Problem:
Under certain conditions, when some IP bocks take a RAS error,
we can get into a situation where a GPU reset is not possible
due to issues in RAS in SMU/PSP.
Temporary fix until proper solution in PSP/SMU is ready:
When uncorrectable error happens the DF will unconditionally
broadcast error event packets to all its clients/slave upon
receiving fatal error event and freeze all its outbound queues,
err_event_athub interrupt will be triggered.
In such case and we use this interrupt
to issue GPU reset. THe GPU reset code is modified for such case to avoid HW
reset, only stops schedulers, deatches all in progress and not yet scheduled
job's fences, set error code on them and signals.
Also reject any new incoming job submissions from user space.
All this is done to notify the applications of the problem.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 4 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 98 ++++++++++++++++++++++--------
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 5 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 6 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 30 +++++++--
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 12 +++-
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 10 +--
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 24 ++++----
drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 5 ++
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 32 +++++-----
10 files changed, 164 insertions(+), 62 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9da681e..300adb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -38,6 +38,7 @@
#include "amdgpu_gmc.h"
#include "amdgpu_gem.h"
#include "amdgpu_display.h"
+#include "amdgpu_ras.h"
#if defined(HAVE_DRM_FREE_LARGE)
#define kvfree drm_free_large
@@ -1461,6 +1462,9 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
bool reserved_buffers = false;
int i, r;
+ if (amdgpu_ras_intr_triggered())
+ return -EHWPOISON;
+
if (!adev->accel_working)
return -EBUSY;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 07a4ba0..3ecee10 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3734,10 +3734,10 @@ static bool amdgpu_device_lock_adev(struct amdgpu_device *adev, bool trylock)
return true;
}
-static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
+static void amdgpu_device_unlock_adev(struct amdgpu_device *adev, bool skip_kfd)
{
/*unlock kfd: SRIOV would do it separately */
- if (!amdgpu_sriov_vf(adev))
+ if (!amdgpu_sriov_vf(adev) && !skip_kfd)
amdgpu_amdkfd_post_reset(adev);
amdgpu_vf_error_trans_all(adev);
adev->mp1_state = PP_MP1_STATE_NONE;
@@ -3746,6 +3746,44 @@ static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
}
+#define to_drm_sched_job(sched_job) \
+ container_of((sched_job), struct drm_sched_job, queue_node)
+
+static void amdgpu_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
+{
+ struct drm_sched_job *s_job;
+ struct drm_sched_entity *s_entity = NULL;
+ int i;
+
+ /* Signal all jobs not yet scheduled */
+ for (i = DRM_SCHED_PRIORITY_MAX - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+ struct drm_sched_rq *rq = &sched->sched_rq[i];
+
+ if (!rq)
+ continue;
+
+ spin_lock(&rq->lock);
+ list_for_each_entry(s_entity, &rq->entities, list) {
+ while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {
+ struct drm_sched_fence *s_fence = s_job->s_fence;
+
+ dma_fence_signal(&s_fence->scheduled);
+ dma_fence_set_error(&s_fence->finished, -EHWPOISON);
+ dma_fence_signal(&s_fence->finished);
+ }
+ }
+ spin_unlock(&rq->lock);
+ }
+
+ /* Signal all jobs already scheduled to HW */
+ list_for_each_entry(s_job, &sched->ring_mirror_list, node) {
+ struct drm_sched_fence *s_fence = s_job->s_fence;
+
+ dma_fence_set_error(&s_fence->finished, -EHWPOISON);
+ dma_fence_signal(&s_fence->finished);
+ }
+}
+
/**
* amdgpu_device_gpu_recover - reset the asic and recover scheduler
*
