From 2846fe5614ac15117fddaa45b86e7e77d91dd569 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Mon, 16 Dec 2024 15:15:33 +0100
Subject: ice: rename devlink_port.[ch] to port.[ch]

Drop "devlink_" prefix from files that sit in devlink/.
I'm going to add more files there, and repeating "devlink" does not feel
good. This is also the scheme used in most other places, most notably the
devlink core files are named like that.

devlink.[ch] stays as is.

Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0ab35607e5d5..d641dd8b8184 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -14,7 +14,7 @@
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
 #include "devlink/devlink.h"
-#include "devlink/devlink_port.h"
+#include "devlink/port.h"
 #include "ice_sf_eth.h"
 #include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
-- 
cgit v1.2.3


From 2a82874a3b7be3f424eb6e94cd4f225e928efe2a Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Mon, 16 Dec 2024 15:15:34 +0100
Subject: ice: add Tx hang devlink health reporter

Add Tx hang devlink health reporter, see struct ice_tx_hang_event to see
what exactly is reported. For now dump descriptors with little metadata
and skb diagnostic information.

Reviewed-by: Igor Bagnucki <igor.bagnucki@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile         |   1 +
 drivers/net/ethernet/intel/ice/devlink/health.c | 192 ++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/devlink/health.h |  47 ++++++
 drivers/net/ethernet/intel/ice/ice.h            |   2 +
 drivers/net/ethernet/intel/ice/ice_main.c       |  18 ++-
 5 files changed, 255 insertions(+), 5 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/ice/devlink/health.c
 create mode 100644 drivers/net/ethernet/intel/ice/devlink/health.h

