linux-kernel - [PATCH 05/26] habanalabs: don't notify user about clk throttling due to power

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu,  8 Dec 2022 17:13:29 +0200
From:   Oded Gabbay <ogabbay@...nel.org>
To:     linux-kernel@...r.kernel.org
Cc:     Ofir Bitton <obitton@...ana.ai>
Subject: [PATCH 05/26] habanalabs: don't notify user about clk throttling due to power

From: Ofir Bitton <obitton@...ana.ai>

As clock throttling due to high power consumption can happen very
frequently and there is no real reason to notify the user about it,
we skip this notification in all asics.

Signed-off-by: Ofir Bitton <obitton@...ana.ai>
Reviewed-by: Oded Gabbay <ogabbay@...nel.org>
Signed-off-by: Oded Gabbay <ogabbay@...nel.org>
---
 drivers/misc/habanalabs/gaudi/gaudi.c   | 7 ++++---
 drivers/misc/habanalabs/gaudi2/gaudi2.c | 7 ++++---
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 9f5e208701ba..ae78f838f987 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7584,7 +7584,7 @@ static int tpc_krn_event_to_tpc_id(u16 tpc_dec_event_type)
 	return (tpc_dec_event_type - GAUDI_EVENT_TPC0_KRN_ERR) / 6;
 }
 
-static void gaudi_print_clk_change_info(struct hl_device *hdev, u16 event_type)
+static void gaudi_print_clk_change_info(struct hl_device *hdev, u16 event_type, u64 *event_mask)
 {
 	ktime_t zero_time = ktime_set(0, 0);
 
@@ -7612,6 +7612,7 @@ static void gaudi_print_clk_change_info(struct hl_device *hdev, u16 event_type)
 		hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_THERMAL;
 		hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].start = ktime_get();
 		hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = zero_time;
+		*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
 		dev_info_ratelimited(hdev->dev,
 			"Clock throttling due to overheating\n");
 		break;
@@ -7619,6 +7620,7 @@ static void gaudi_print_clk_change_info(struct hl_device *hdev, u16 event_type)
 	case GAUDI_EVENT_FIX_THERMAL_ENV_E:
 		hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_THERMAL;
 		hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = ktime_get();
+		*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
 		dev_info_ratelimited(hdev->dev,
 			"Thermal envelop is safe, back to optimal clock\n");
 		break;
@@ -7887,8 +7889,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entr
 		break;
 
 	case GAUDI_EVENT_FIX_POWER_ENV_S ... GAUDI_EVENT_FIX_THERMAL_ENV_E:
-		event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
-		gaudi_print_clk_change_info(hdev, event_type);
+		gaudi_print_clk_change_info(hdev, event_type, &event_mask);
 		hl_fw_unmask_irq(hdev, event_type);
 		break;
 
diff --git a/drivers/misc/habanalabs/gaudi2/gaudi2.c b/drivers/misc/habanalabs/gaudi2/gaudi2.c
index e793fb2bdcbe..c14b3bb16f96 100644
--- a/drivers/misc/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/misc/habanalabs/gaudi2/gaudi2.c
@@ -8603,7 +8603,7 @@ static void gaudi2_handle_hbm_mc_spi(struct hl_device *hdev, u64 intr_cause_data
 				hbm_mc_spi[i].cause);
 }
 
-static void gaudi2_print_clk_change_info(struct hl_device *hdev, u16 event_type)
+static void gaudi2_print_clk_change_info(struct hl_device *hdev, u16 event_type, u64 *event_mask)
 {
 	ktime_t zero_time = ktime_set(0, 0);
 
@@ -8629,12 +8629,14 @@ static void gaudi2_print_clk_change_info(struct hl_device *hdev, u16 event_type)
 		hdev->clk_throttling.aggregated_reason |= HL_CLK_THROTTLE_THERMAL;
 		hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].start = ktime_get();
 		hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = zero_time;
+		*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
 		dev_info_ratelimited(hdev->dev, "Clock throttling due to overheating\n");
 		break;
 
 	case GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_E:
 		hdev->clk_throttling.current_reason &= ~HL_CLK_THROTTLE_THERMAL;
 		hdev->clk_throttling.timestamp[HL_CLK_THROTTLE_TYPE_THERMAL].end = ktime_get();
+		*event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
 		dev_info_ratelimited(hdev->dev, "Thermal envelop is safe, back to optimal clock\n");
 		break;
 
@@ -9085,8 +9087,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 	case GAUDI2_EVENT_CPU_FIX_POWER_ENV_E:
 	case GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_S:
 	case GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_E:
-		gaudi2_print_clk_change_info(hdev, event_type);
-		event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
+		gaudi2_print_clk_change_info(hdev, event_type, &event_mask);
 		break;
 
 	case GAUDI2_EVENT_CPU_PKT_QUEUE_OUT_SYNC:
-- 
2.25.1