Commit e0171b87 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'add-devlink-health-reporters-for-nix-block' 

George Cherian says:

====================
Add devlink health reporters for NIX block

Devlink health reporters are added for the NIX block.

Address Jakub's comment to add devlink support for error reporting.
https://www.spinics.net/lists/netdev/msg670712.html

This series is in continuation to
https://www.spinics.net/lists/netdev/msg707798.html

Added Documentation for the same.
====================

Link: https://lore.kernel.org/r/20210119100120.2614730-1-george.cherian@marvell.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 9e8789c8 d41b3365

Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst

+70 −0
Original line number Diff line number Diff line
@@ -217,3 +217,73 @@ For example:: 
	 NPA_AF_ERR:

	        NPA Error Interrupt Reg : 4096

	        AQ Doorbell Error





NIX Reporters

-------------

The NIX reporters are responsible for reporting and recovering the following group of errors:



1. GENERAL events



   - Receive mirror/multicast packet drop due to insufficient buffer.

   - SMQ Flush operation.



2. ERROR events



   - Memory Fault due to WQE read/write from multicast/mirror buffer.

   - Receive multicast/mirror replication list error.

   - Receive packet on an unmapped PF.

   - Fault due to NIX_AQ_INST_S read or NIX_AQ_RES_S write.

   - AQ Doorbell Error.



3. RAS events



   - RAS Error Reporting for NIX Receive Multicast/Mirror Entry Structure.

   - RAS Error Reporting for WQE/Packet Data read from Multicast/Mirror Buffer..

   - RAS Error Reporting for NIX_AQ_INST_S/NIX_AQ_RES_S.



4. RVU events



   - Error due to unmapped slot.



Sample Output::



	~# ./devlink health

	pci/0002:01:00.0:

	  reporter hw_npa_intr

	    state healthy error 0 recover 0 grace_period 0 auto_recover true auto_dump true

	  reporter hw_npa_gen

	    state healthy error 0 recover 0 grace_period 0 auto_recover true auto_dump true

	  reporter hw_npa_err

	    state healthy error 0 recover 0 grace_period 0 auto_recover true auto_dump true

	  reporter hw_npa_ras

	    state healthy error 0 recover 0 grace_period 0 auto_recover true auto_dump true

	  reporter hw_nix_intr

	    state healthy error 1121 recover 1121 last_dump_date 2021-01-19 last_dump_time 05:42:26 grace_period 0 auto_recover true auto_dump true

	  reporter hw_nix_gen

	    state healthy error 949 recover 949 last_dump_date 2021-01-19 last_dump_time 05:42:43 grace_period 0 auto_recover true auto_dump true

	  reporter hw_nix_err

	    state healthy error 1147 recover 1147 last_dump_date 2021-01-19 last_dump_time 05:42:59 grace_period 0 auto_recover true auto_dump true

	  reporter hw_nix_ras

	    state healthy error 409 recover 409 last_dump_date 2021-01-19 last_dump_time 05:43:16 grace_period 0 auto_recover true auto_dump true



Each reporter dumps the



 - Error Type

 - Error Register value

 - Reason in words



For example::



	~# devlink health dump show pci/0002:01:00.0 reporter hw_nix_intr

	 NIX_AF_RVU:

	        NIX RVU Interrupt Reg : 1

	        Unmap Slot Error

	~# devlink health dump show pci/0002:01:00.0 reporter hw_nix_gen

	 NIX_AF_GENERAL:

	        NIX General Interrupt Reg : 1

	        Rx multicast pkt drop

	~# devlink health dump show pci/0002:01:00.0 reporter hw_nix_err

	 NIX_AF_ERR:

	        NIX Error Interrupt Reg : 64

	        Rx on unmapped PF_FUNC

drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c

+651 −1

File changed.

Preview size limit exceeded, changes collapsed.

drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.h

+27 −0
Original line number Diff line number Diff line
@@ -41,11 +41,38 @@ struct rvu_npa_health_reporters { 
	struct work_struct              ras_work;

};



enum nix_af_rvu_health {

	NIX_AF_RVU_INTR,

	NIX_AF_RVU_GEN,

	NIX_AF_RVU_ERR,

	NIX_AF_RVU_RAS,

};



struct rvu_nix_event_ctx {

	u64 nix_af_rvu_int;

	u64 nix_af_rvu_gen;

	u64 nix_af_rvu_err;

	u64 nix_af_rvu_ras;

};



struct rvu_nix_health_reporters {

	struct rvu_nix_event_ctx *nix_event_ctx;

	struct devlink_health_reporter *rvu_hw_nix_intr_reporter;

	struct work_struct		intr_work;

	struct devlink_health_reporter *rvu_hw_nix_gen_reporter;

	struct work_struct		gen_work;

	struct devlink_health_reporter *rvu_hw_nix_err_reporter;

	struct work_struct		err_work;

	struct devlink_health_reporter *rvu_hw_nix_ras_reporter;

	struct work_struct		ras_work;

};



struct rvu_devlink {

	struct devlink *dl;

	struct rvu *rvu;

	struct workqueue_struct *devlink_wq;

	struct rvu_npa_health_reporters *rvu_npa_health_reporter;

	struct rvu_nix_health_reporters *rvu_nix_health_reporter;

};



/* Devlink APIs */

drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h

+10 −0
Original line number Diff line number Diff line
@@ -74,6 +74,16 @@ enum npa_af_int_vec_e { 
	NPA_AF_INT_VEC_CNT	= 0x5,

};



/* NIX Admin function Interrupt Vector Enumeration */

enum nix_af_int_vec_e {

	NIX_AF_INT_VEC_RVU	= 0x0,

	NIX_AF_INT_VEC_GEN	= 0x1,

	NIX_AF_INT_VEC_AQ_DONE	= 0x2,

	NIX_AF_INT_VEC_AF_ERR	= 0x3,

	NIX_AF_INT_VEC_POISON	= 0x4,

	NIX_AF_INT_VEC_CNT	= 0x5,

};



/**

 * RVU PF Interrupt Vector Enumeration

 */