *g)
 {
+        nvgpu_log_fn(g, " ");
+
         nvgpu_mutex_acquire(&g->mm.hub_isr_mutex);
 
         gv11b_fb_disable_hub_intr(g, STALL_REG_INDEX, HUB_INTR_TYPE_OTHER |
@@ -136,6 +138,8 @@ static void gv11b_mm_mmu_hw_fault_buf_deinit(struct gk20a *g)
 {
         struct vm_gk20a *vm = g->mm.bar2.vm;
 
+        nvgpu_log_fn(g, " ");
+
         gv11b_fb_disable_hub_intr(g, STALL_REG_INDEX, HUB_INTR_TYPE_NONREPLAY |
                                          HUB_INTR_TYPE_REPLAY);
 
@@ -173,6 +177,8 @@ static void gv11b_mm_remove_bar2_vm(struct gk20a *g)
 {
         struct mm_gk20a *mm = &g->mm;
 
+        nvgpu_log_fn(g, " ");
+
         gv11b_mm_mmu_hw_fault_buf_deinit(g);
 
         gk20a_free_inst_block(g, &mm->bar2.inst_block);
@@ -195,6 +201,8 @@ static int gv11b_mm_mmu_fault_setup_sw(struct gk20a *g)
 {
         int err;
 
+        nvgpu_log_fn(g, " ");
+
         nvgpu_mutex_init(&g->mm.hub_isr_mutex);
 
         g->mm.hw_fault_buf_status[NONREPLAY_REG_INDEX] =
@@ -216,7 +224,7 @@ static int gv11b_init_mm_setup_hw(struct gk20a *g)
 {
         int err = 0;
 
-        nvgpu_log_fn(g, "start");
+        nvgpu_log_fn(g, " ");
 
         g->ops.fb.set_mmu_page_size(g);
         g->ops.fb.init_hw(g);