Merge branch 'add-devlink-and-devlink-health-reporters-to'

George Cherian says:

====================
Add devlink and devlink health reporters to octeontx2

Add basic devlink and devlink health reporters.
Devlink health reporters are added for NPA block.

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

For now, I have dropped the NIX block health reporters.
This series attempts to add health reporters only for the NPA block.
As per Jakub's suggestion separate reporters per event is used and also
got rid of the counters.
====================

Link: https://lore.kernel.org/r/20201211062526.2302643-1-george.cherian@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -12,6 +12,7 @@ Contents
 - `Overview`_
 - `Drivers`_
 - `Basic packet flow`_
+- `Devlink health reporters`_
 
 Overview
 ========
@@ -157,3 +158,52 @@ Egress
 3. The SQ descriptor ring is maintained in buffers allocated from SQ mapped pool of NPA block LF.
 4. NIX block transmits the pkt on the designated channel.
 5. NPC MCAM entries can be installed to divert pkt onto a different channel.
+
+Devlink health reporters
+========================
+
+NPA Reporters
+-------------
+The NPA reporters are responsible for reporting and recovering the following group of errors
+1. GENERAL events
+   - Error due to operation of unmapped PF.
+   - Error due to disabled alloc/free for other HW blocks (NIX, SSO, TIM, DPI and AURA).
+2. ERROR events
+   - Fault due to NPA_AQ_INST_S read or NPA_AQ_RES_S write.
+   - AQ Doorbell Error.
+3. RAS events
+   - RAS Error Reporting for NPA_AQ_INST_S/NPA_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 2872 recover 2872 last_dump_date 2020-12-10 last_dump_time 09:39:09 grace_period 0 auto_recover true auto_dump true
+  reporter hw_npa_gen
+      state healthy error 2872 recover 2872 last_dump_date 2020-12-11 last_dump_time 04:43:04 grace_period 0 auto_recover true auto_dump true
+  reporter hw_npa_err
+      state healthy error 2871 recover 2871 last_dump_date 2020-12-10 last_dump_time 09:39:17 grace_period 0 auto_recover true auto_dump true
+   reporter hw_npa_ras
+      state healthy error 0 recover 0 last_dump_date 2020-12-10 last_dump_time 09:32:40 grace_period 0 auto_recover true auto_dump true
+
+Each reporter dumps the
+ - Error Type
+ - Error Register value
+ - Reason in words
+
+For eg:
+~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_gen
+ NPA_AF_GENERAL:
+         NPA General Interrupt Reg : 1
+         NIX0: free disabled RX
+~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_intr
+ NPA_AF_RVU:
+         NPA RVU Interrupt Reg : 1
+         Unmap Slot Error
+~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_err
+ NPA_AF_ERR:
+        NPA Error Interrupt Reg : 4096
+        AQ Doorbell Error

drivers/net/ethernet/marvell/octeontx2/Kconfig

@@ -9,6 +9,7 @@ config OCTEONTX2_MBOX
 config OCTEONTX2_AF
 	tristate "Marvell OcteonTX2 RVU Admin Function driver"
 	select OCTEONTX2_MBOX
+	select NET_DEVLINK
 	depends on (64BIT && COMPILE_TEST) || ARM64
 	depends on PCI
 	help

drivers/net/ethernet/marvell/octeontx2/af/Makefile

@@ -10,4 +10,4 @@ obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o
 octeontx2_mbox-y := mbox.o rvu_trace.o
 octeontx2_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
 		  rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
-		  rvu_cpt.o
+		  rvu_cpt.o rvu_devlink.o

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

@@ -2826,17 +2826,23 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_flr;
 
+	err = rvu_register_dl(rvu);
+	if (err)
+		goto err_irq;
+
 	rvu_setup_rvum_blk_revid(rvu);
 
 	/* Enable AF's VFs (if any) */
 	err = rvu_enable_sriov(rvu);
 	if (err)
-		goto err_irq;
+		goto err_dl;
 
 	/* Initialize debugfs */
 	rvu_dbg_init(rvu);
 
 	return 0;
+err_dl:
+	rvu_unregister_dl(rvu);
 err_irq:
 	rvu_unregister_interrupts(rvu);
 err_flr:
@@ -2868,6 +2874,7 @@ static void rvu_remove(struct pci_dev *pdev)
 
 	rvu_dbg_exit(rvu);
 	rvu_unregister_interrupts(rvu);
+	rvu_unregister_dl(rvu);
 	rvu_flr_wq_destroy(rvu);
 	rvu_cgx_exit(rvu);
 	rvu_fwdata_exit(rvu);

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

@@ -12,7 +12,10 @@
 #define RVU_H
 
 #include <linux/pci.h>
+#include <net/devlink.h>
+
 #include "rvu_struct.h"
+#include "rvu_devlink.h"
 #include "common.h"
 #include "mbox.h"
 #include "npc.h"
@@ -422,6 +425,7 @@ struct rvu {
 #ifdef CONFIG_DEBUG_FS
 	struct rvu_debugfs	rvu_dbg;
 #endif
+	struct rvu_devlink	*rvu_dl;
 };
 
 static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)