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 56aa23aee472..9e0d9f710441 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -32,6 +32,7 @@ ice-y := ice_main.o	\
 	 ice_parser_rt.o \
 	 ice_idc.o	\
 	 devlink/devlink.o	\
+	 devlink/health.o \
 	 devlink/port.o \
 	 ice_sf_eth.o	\
 	 ice_sf_vsi_vlan_ops.o \
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c
new file mode 100644
index 000000000000..984d910fc41d
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/devlink/health.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Intel Corporation. */
+
+#include "health.h"
+#include "ice.h"
+
+#define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \
+	devlink_fmsg_put(fmsg, #name, (obj)->name)
+
+/**
+ * ice_devlink_health_report - boilerplate to call given @reporter
+ *
+ * @reporter: devlink health reporter to call, do nothing on NULL
+ * @msg: message to pass up, "event name" is fine
+ * @priv_ctx: typically some event struct
+ */
+static void ice_devlink_health_report(struct devlink_health_reporter *reporter,
+				      const char *msg, void *priv_ctx)
+{
+	if (!reporter)
+		return;
+
+	/* We do not do auto recovering, so return value of the below function
+	 * will always be 0, thus we do ignore it.
+	 */
+	devlink_health_report(reporter, msg, priv_ctx);
+}
+
+/**
+ * ice_fmsg_put_ptr - put hex value of pointer into fmsg
+ *
+ * @fmsg: devlink fmsg under construction
+ * @name: name to pass
+ * @ptr: 64 bit value to print as hex and put into fmsg
+ */
+static void ice_fmsg_put_ptr(struct devlink_fmsg *fmsg, const char *name,
+			     void *ptr)
+{
+	char buf[sizeof(ptr) * 3];
+
+	sprintf(buf, "%p", ptr);
+	devlink_fmsg_put(fmsg, name, buf);
+}
+
+struct ice_tx_hang_event {
+	u32 head;
+	u32 intr;
+	u16 vsi_num;
+	u16 queue;
+	u16 next_to_clean;
+	u16 next_to_use;
+	struct ice_tx_ring *tx_ring;
+};
+
+static int ice_tx_hang_reporter_dump(struct devlink_health_reporter *reporter,
+				     struct devlink_fmsg *fmsg, void *priv_ctx,
+				     struct netlink_ext_ack *extack)
+{
+	struct ice_tx_hang_event *event = priv_ctx;
+	struct sk_buff *skb;
+
+	if (!event)
+		return 0;
+
+	skb = event->tx_ring->tx_buf->skb;
+	devlink_fmsg_obj_nest_start(fmsg);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, head);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, intr);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, vsi_num);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, queue);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_clean);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, event, next_to_use);
+	devlink_fmsg_put(fmsg, "irq-mapping", event->tx_ring->q_vector->name);
+	ice_fmsg_put_ptr(fmsg, "desc-ptr", event->tx_ring->desc);
+	ice_fmsg_put_ptr(fmsg, "dma-ptr", (void *)(long)event->tx_ring->dma);
+	ice_fmsg_put_ptr(fmsg, "skb-ptr", skb);
+	devlink_fmsg_binary_pair_put(fmsg, "desc", event->tx_ring->desc,
+				     event->tx_ring->count * sizeof(struct ice_tx_desc));
+	devlink_fmsg_dump_skb(fmsg, skb);
+	devlink_fmsg_obj_nest_end(fmsg);
+
+	return 0;
+}
+
+void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring,
+			     u16 vsi_num, u32 head, u32 intr)
+{
+	struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf;
+
+	buf->tx_ring = tx_ring;
+	buf->vsi_num = vsi_num;
+	buf->head = head;
+	buf->intr = intr;
+}
+
+void ice_report_tx_hang(struct ice_pf *pf)
+{
+	struct ice_health_tx_hang_buf *buf = &pf->health_reporters.tx_hang_buf;
+	struct ice_tx_ring *tx_ring = buf->tx_ring;
+
+	struct ice_tx_hang_event ev = {
+		.head = buf->head,
+		.intr = buf->intr,
+		.vsi_num = buf->vsi_num,
+		.queue = tx_ring->q_index,
+		.next_to_clean = tx_ring->next_to_clean,
+		.next_to_use = tx_ring->next_to_use,
+		.tx_ring = tx_ring,
+	};
+
+	ice_devlink_health_report(pf->health_reporters.tx_hang, "Tx hang", &ev);
+}
+
+static struct devlink_health_reporter *
+ice_init_devlink_rep(struct ice_pf *pf,
+		     const struct devlink_health_reporter_ops *ops)
+{
+	struct devlink *devlink = priv_to_devlink(pf);
+	struct devlink_health_reporter *rep;
+	const u64 graceful_period = 0;
+
+	rep = devl_health_reporter_create(devlink, ops, graceful_period, pf);
+	if (IS_ERR(rep)) {
+		struct device *dev = ice_pf_to_dev(pf);
+
+		dev_err(dev, "failed to create devlink %s health report er",
+			ops->name);
+		return NULL;
+	}
+	return rep;
+}
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS(_name) \
+	static const struct devlink_health_reporter_ops ice_ ## _name ## _reporter_ops = { \
+	.name = #_name, \
+	.dump = ice_ ## _name ## _reporter_dump, \
+}
+
+ICE_DEFINE_HEALTH_REPORTER_OPS(tx_hang);
+
+/**
+ * ice_health_init - allocate and init all ice devlink health reporters and
+ * accompanied data
+ *
+ * @pf: PF struct
+ */
+void ice_health_init(struct ice_pf *pf)
+{
+	struct ice_health *reps = &pf->health_reporters;
+
+	reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops);
+}
+
+/**
+ * ice_deinit_devl_reporter - destroy given devlink health reporter
+ * @reporter: reporter to destroy
+ */
+static void ice_deinit_devl_reporter(struct devlink_health_reporter *reporter)
+{
+	if (reporter)
+		devl_health_reporter_destroy(reporter);
+}
+
+/**
+ * ice_health_deinit - deallocate all ice devlink health reporters and
+ * accompanied data
+ *
+ * @pf: PF struct
+ */
+void ice_health_deinit(struct ice_pf *pf)
+{
+	ice_deinit_devl_reporter(pf->health_reporters.tx_hang);
+}
+
+static
+void ice_health_assign_healthy_state(struct devlink_health_reporter *reporter)
+{
+	if (reporter)
+		devlink_health_reporter_state_update(reporter,
+						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+}
+
+/**
+ * ice_health_clear - clear devlink health issues after a reset
+ * @pf: the PF device structure
+ *
+ * Mark the PF in healthy state again after a reset has completed.
+ */
+void ice_health_clear(struct ice_pf *pf)
+{
+	ice_health_assign_healthy_state(pf->health_reporters.tx_hang);
+}
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h
new file mode 100644
index 000000000000..5ce601227acb
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/devlink/health.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024, Intel Corporation. */
+
+#ifndef _HEALTH_H_
+#define _HEALTH_H_
+
+#include <linux/types.h>
+
+/**
+ * DOC: health.h
+ *
+ * This header file stores everything that is needed for broadly understood
+ * devlink health mechanism for ice driver.
+ */
+
+struct ice_pf;
+struct ice_tx_ring;
+
+/**
+ * struct ice_health - stores ice devlink health reporters and accompanied data
+ * @tx_hang: devlink health reporter for tx_hang event
+ * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from
+ *               non-sleeping context
+ * @tx_ring: ring that the hang occurred on
+ * @head: descriptor head
+ * @intr: interrupt register value
+ * @vsi_num: VSI owning the queue that the hang occurred on
+ */
+struct ice_health {
+	struct devlink_health_reporter *tx_hang;
+	struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf,
+		struct ice_tx_ring *tx_ring;
+		u32 head;
+		u32 intr;
+		u16 vsi_num;
+	);
+};
+
+void ice_health_init(struct ice_pf *pf);
+void ice_health_deinit(struct ice_pf *pf);
+void ice_health_clear(struct ice_pf *pf);
+
+void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring,
+			     u16 vsi_num, u32 head, u32 intr);
+void ice_report_tx_hang(struct ice_pf *pf);
+
+#endif /* _HEALTH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2f5d6f974185..71e05d30f0fd 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -78,6 +78,7 @@
 #include "ice_irq.h"
 #include "ice_dpll.h"
 #include "ice_adapter.h"
+#include "devlink/health.h"
 
