habanalabs: fix reset process in case of failures

There are some points in the reset process where if the code fails
for some reason, and the system admin tries to initiate the reset
process again we will get a kernel panic.

This is because there aren't any protections in different fini
functions that are called during the reset process.

The protections that are added in this patch make sure that if the fini
functions are called multiple times, without calling init functions
between them, there won't be double release of already released
resources.

Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 1456eab..1ea57d8 100644 (file)
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -1037,7 +1037,7 @@ kill_processes:
 
        if (hard_reset) {
                /* Release kernel context */
-               if (hl_ctx_put(hdev->kernel_ctx) == 1)
+               if (hdev->kernel_ctx && hl_ctx_put(hdev->kernel_ctx) == 1)
                        hdev->kernel_ctx = NULL;
                hl_vm_fini(hdev);
                hl_mmu_fini(hdev);

diff --git a/drivers/misc/habanalabs/common/mmu_v1.c b/drivers/misc/habanalabs/common/mmu_v1.c
index 2ce6ea8..06d8a44 100644 (file)
--- a/drivers/misc/habanalabs/common/mmu_v1.c
+++ b/drivers/misc/habanalabs/common/mmu_v1.c
@@ -467,8 +467,16 @@ static void hl_mmu_v1_fini(struct hl_device *hdev)
 {
        /* MMU H/W fini was already done in device hw_fini() */
 
-       kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
-       gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
+       if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.hr.mmu_shadow_hop0)) {
+               kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
+               gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
+       }
+
+       /* Make sure that if we arrive here again without init was called we
+        * won't cause kernel panic. This can happen for example if we fail
+        * during hard reset code at certain points
+        */
+       hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL;
 }
 
 /**