Merge tag 'misc-habanalabs-fixes-2020-12-30' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux into char-misc-linus

Oded writes:

This tag contains the following fixes for 5.11-rc2:

- Fixes that are needed for supporting the new F/W with security features:
  - Correctly fetch PLL information in GOYA when security is enabled in F/W
  - Fix hard-reset support when F/W is in its preboot stage
  - Disable clock gating when initializing the H/W
  - Fix hard-reset procedure
  - Fix PCI controller initialization
- Remove setting of Engine-Barrier in collective wait operations. This
  barrier created a drop in performance
- Retry loading the TPC firmware in case of EINTR during loading
- Fix CS counters
- Register to PCI shutdown callback to fix handling of VM shutdown
- Fix order of status check
- Fix memory leak in reset procedure
- Fix and add comments and fix indentations

* tag 'misc-habanalabs-fixes-2020-12-30' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux:
  habanalabs: Fix memleak in hl_device_reset
  habanalabs: fix order of status check
  habanalabs: register to pci shutdown callback
  habanalabs: add validation cs counter, fix misplaced counters
  habanalabs/gaudi: retry loading TPC f/w on -EINTR
  habanalabs: adjust pci controller init to new firmware
  habanalabs: update comment in hl_boot_if.h
  habanalabs/gaudi: enhance reset message
  habanalabs: full FW hard reset support
  habanalabs/gaudi: disable CGM at HW initialization
  habanalabs: Revise comment to align with mirror list name
  habanalabs/gaudi: do not set EB in collective slave queues
  habanalabs: preboot hard reset support
  habanalabs: remove generic gaudi get_pll_freq function
  habanalabs: fetch PSOC PLL frequency from F/W in goya
  habanalabs: add comment for pll frequency ioctl opcode
  habanalabs: Fix a missing-braces warning

1 files changed, 5 insertions, 0 deletions

diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 8c15a7d336a0..dba3827c43ca 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -279,6 +279,7 @@ enum hl_device_status {
  * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
  * HL_INFO_SYNC_MANAGER  - Retrieve sync manager info per dcore
  * HL_INFO_TOTAL_ENERGY  - Retrieve total energy consumption
+ * HL_INFO_PLL_FREQUENCY - Retrieve PLL frequency
  */
 #define HL_INFO_HW_IP_INFO		0
 #define HL_INFO_HW_EVENTS		1
@@ -425,6 +426,8 @@ struct hl_info_sync_manager {
  * @ctx_device_in_reset_drop_cnt: context dropped due to device in reset
  * @total_max_cs_in_flight_drop_cnt: total dropped due to maximum CS in-flight
  * @ctx_max_cs_in_flight_drop_cnt: context dropped due to maximum CS in-flight
+ * @total_validation_drop_cnt: total dropped due to validation error
+ * @ctx_validation_drop_cnt: context dropped due to validation error
  */
 struct hl_info_cs_counters {
 	__u64 total_out_of_mem_drop_cnt;
@@ -437,6 +440,8 @@ struct hl_info_cs_counters {
 	__u64 ctx_device_in_reset_drop_cnt;
 	__u64 total_max_cs_in_flight_drop_cnt;
 	__u64 ctx_max_cs_in_flight_drop_cnt;
+	__u64 total_validation_drop_cnt;
+	__u64 ctx_validation_drop_cnt;
 };
 
 enum gaudi_dcores {