 #define ICE_BAR0		0
 #define ICE_REQ_DESC_MULTIPLE	32
@@ -665,6 +666,7 @@ struct ice_pf {
 	struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES];
 	struct ice_dplls dplls;
 	struct device *hwmon_dev;
+	struct ice_health health_reporters;
 
 	u8 num_quanta_prof_used;
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index d641dd8b8184..316f5109bd3f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2364,9 +2364,11 @@ static void ice_service_task(struct work_struct *work)
 	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
 	unsigned long start_time = jiffies;
 
-	/* subtasks */
+	if (pf->health_reporters.tx_hang_buf.tx_ring) {
+		ice_report_tx_hang(pf);
+		pf->health_reporters.tx_hang_buf.tx_ring = NULL;
+	}
 
-	/* process reset requests first */
 	ice_reset_subtask(pf);
 
 	/* bail if a reset/recovery cycle is pending or rebuild failed */
@@ -5087,6 +5089,7 @@ static int ice_init_devlink(struct ice_pf *pf)
 		return err;
 
 	ice_devlink_init_regions(pf);
+	ice_health_init(pf);
 	ice_devlink_register(pf);
 
 	return 0;
@@ -5095,6 +5098,7 @@ static int ice_init_devlink(struct ice_pf *pf)
 static void ice_deinit_devlink(struct ice_pf *pf)
 {
 	ice_devlink_unregister(pf);
+	ice_health_deinit(pf);
 	ice_devlink_destroy_regions(pf);
 	ice_devlink_unregister_params(pf);
 }
@@ -7793,6 +7797,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	/* if we get here, reset flow is successful */
 	clear_bit(ICE_RESET_FAILED, pf->state);
 
