[PATCH 3/4] habanalabs/gaudi: use HBM_ECC_EN bit for ECC ERR

From: Oded Gabbay
Date: Tue Feb 02 2021 - 12:11:38 EST


From: Ohad Sharabi <osharabi@xxxxxxxxx>

driver should use ECC info from FW only if HBM ECC CAP is set.
otherwise, try to fetch the data from MC regs only if security is
disabled.

Signed-off-by: Ohad Sharabi <osharabi@xxxxxxxxx>
Reviewed-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
Signed-off-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
---
drivers/misc/habanalabs/gaudi/gaudi.c | 18 +++++++++++++++---
1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 8fc0de3cf3a9..b929e602fa3d 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7105,7 +7105,9 @@ static int gaudi_hbm_read_interrupts(struct hl_device *hdev, int device,
u32 base, val, val2, wr_par, rd_par, ca_par, derr, serr, type, ch;
int err = 0;

- if (!hdev->asic_prop.fw_security_disabled) {
+ if (hdev->asic_prop.fw_security_status_valid &&
+ (hdev->asic_prop.fw_app_security_map &
+ CPU_BOOT_DEV_STS0_HBM_ECC_EN)) {
if (!hbm_ecc_data) {
dev_err(hdev->dev, "No FW ECC data");
return 0;
@@ -7127,14 +7129,24 @@ static int gaudi_hbm_read_interrupts(struct hl_device *hdev, int device,
le32_to_cpu(hbm_ecc_data->hbm_ecc_info));

dev_err(hdev->dev,
- "HBM%d pc%d ECC: TYPE=%d, WR_PAR=%d, RD_PAR=%d, CA_PAR=%d, SERR=%d, DERR=%d\n",
- device, ch, type, wr_par, rd_par, ca_par, serr, derr);
+ "HBM%d pc%d interrupts info: WR_PAR=%d, RD_PAR=%d, CA_PAR=%d, SERR=%d, DERR=%d\n",
+ device, ch, wr_par, rd_par, ca_par, serr, derr);
+ dev_err(hdev->dev,
+ "HBM%d pc%d ECC info: 1ST_ERR_ADDR=0x%x, 1ST_ERR_TYPE=%d, SEC_CONT_CNT=%u, SEC_CNT=%d, DEC_CNT=%d\n",
+ device, ch, hbm_ecc_data->first_addr, type,
+ hbm_ecc_data->sec_cont_cnt, hbm_ecc_data->sec_cnt,
+ hbm_ecc_data->dec_cnt);

err = 1;

return 0;
}

+ if (!hdev->asic_prop.fw_security_disabled) {
+ dev_info(hdev->dev, "Cannot access MC regs for ECC data while security is enabled\n");
+ return 0;
+ }
+
base = GAUDI_HBM_CFG_BASE + device * GAUDI_HBM_CFG_OFFSET;
for (ch = 0 ; ch < GAUDI_HBM_CHANNELS ; ch++) {
val = RREG32_MASK(base + ch * 0x1000 + 0x06C, 0x0000FFFF);
--
2.25.1