@@ -3765,11 +3803,12 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
struct amdgpu_hive_info *hive = NULL;
struct amdgpu_device *tmp_adev = NULL;
int i, r = 0;
+ bool in_ras_intr = amdgpu_ras_intr_triggered();
need_full_reset = job_signaled = false;
INIT_LIST_HEAD(&device_list);
- dev_info(adev->dev, "GPU reset begin!\n");
+ dev_info(adev->dev, "GPU %s begin!\n", in_ras_intr ? "jobs stop":"reset");
cancel_delayed_work_sync(&adev->delayed_init_work);
@@ -3799,7 +3838,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
/* Build list of devices to reset */
if (adev->gmc.xgmi.num_physical_nodes > 1) {
if (!hive) {
- amdgpu_device_unlock_adev(adev);
+ amdgpu_device_unlock_adev(adev, false);
return -ENODEV;
}
@@ -3824,7 +3863,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
/* block all schedulers and reset given job's ring */
list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
/* disable ras on ALL IPs */
- if (amdgpu_device_ip_need_full_reset(tmp_adev))
+ if (!in_ras_intr && amdgpu_device_ip_need_full_reset(tmp_adev))
amdgpu_ras_suspend(tmp_adev);
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -3834,10 +3873,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
continue;
drm_sched_stop(&ring->sched, job ? &job->base : NULL);
+
+ if (in_ras_intr)
+ amdgpu_stop_all_jobs_on_sched(&ring->sched);
}
}
+ if (in_ras_intr)
+ goto skip_hw_reset;
+
/*
* Must check guilty signal here since after this point all old
* HW fences are force signaled.
@@ -3902,34 +3947,37 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
/* Post ASIC reset for all devs .*/
list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
- for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
- struct amdgpu_ring *ring = tmp_adev->rings[i];
- if (!ring || !ring->sched.thread)
- continue;
+ if (!in_ras_intr) {
+ for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+ struct amdgpu_ring *ring = tmp_adev->rings[i];
- /* No point to resubmit jobs if we didn't HW reset*/
- if (!tmp_adev->asic_reset_res && !job_signaled)
- drm_sched_resubmit_jobs(&ring->sched);
+ if (!ring || !ring->sched.thread)
+ continue;
- drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
- }
+ /* No point to resubmit jobs if we didn't HW reset*/
+ if (!tmp_adev->asic_reset_res && !job_signaled)
+ drm_sched_resubmit_jobs(&ring->sched);
- if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) {
- drm_helper_resume_force_mode(tmp_adev->ddev);
- }
+ drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
+ }
- tmp_adev->asic_reset_res = 0;
+ if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) {
+ drm_helper_resume_force_mode(tmp_adev->ddev);
+ }
- if (r) {
- /* bad news, how to tell it to userspace ? */
- dev_info(tmp_adev->dev, "GPU reset(%d) failed\n", atomic_read(&adev->gpu_reset_counter));
- amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
- } else {
- dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&adev->gpu_reset_counter));
+ tmp_adev->asic_reset_res = 0;
+
+ if (r) {
+ /* bad news, how to tell it to userspace ? */
+ dev_info(tmp_adev->dev, "GPU reset(%d) failed\n", atomic_read(&adev->gpu_reset_counter));
+ amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
+ } else {
+ dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&adev->gpu_reset_counter));
+ }
}
- amdgpu_device_unlock_adev(tmp_adev);
+ amdgpu_device_unlock_adev(tmp_adev, in_ras_intr);
}
if (hive)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 151d7f2..757fd6d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -40,6 +40,8 @@
#include "amdgpu_amdkfd.h"
+#include "amdgpu_ras.h"
+
/*
* KMS wrapper.
* - 3.0.0 - initial driver
@@ -1179,6 +1181,9 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
struct drm_device *dev = pci_get_drvdata(pdev);
struct amdgpu_device *adev = dev->dev_private;
+ if (amdgpu_ras_intr_triggered())
+ return;
+
/* if we are running in a VM, make sure the device
* torn down properly on reboot/shutdown.