+	ice_health_clear(pf);
+
 	ice_plug_aux_dev(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
@@ -8283,16 +8289,18 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 
 	if (tx_ring) {
 		struct ice_hw *hw = &pf->hw;
-		u32 head, val = 0;
+		u32 head, intr = 0;
 
 		head = FIELD_GET(QTX_COMM_HEAD_HEAD_M,
 				 rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])));
 		/* Read interrupt register */
-		val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
+		intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, txqueue, tx_ring->next_to_clean,
-			    head, tx_ring->next_to_use, val);
+			    head, tx_ring->next_to_use, intr);
+
+		ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr);
 	}
 
 	pf->tx_timeout_last_recovery = jiffies;
-- 
cgit v1.2.3


From bc1027473986dbbd93f9eb41de33307f9abe1319 Mon Sep 17 00:00:00 2001
From: Ben Shelton <benjamin.h.shelton@intel.com>
Date: Mon, 16 Dec 2024 15:15:35 +0100
Subject: ice: Add MDD logging via devlink health

Add a devlink health reporter for MDD events. The 'dump' handler will
return the information captured in each call to ice_handle_mdd_event().
A device reset (CORER/PFR) will put the reporter back in healthy state.

Signed-off-by: Ben Shelton <benjamin.h.shelton@intel.com>
Reviewed-by: Igor Bagnucki <igor.bagnucki@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Co-developed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/health.c | 77 +++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/devlink/health.h | 11 ++++
 drivers/net/ethernet/intel/ice/ice_main.c       |  6 ++
 3 files changed, 94 insertions(+)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c
index 984d910fc41d..d23ae3aafaa7 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.c
+++ b/drivers/net/ethernet/intel/ice/devlink/health.c
@@ -26,6 +26,79 @@ static void ice_devlink_health_report(struct devlink_health_reporter *reporter,
 	devlink_health_report(reporter, msg, priv_ctx);
 }
 
+struct ice_mdd_event {
+	enum ice_mdd_src src;
+	u16 vf_num;
+	u16 queue;
+	u8 pf_num;
+	u8 event;
+};
+
+static const char *ice_mdd_src_to_str(enum ice_mdd_src src)
+{
+	switch (src) {
+	case ICE_MDD_SRC_TX_PQM:
+		return "tx_pqm";
+	case ICE_MDD_SRC_TX_TCLAN:
+		return "tx_tclan";
+	case ICE_MDD_SRC_TX_TDPU:
+		return "tx_tdpu";
+	case ICE_MDD_SRC_RX:
+		return "rx";
+	default:
+		return "invalid";
+	}
+}
+
+static int
+ice_mdd_reporter_dump(struct devlink_health_reporter *reporter,
+		      struct devlink_fmsg *fmsg, void *priv_ctx,
+		      struct netlink_ext_ack *extack)
+{
+	struct ice_mdd_event *mdd_event = priv_ctx;
+	const char *src;
+
+	if (!mdd_event)
+		return 0;
+
+	src = ice_mdd_src_to_str(mdd_event->src);
+
+	devlink_fmsg_obj_nest_start(fmsg);
+	devlink_fmsg_put(fmsg, "src", src);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, pf_num);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, vf_num);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, event);
+	ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, mdd_event, queue);
+	devlink_fmsg_obj_nest_end(fmsg);
+
+	return 0;
+}
+
+/**
+ * ice_report_mdd_event - Report an MDD event through devlink health
+ * @pf: the PF device structure
+ * @src: the HW block that was the source of this MDD event
+ * @pf_num: the pf_num on which the MDD event occurred
+ * @vf_num: the vf_num on which the MDD event occurred
+ * @event: the event type of the MDD event
+ * @queue: the queue on which the MDD event occurred
+ *
+ * Report an MDD event that has occurred on this PF.
+ */
+void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num,
+			  u16 vf_num, u8 event, u16 queue)
+{
+	struct ice_mdd_event ev = {
+		.src = src,
+		.pf_num = pf_num,
+		.vf_num = vf_num,
+		.event = event,
+		.queue = queue,
+	};
+
+	ice_devlink_health_report(pf->health_reporters.mdd, "MDD event", &ev);
+}
+
 /**
  * ice_fmsg_put_ptr - put hex value of pointer into fmsg
  *
@@ -136,6 +209,7 @@ ice_init_devlink_rep(struct ice_pf *pf,
 	.dump = ice_ ## _name ## _reporter_dump, \
 }
 
