gpu: nvgpu: gv11b: replay invalid pte faults only

Try to fix invalid pte type repalayable faults only.
All other replayable faults will be cancelled so that
next mmu fault for same fault address will be triggered
as non-replayable fault and ch/tsg teardown will take place.

Bug 1958308

Change-Id: I63b90ce7c639ee183f87db3e771f253fd04c3567
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1566576
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 22 insertions, 5 deletions

diff --git a/drivers/gpu/nvgpu/gv11b/fb_gv11b.c b/drivers/gpu/nvgpu/gv11b/fb_gv11b.c
index 75045800..d89018e5 100644
--- a/drivers/gpu/nvgpu/gv11b/fb_gv11b.c
+++ b/drivers/gpu/nvgpu/gv11b/fb_gv11b.c
@@ -1434,13 +1434,19 @@ static void gv11b_fb_handle_mmu_fault_common(struct gk20a *g,
                 g->ops.fifo.teardown_ch_tsg(g, act_eng_bitmask,
                         id, id_type, RC_TYPE_MMU_FAULT, mmfault);
         } else {
-                err = gv11b_fb_fix_page_fault(g, mmfault);
-                if (err) {
-                        *invalidate_replay_val |=
-                                fb_mmu_invalidate_replay_cancel_global_f();
+                if (mmfault->fault_type == gmmu_fault_type_pte_v()) {
+                        nvgpu_log(g, gpu_dbg_intr, "invalid pte! try to fix");
+                        err = gv11b_fb_fix_page_fault(g, mmfault);
+                        if (err)
+                                *invalidate_replay_val |=
+                                        fb_mmu_invalidate_replay_cancel_global_f();
+                        else
+                                *invalidate_replay_val |=
+                                        fb_mmu_invalidate_replay_start_ack_all_f();
                 } else {
+                        /* cancel faults other than invalid pte */
                         *invalidate_replay_val |=
-                                fb_mmu_invalidate_replay_start_ack_all_f();
+                                fb_mmu_invalidate_replay_cancel_global_f();
                 }
                 /* refch in mmfault is assigned at the time of copying
                  * fault info from snap reg or bar2 fault buf
@@ -1960,6 +1966,17 @@ static int gv11b_fb_fix_page_fault(struct gk20a *g,
         nvgpu_log(g, gpu_dbg_intr | gpu_dbg_pte,
                         "pte: %#08x %#08x", pte[1], pte[0]);
 
+        if (pte[0] == 0x0 && pte[1] == 0x0) {
+                nvgpu_log(g, gpu_dbg_intr | gpu_dbg_pte,
+                                "pte all zeros, do not set valid");
+                return -1;
+        }
+        if (pte[0] & gmmu_new_pte_valid_true_f()) {
+                nvgpu_log(g, gpu_dbg_intr | gpu_dbg_pte,
+                                "pte valid already set");
+                return -1;
+        }
+
         pte[0] |= gmmu_new_pte_valid_true_f();
         if (pte[0] & gmmu_new_pte_read_only_true_f())
                 pte[0] &= ~(gmmu_new_pte_read_only_true_f());