* unfortunately we can't detect certain
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index da2143d..ced766c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1046,6 +1046,12 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
/* Ensure IB tests are run on ring */
flush_delayed_work(&adev->delayed_init_work);
+
+ if (amdgpu_ras_intr_triggered()) {
+ DRM_ERROR("RAS Intr triggered, device disabled!!");
+ return -EHWPOISON;
+ }
+
file_priv->driver_priv = NULL;
r = pm_runtime_get_sync(dev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 2d5897a..086e6df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -24,6 +24,8 @@
#include <linux/debugfs.h>
#include <linux/list.h>
#include <linux/module.h>
+#include <linux/reboot.h>
+#include <linux/syscalls.h>
#include "amdgpu.h"
#include "amdgpu_ras.h"
#include "amdgpu_atomfirmware.h"
@@ -64,6 +66,9 @@ const char *ras_block_string[] = {
/* inject address is 52 bits */
#define RAS_UMC_INJECT_ADDR_LIMIT (0x1ULL << 52)
+
+atomic_t amdgpu_ras_in_intr = ATOMIC_INIT(0);
+
static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev,
uint64_t offset, uint64_t size,
struct amdgpu_bo **bo_ptr);
@@ -80,7 +85,7 @@ static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf,
ssize_t s;
char val[128];
- if (amdgpu_ras_error_query(obj->adev, &info))
+ if (amdgpu_ras_error_query(obj->adev, &info, false))
return -EINVAL;
s = snprintf(val, sizeof(val), "%s: %lu\n%s: %lu\n",
@@ -188,6 +193,10 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
return 0;
}
+
+static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
+ struct ras_common_if *head);
+
/**
* DOC: AMDGPU RAS debugfs control interface
*
@@ -304,7 +313,7 @@ static ssize_t amdgpu_ras_sysfs_read(struct device *dev,
.head = obj->head,
};
- if (amdgpu_ras_error_query(obj->adev, &info))
+ if (amdgpu_ras_error_query(obj->adev, &info, false))
return -EINVAL;
return snprintf(buf, PAGE_SIZE, "%s: %lu\n%s: %lu\n",
@@ -591,7 +600,7 @@ static int amdgpu_ras_enable_all_features(struct amdgpu_device *adev,
/* query/inject/cure begin */
int amdgpu_ras_error_query(struct amdgpu_device *adev,
- struct ras_query_if *info)
+ struct ras_query_if *info, bool print)
{
struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
struct ras_err_data err_data = {0, 0, 0, NULL};
@@ -627,12 +636,14 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
info->ue_count = obj->err_data.ue_count;
info->ce_count = obj->err_data.ce_count;
- if (err_data.ce_count)
+ if (err_data.ce_count || print) {
dev_info(adev->dev, "%ld correctable errors detected in %s block\n",
obj->err_data.ce_count, ras_block_str(info->head.block));
- if (err_data.ue_count)
+ }
+ if (err_data.ue_count || print) {
dev_info(adev->dev, "%ld uncorrectable errors detected in %s block\n",
obj->err_data.ue_count, ras_block_str(info->head.block));
+ }
return 0;
}
@@ -702,7 +713,7 @@ int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
.head = obj->head,
};
- if (amdgpu_ras_error_query(adev, &info))
+ if (amdgpu_ras_error_query(adev, &info, true))
return -EINVAL;
data.ce_count += info.ce_count;
@@ -1718,3 +1729,10 @@ int amdgpu_ras_fini(struct amdgpu_device *adev)
return 0;
}
+
+void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
+{
+ if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
+ DRM_WARN("RAS event of type ERREVENT_ATHUB_INTERRUPT detected! Stopping all GPU jobs.\n");
+ }
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 5a0df73..c0e22af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -587,7 +587,7 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev,
struct ras_common_if *head);
int amdgpu_ras_error_query(struct amdgpu_device *adev,
- struct ras_query_if *info);
+ struct ras_query_if *info, bool print);
int amdgpu_ras_error_inject(struct amdgpu_device *adev,
struct ras_inject_if *info);
@@ -600,4 +600,14 @@ int amdgpu_ras_interrupt_remove_handler(struct amdgpu_device *adev,
int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev,
struct ras_dispatch_if *info);
+
+extern atomic_t amdgpu_ras_in_intr;
+
+static inline bool amdgpu_ras_intr_triggered(void)
+{