+ICE_DEFINE_HEALTH_REPORTER_OPS(mdd);
 ICE_DEFINE_HEALTH_REPORTER_OPS(tx_hang);
 
 /**
@@ -148,6 +222,7 @@ void ice_health_init(struct ice_pf *pf)
 {
 	struct ice_health *reps = &pf->health_reporters;
 
+	reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops);
 	reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops);
 }
 
@@ -169,6 +244,7 @@ static void ice_deinit_devl_reporter(struct devlink_health_reporter *reporter)
  */
 void ice_health_deinit(struct ice_pf *pf)
 {
+	ice_deinit_devl_reporter(pf->health_reporters.mdd);
 	ice_deinit_devl_reporter(pf->health_reporters.tx_hang);
 }
 
@@ -188,5 +264,6 @@ void ice_health_assign_healthy_state(struct devlink_health_reporter *reporter)
  */
 void ice_health_clear(struct ice_pf *pf)
 {
+	ice_health_assign_healthy_state(pf->health_reporters.mdd);
 	ice_health_assign_healthy_state(pf->health_reporters.tx_hang);
 }
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h
index 5ce601227acb..532277fc57d7 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.h
+++ b/drivers/net/ethernet/intel/ice/devlink/health.h
@@ -16,9 +16,17 @@
 struct ice_pf;
 struct ice_tx_ring;
 
+enum ice_mdd_src {
+	ICE_MDD_SRC_TX_PQM,
+	ICE_MDD_SRC_TX_TCLAN,
+	ICE_MDD_SRC_TX_TDPU,
+	ICE_MDD_SRC_RX,
+};
+
 /**
  * struct ice_health - stores ice devlink health reporters and accompanied data
  * @tx_hang: devlink health reporter for tx_hang event
+ * @mdd: devlink health reporter for MDD detection event
  * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from
  *               non-sleeping context
  * @tx_ring: ring that the hang occurred on
@@ -27,6 +35,7 @@ struct ice_tx_ring;
  * @vsi_num: VSI owning the queue that the hang occurred on
  */
 struct ice_health {
+	struct devlink_health_reporter *mdd;
 	struct devlink_health_reporter *tx_hang;
 	struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf,
 		struct ice_tx_ring *tx_ring;
@@ -42,6 +51,8 @@ void ice_health_clear(struct ice_pf *pf);
 
 void ice_prep_tx_hang_report(struct ice_pf *pf, struct ice_tx_ring *tx_ring,
 			     u16 vsi_num, u32 head, u32 intr);
+void ice_report_mdd_event(struct ice_pf *pf, enum ice_mdd_src src, u8 pf_num,
+			  u16 vf_num, u8 event, u16 queue);
 void ice_report_tx_hang(struct ice_pf *pf);
 
 #endif /* _HEALTH_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 316f5109bd3f..1701f7143f24 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1816,6 +1816,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num,
+				     event, queue);
 		wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
 	}
 
@@ -1829,6 +1831,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num,
+				     event, queue);
 		wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX);
 	}
 
@@ -1842,6 +1846,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_rx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event,
+				     queue);
 		wr32(hw, GL_MDET_RX, 0xffffffff);
 	}
 
-- 
cgit v1.2.3


From 258f5f905815979f15d5151d2ea4f20d8e057fe1 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Tue, 5 Nov 2024 13:29:16 +0100
Subject: ice: Add correct PHY lane assignment

Driver always naively assumes, that for PTP purposes, PHY lane to
configure is corresponding to PF ID.

