[PATCHv2 2/2] drm/amdgpu: Register MCE notifier for Aldebaran RAS

From: Mukul Joshi
Date: Sun Sep 12 2021 - 22:14:43 EST


On Aldebaran, GPU driver will handle bad page retirement
even though UMC is host managed. As a result, register a
bad page retirement handler on the mce notifier chain to
retire bad pages on Aldebaran.

v1->v2:
- Use smca_get_bank_type() to determine MCA bank.
- Envelope the changes under #ifdef CONFIG_X86_MCE_AMD.
- Use MCE_PRIORITY_UC instead of MCE_PRIO_ACCEL as we are
only handling uncorrectable errors.
- Use macros to determine UMC instance and channel instance
where the uncorrectable error occured.
- Update the headline.

Signed-off-by: Mukul Joshi <mukul.joshi@xxxxxxx>
Link: https://lore.kernel.org/amd-gfx/20210512013058.6827-1-mukul.joshi@xxxxxxx/
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 142 ++++++++++++++++++++++++
1 file changed, 142 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index b5332db4d287..35cfcc71ff94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -35,7 +35,11 @@
#include "amdgpu_xgmi.h"
#include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
#include "atom.h"
+#ifdef CONFIG_X86_MCE_AMD
+#include <asm/mce.h>

+static bool notifier_registered;
+#endif
static const char *RAS_FS_NAME = "ras";

const char *ras_error_string[] = {
@@ -86,6 +90,9 @@ static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
uint64_t addr);
static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
uint64_t addr);
+#ifdef CONFIG_X86_MCE_AMD
+static void amdgpu_register_bad_pages_mca_notifier(void);
+#endif

void amdgpu_ras_set_error_query_ready(struct amdgpu_device *adev, bool ready)
{
@@ -2018,6 +2025,11 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.ras_num_recs);
}

+#ifdef CONFIG_X86_MCE_AMD
+ if ((adev->asic_type == CHIP_ALDEBARAN) &&
+ (adev->gmc.xgmi.connected_to_cpu))
+ amdgpu_register_bad_pages_mca_notifier();
+#endif
return 0;

free:
@@ -2511,3 +2523,133 @@ void amdgpu_release_ras_context(struct amdgpu_device *adev)
kfree(con);
}
}
+
+#ifdef CONFIG_X86_MCE_AMD
+static struct amdgpu_device *find_adev(uint32_t node_id)
+{
+ struct amdgpu_gpu_instance *gpu_instance;
+ int i;
+ struct amdgpu_device *adev = NULL;
+
+ mutex_lock(&mgpu_info.mutex);
+
+ for (i = 0; i < mgpu_info.num_gpu; i++) {
+ gpu_instance = &(mgpu_info.gpu_ins[i]);
+ adev = gpu_instance->adev;
+
+ if (adev->gmc.xgmi.connected_to_cpu &&
+ adev->gmc.xgmi.physical_node_id == node_id)
+ break;
+ adev = NULL;
+ }
+
+ mutex_unlock(&mgpu_info.mutex);
+
+ return adev;
+}
+
+#define GET_MCA_IPID_GPUID(m) (((m) >> 44) & 0xF)
+#define GET_UMC_INST(m) (((m) >> 21) & 0x7)
+#define GET_CHAN_INDEX(m) ((((m) >> 12) & 0x3) | (((m) >> 18) & 0x4))
+#define GPU_ID_OFFSET 8
+
+static int amdgpu_bad_page_notifier(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ struct mce *m = (struct mce *)data;
+ struct amdgpu_device *adev = NULL;
+ uint32_t gpu_id = 0;
+ uint32_t umc_inst = 0;
+ uint32_t ch_inst, channel_index = 0;
+ struct ras_err_data err_data = {0, 0, 0, NULL};
+ struct eeprom_table_record err_rec;
+ uint64_t retired_page;
+
+ /*
+ * If the error was generated in UMC_V2, which belongs to GPU UMCs,
+ * and error occurred in DramECC (Extended error code = 0) then only
+ * process the error, else bail out.
+ */
+ if (!m || !((smca_get_bank_type(m->bank) == SMCA_UMC_V2) &&
+ (XEC(m->status, 0x1f) == 0x0)))
+ return NOTIFY_DONE;
+
+ /*
+ * GPU Id is offset by GPU_ID_OFFSET in MCA_IPID_UMC register.
+ */
+ gpu_id = GET_MCA_IPID_GPUID(m->ipid) - GPU_ID_OFFSET;
+
+ adev = find_adev(gpu_id);
+ if (!adev) {
+ dev_warn(adev->dev, "%s: Unable to find adev for gpu_id: %d\n",
+ __func__, gpu_id);
+ return NOTIFY_DONE;
+ }
+
+ /*
+ * If it is correctable error, return.
+ */
+ if (mce_is_correctable(m)) {
+ return NOTIFY_OK;
+ }
+
+ /*
+ * If it is uncorrectable error, then find out UMC instance and
+ * channel index.
+ */
+ umc_inst = GET_UMC_INST(m->ipid);
+ ch_inst = GET_CHAN_INDEX(m->ipid);
+
+ dev_info(adev->dev, "Uncorrectable error detected in UMC inst: %d, chan_idx: %d",
+ umc_inst, ch_inst);
+
+ memset(&err_rec, 0x0, sizeof(struct eeprom_table_record));
+
+ /*
+ * Translate UMC channel address to Physical address
+ */
+ channel_index =
+ adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num
+ + ch_inst];
+
+ retired_page = ADDR_OF_8KB_BLOCK(m->addr) |
+ ADDR_OF_256B_BLOCK(channel_index) |
+ OFFSET_IN_256B_BLOCK(m->addr);
+
+ err_rec.address = m->addr;
+ err_rec.retired_page = retired_page >> AMDGPU_GPU_PAGE_SHIFT;
+ err_rec.ts = (uint64_t)ktime_get_real_seconds();
+ err_rec.err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE;
+ err_rec.cu = 0;
+ err_rec.mem_channel = channel_index;
+ err_rec.mcumc_id = umc_inst;
+
+ err_data.err_addr = &err_rec;
+ err_data.err_addr_cnt = 1;
+
+ if (amdgpu_bad_page_threshold != 0) {
+ amdgpu_ras_add_bad_pages(adev, err_data.err_addr,
+ err_data.err_addr_cnt);
+ amdgpu_ras_save_bad_pages(adev);
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block amdgpu_bad_page_nb = {
+ .notifier_call = amdgpu_bad_page_notifier,
+ .priority = MCE_PRIO_UC,
+};
+
+static void amdgpu_register_bad_pages_mca_notifier(void)
+{
+ /*
+ * Register the x86 notifier only once
+ * with MCE subsystem.
+ */
+ if (notifier_registered == false) {
+ mce_register_decode_chain(&amdgpu_bad_page_nb);
+ notifier_registered = true;
+ }
+}
+#endif
--
2.17.1