+ return !!atomic_read(&amdgpu_ras_in_intr);
+}
+
+void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev);
+
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index b2c86a0..e7a83f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -5669,10 +5669,12 @@ static int gfx_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
struct amdgpu_iv_entry *entry)
{
/* TODO ue will trigger an interrupt. */
- kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
- if (adev->gfx.funcs->query_ras_error_count)
- adev->gfx.funcs->query_ras_error_count(adev, err_data);
- amdgpu_ras_reset_gpu(adev, 0);
+ if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) {
+ kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+ if (adev->gfx.funcs->query_ras_error_count)
+ adev->gfx.funcs->query_ras_error_count(adev, err_data);
+ amdgpu_ras_reset_gpu(adev, 0);
+ }
return AMDGPU_RAS_SUCCESS;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 43b4fbc..87a66c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -243,18 +243,20 @@ static int gmc_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
struct ras_err_data *err_data,
struct amdgpu_iv_entry *entry)
{
- kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
- if (adev->umc.funcs->query_ras_error_count)
- adev->umc.funcs->query_ras_error_count(adev, err_data);
- /* umc query_ras_error_address is also responsible for clearing
- * error status
- */
- if (adev->umc.funcs->query_ras_error_address)
- adev->umc.funcs->query_ras_error_address(adev, err_data);
+ if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) {
+ kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+ if (adev->umc.funcs->query_ras_error_count)
+ adev->umc.funcs->query_ras_error_count(adev, err_data);
+ /* umc query_ras_error_address is also responsible for clearing
+ * error status
+ */
+ if (adev->umc.funcs->query_ras_error_address)
+ adev->umc.funcs->query_ras_error_address(adev, err_data);
- /* only uncorrectable error needs gpu reset */
- if (err_data->ue_count)
- amdgpu_ras_reset_gpu(adev, 0);
+ /* only uncorrectable error needs gpu reset */
+ if (err_data->ue_count)
+ amdgpu_ras_reset_gpu(adev, 0);
+ }
return AMDGPU_RAS_SUCCESS;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 367f9d6..545990c 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -30,6 +30,7 @@
#include "nbio/nbio_7_4_0_smn.h"
#include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
#include <uapi/linux/kfd_ioctl.h>
+#include "amdgpu_ras.h"
#define smnNBIF_MGCG_CTRL_LCLK 0x1013a21c
@@ -329,6 +330,8 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
BIF_DOORBELL_INT_CNTL,
RAS_CNTLR_INTERRUPT_CLEAR, 1);
WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+ amdgpu_ras_global_ras_isr(adev);
}
}
@@ -344,6 +347,8 @@ static void nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring(struct amdgpu_d
BIF_DOORBELL_INT_CNTL,
RAS_ATHUB_ERR_EVENT_INTERRUPT_CLEAR, 1);
WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+ amdgpu_ras_global_ras_isr(adev);
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 956432f..438e504 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1972,24 +1972,26 @@ static int sdma_v4_0_process_ras_data_cb(struct amdgpu_device *adev,
uint32_t err_source;
int instance;
- instance = sdma_v4_0_irq_id_to_seq(entry->client_id);
- if (instance < 0)
- return 0;
+ if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) {
+ instance = sdma_v4_0_irq_id_to_seq(entry->client_id);
+ if (instance < 0)
+ return 0;
- switch (entry->src_id) {
- case SDMA0_4_0__SRCID__SDMA_SRAM_ECC:
- err_source = 0;
- break;
- case SDMA0_4_0__SRCID__SDMA_ECC:
- err_source = 1;
- break;
- default:
- return 0;
- }
+ switch (entry->src_id) {
+ case SDMA0_4_0__SRCID__SDMA_SRAM_ECC:
+ err_source = 0;
+ break;
+ case SDMA0_4_0__SRCID__SDMA_ECC:
+ err_source = 1;
+ break;
+ default:
+ return 0;
+ }
- kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+ kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
- amdgpu_ras_reset_gpu(adev, 0);
+ amdgpu_ras_reset_gpu(adev, 0);
+ }
return AMDGPU_RAS_SUCCESS;
}
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
