Even though the GPU is shut down, during kexec reboot we can have userspace
still running. This is especially true if KEXEC_JUMP is not enabled, because we
do not freeze userspace in this case.
To prevent crashes, track that the GPU is shutdown and prevent get_param() from
accessing GPU resources if we find it shutdown.
This fixes the following crash during kexec reboot on an ARM64 device with adreno GPU:
[ 292.534314] Kernel panic - not syncing: Asynchronous SError Interrupt
[ 292.534323] Hardware name: Google Lazor (rev3 - 8) with LTE (DT)
[ 292.534326] Call trace:
[ 292.534328] dump_backtrace+0x0/0x1d4
[ 292.534337] show_stack+0x20/0x2c
[ 292.534342] dump_stack_lvl+0x60/0x78
[ 292.534347] dump_stack+0x18/0x38
[ 292.534352] panic+0x148/0x3b0
[ 292.534357] nmi_panic+0x80/0x94
[ 292.534364] arm64_serror_panic+0x70/0x7c
[ 292.534369] do_serror+0x0/0x7c
[ 292.534372] do_serror+0x54/0x7c
[ 292.534377] el1h_64_error_handler+0x34/0x4c
[ 292.534381] el1h_64_error+0x7c/0x80
[ 292.534386] el1_interrupt+0x20/0x58
[ 292.534389] el1h_64_irq_handler+0x18/0x24
[ 292.534395] el1h_64_irq+0x7c/0x80
[ 292.534399] local_daif_inherit+0x10/0x18
[ 292.534405] el1h_64_sync_handler+0x48/0xb4
[ 292.534410] el1h_64_sync+0x7c/0x80
[ 292.534414] a6xx_gmu_set_oob+0xbc/0x1fc
[ 292.534422] a6xx_get_timestamp+0x40/0xb4
[ 292.534426] adreno_get_param+0x12c/0x1e0
[ 292.534433] msm_ioctl_get_param+0x64/0x70
[ 292.534440] drm_ioctl_kernel+0xe8/0x158
[ 292.534448] drm_ioctl+0x208/0x320
[ 292.534453] __arm64_sys_ioctl+0x98/0xd0
[ 292.534461] invoke_syscall+0x4c/0x118
[ 292.534467] el0_svc_common+0x98/0x104
[ 292.534473] do_el0_svc+0x30/0x80
[ 292.534478] el0_svc+0x20/0x50
[ 292.534481] el0t_64_sync_handler+0x78/0x108
[ 292.534485] el0t_64_sync+0x1a4/0x1a8
[ 292.534632] Kernel Offset: 0x1a5f800000 from 0xffffffc008000000
[ 292.534635] PHYS_OFFSET: 0x80000000
[ 292.534638] CPU features: 0x40018541,a3300e42
[ 292.534644] Memory Limit: none
Cc: Rob Clark <robdclark@xxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ricardo Ribalda <ribalda@xxxxxxxxxxxx>
Cc: Ross Zwisler <zwisler@xxxxxxxxxx>
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/msm/adreno/adreno_device.c | 1 +
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 2 +-
drivers/gpu/drm/msm/msm_gpu.h | 3 +++
3 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index f0cff62812c3..03d912dc0130 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -612,6 +612,7 @@ static void adreno_shutdown(struct platform_device *pdev)
{
struct msm_gpu *gpu = dev_to_gpu(&pdev->dev);
+ gpu->is_shutdown = true;
WARN_ON_ONCE(adreno_system_suspend(&pdev->dev));
}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 382fb7f9e497..6903c6892469 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -251,7 +251,7 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
/* No pointer params yet */
- if (*len != 0)
+ if (*len != 0 || gpu->is_shutdown)
return -EINVAL;
switch (param) {
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index ff911e7305ce..f18b0a91442b 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -214,6 +214,9 @@ struct msm_gpu {
/* does gpu need hw_init? */
bool needs_hw_init;
+ /* is the GPU shutdown? */
+ bool is_shutdown;
+
/**
* global_faults: number of GPU hangs not attributed to a particular
* address space
--
2.38.1.493.g58b659f92b-goog
