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.
Signed-off-by: Mukul Joshi <mukul.joshi@xxxxxxx>
Reviewed-by: John Clements <John.Clements@xxxxxxx>
Acked-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 154 ++++++++++++++++++++++++
1 file changed, 154 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index b1c57a5b6e89..02263f509b36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -34,7 +34,9 @@
#include "amdgpu_xgmi.h"
#include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
#include "atom.h"
+#include <asm/mce.h>
+static bool notifier_registered;
static const char *RAS_FS_NAME = "ras";
const char *ras_error_string[] = {
@@ -73,6 +75,11 @@ const char *ras_block_string[] = {
/* typical ECC bad page rate(1 bad page per 100MB VRAM) */
#define RAS_BAD_PAGE_RATE (100 * 1024 * 1024ULL)
+#define GET_MCA_IPID_GPUID(m) (((m) >> 44) & 0xF)
+#define GET_UMC_INST_NIBBLE(m) (((m) >> 20) & 0xF)
+#define GET_CHAN_INDEX_NIBBLE(m) (((m) >> 12) & 0xF)
+#define GPU_ID_OFFSET 8
+
enum amdgpu_ras_retire_page_reservation {
AMDGPU_RAS_RETIRE_PAGE_RESERVED,
AMDGPU_RAS_RETIRE_PAGE_PENDING,
@@ -85,6 +92,7 @@ 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);
+static void amdgpu_register_bad_pages_mca_notifier(void);
void amdgpu_ras_set_error_query_ready(struct amdgpu_device *adev, bool ready)
{
@@ -1978,6 +1986,10 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
goto free;
}
+ if ((adev->asic_type == CHIP_ALDEBARAN) &&
+ (adev->gmc.xgmi.connected_to_cpu))
+ amdgpu_register_bad_pages_mca_notifier();
+
return 0;
free:
@@ -2427,3 +2439,145 @@ void amdgpu_release_ras_context(struct amdgpu_device *adev)
kfree(con);
}
}
+
+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;
+}
+
+static void find_umc_inst_chan_index(struct mce *m, uint32_t *umc_inst,
+ uint32_t *chan_index)
+{
+ uint32_t val1 = 0;
+ uint32_t val2 = 0;
+ uint32_t rem = 0;
+
+ /*
+ * Bit 20-23 provides the UMC instance nibble.
+ * Bit 12-15 provides the channel index nibble.
+ */
+ val1 = GET_UMC_INST_NIBBLE(m->ipid);
+ val2 = GET_CHAN_INDEX_NIBBLE(m->ipid);
+
+ *umc_inst = val1/2;
+ rem = val1%2;
+
+ *chan_index = (4*rem) + val2;
+}
+
+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 chan_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 || !(is_smca_umc_v2(m->bank) && (XEC(m->status, 0x1f) == 0x0)))
+ return NOTIFY_DONE;
+
+ gpu_id = GET_MCA_IPID_GPUID(m->ipid);
+
+ /*
+ * GPU Id is offset by GPU_ID_OFFSET in MCA_IPID_UMC register.
+ */
+ gpu_id -= 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, then print a message and return.
+ */
+ if (mce_is_correctable(m)) {
+ dev_info(adev->dev, "%s: UMC Correctable error detected.",
+ __func__);
+ return NOTIFY_OK;
+ }
+
+ /*
+ * If it is uncorrectable error, then find out UMC instance and
+ * channel index.
+ */
+ find_umc_inst_chan_index(m, &umc_inst, &chan_index);
+
+ dev_info(adev->dev, "Uncorrectable error detected in UMC inst: %d,"
+ " chan_idx: %d", umc_inst, chan_index);
+
+ memset(&err_rec, 0x0, sizeof(struct eeprom_table_record));
+
+ /*
+ * Translate UMC channel address to Physical address
+ */
+ retired_page = ADDR_OF_8KB_BLOCK(m->addr) |
+ ADDR_OF_256B_BLOCK(chan_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 = chan_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_ACCEL,
+};
+
+static void amdgpu_register_bad_pages_mca_notifier(void)
+{
+ /*
+ * Register the x86 notifier with MCE subsystem.
+ * Please note a notifier can be registered only once
+ * with the MCE subsystem.
+ */
+ if (notifier_registered == false) {
+ mce_register_decode_chain(&amdgpu_bad_page_nb);
+ notifier_registered = true;
+ }
+}
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