This is not true for some port configurations, e.g.:
- 2x50G per quad, where lanes used are 0 and 2 on each quad, but PF IDs
  are 0 and 1
- 100G per quad on 2 quads, where lanes used are 0 and 4, but PF IDs are
  0 and 1

Use correct PHY lane assignment by getting and parsing port options.
This is read from the NVM by the FW and provided to the driver with
the indication of active port split.

Remove ice_is_muxed_topo(), which is no longer needed.

Fixes: 4409ea1726cb ("ice: Adjust PTP init for 2x50G E825C devices")
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Arkadiusz Kubalewski <Arkadiusz.kubalewski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h |  1 +
 drivers/net/ethernet/intel/ice/ice_common.c     | 51 +++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_common.h     |  1 +
 drivers/net/ethernet/intel/ice/ice_main.c       |  6 +--
 drivers/net/ethernet/intel/ice/ice_ptp.c        | 23 +++++------
 drivers/net/ethernet/intel/ice/ice_ptp.h        |  4 +-
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c     | 26 +------------
 drivers/net/ethernet/intel/ice/ice_type.h       |  1 -
 8 files changed, 68 insertions(+), 45 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index ef14cff9a333..46f9726d9a8a 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1665,6 +1665,7 @@ struct ice_aqc_get_port_options_elem {
 #define ICE_AQC_PORT_OPT_MAX_LANE_25G	5
 #define ICE_AQC_PORT_OPT_MAX_LANE_50G	6
 #define ICE_AQC_PORT_OPT_MAX_LANE_100G	7
+#define ICE_AQC_PORT_OPT_MAX_LANE_200G	8
 
 	u8 global_scid[2];
 	u8 phy_scid[2];
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 496d86cbd13f..532024f34ce4 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -4095,6 +4095,57 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
 
+/**
+ * ice_get_phy_lane_number - Get PHY lane number for current adapter
+ * @hw: pointer to the hw struct
+ *
+ * Return: PHY lane number on success, negative error code otherwise.
+ */
+int ice_get_phy_lane_number(struct ice_hw *hw)
+{
+	struct ice_aqc_get_port_options_elem *options;
+	unsigned int lport = 0;
+	unsigned int lane;
+	int err;
+
+	options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL);
+	if (!options)
+		return -ENOMEM;
+
+	for (lane = 0; lane < ICE_MAX_PORT_PER_PCI_DEV; lane++) {
+		u8 options_count = ICE_AQC_PORT_OPT_MAX;
+		u8 speed, active_idx, pending_idx;
+		bool active_valid, pending_valid;
+
+		err = ice_aq_get_port_options(hw, options, &options_count, lane,
+					      true, &active_idx, &active_valid,
+					      &pending_idx, &pending_valid);
+		if (err)
+			goto err;
+
+		if (!active_valid)
+			continue;
+
+		speed = options[active_idx].max_lane_speed;
+		/* If we don't get speed for this lane, it's unoccupied */
+		if (speed > ICE_AQC_PORT_OPT_MAX_LANE_200G)
+			continue;
+
+		if (hw->pf_id == lport) {
+			kfree(options);
+			return lane;
+		}
+
+		lport++;
+	}
+
+	/* PHY lane not found */
+	err = -ENXIO;
+err:
+	kfree(options);
+	return err;
+}
+
 /**
  * ice_aq_sff_eeprom
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 27208a60cece..fe6f88cfd948 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -193,6 +193,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 int
 ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 		       u8 new_option);
+int ice_get_phy_lane_number(struct ice_hw *hw);
 int
 ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		  u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length,
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0ab35607e5d5..89fa3d53d317 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1144,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	if (link_up == old_link && link_speed == old_link_speed)
 		return 0;
 
-	ice_ptp_link_change(pf, pf->hw.pf_id, link_up);
+	ice_ptp_link_change(pf, link_up);
 
 	if (ice_is_dcb_active(pf)) {
 		if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
@@ -6790,7 +6790,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 		ice_print_link_msg(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
-		ice_ptp_link_change(pf, pf->hw.pf_id, true);
+		ice_ptp_link_change(pf, true);
 	}
 
 	/* Perform an initial read of the statistics registers now to
@@ -7260,7 +7260,7 @@ int ice_down(struct ice_vsi *vsi)
 
 	if (vsi->netdev) {
 		vlan_err = ice_vsi_del_vlan_zero(vsi);
-		ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false);
+		ice_ptp_link_change(vsi->back, false);
 		netif_carrier_off(vsi->netdev);
 		netif_tx_disable(vsi->netdev);
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index a999fface272..efd770dfec44 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1388,10 +1388,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 /**
  * ice_ptp_link_change - Reconfigure PTP after link status change
  * @pf: Board private structure
- * @port: Port for which the PHY start is set
  * @linkup: Link is up or down
  */
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 	struct ice_ptp_port *ptp_port;
 	struct ice_hw *hw = &pf->hw;
@@ -1399,14 +1398,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	if (pf->ptp.state != ICE_PTP_READY)
 		return;
 
-	if (WARN_ON_ONCE(port >= hw->ptp.num_lports))
-		return;
-
 	ptp_port = &pf->ptp.port;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		port *= 2;
-	if (WARN_ON_ONCE(ptp_port->port_num != port))
-		return;
 
 	/* Update cached link status for this port immediately */
 	ptp_port->link_up = linkup;
@@ -3164,10 +3156,17 @@ void ice_ptp_init(struct ice_pf *pf)
 {
 	struct ice_ptp *ptp = &pf->ptp;
 	struct ice_hw *hw = &pf->hw;
-	int err;
+	int lane_num, err;
 
 	ptp->state = ICE_PTP_INITIALIZING;
 
+	lane_num = ice_get_phy_lane_number(hw);
+	if (lane_num < 0) {
+		err = lane_num;
+		goto err_exit;
+	}
+
+	ptp->port.port_num = (u8)lane_num;
 	ice_ptp_init_hw(hw);
 
 	ice_ptp_init_tx_interrupt_mode(pf);
@@ -3188,10 +3187,6 @@ void ice_ptp_init(struct ice_pf *pf)
 	if (err)
 		goto err_exit;
 
-	ptp->port.port_num = hw->pf_id;
-	if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo)
-		ptp->port.port_num = hw->pf_id * 2;
-
 	err = ice_ptp_init_port(pf, &ptp->port);
 	if (err)
 		goto err_exit;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 824e73b677a4..c490d98fd9c6 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -310,7 +310,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 			       enum ice_reset_req reset_type);
 void ice_ptp_init(struct ice_pf *pf);
 void ice_ptp_release(struct ice_pf *pf);
-void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup);
+void ice_ptp_link_change(struct ice_pf *pf, bool linkup);
 #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 {
@@ -358,7 +358,7 @@ static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf,
 }
 static inline void ice_ptp_init(struct ice_pf *pf) { }
 static inline void ice_ptp_release(struct ice_pf *pf) { }
-static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
+static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 {
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index d35f6a4d0cd1..02e84f5b1d45 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -2721,26 +2721,6 @@ static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port,
 	return 0;
 }
 
-/**
- * ice_is_muxed_topo - detect breakout 2x50G topology for E825C
- * @hw: pointer to the HW struct
- *
- * Return: true if it's 2x50 breakout topology, false otherwise
- */
-static bool ice_is_muxed_topo(struct ice_hw *hw)
-{
-	u8 link_topo;
-	bool mux;
-	u32 val;
-
-	val = rd32(hw, GLGEN_SWITCH_MODE_CONFIG);
-	mux = FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, val);
-	val = rd32(hw, GLGEN_MAC_LINK_TOPO);
-	link_topo = FIELD_GET(GLGEN_MAC_LINK_TOPO_LINK_TOPO_M, val);
-
-	return (mux && link_topo == ICE_LINK_TOPO_UP_TO_2_LINKS);
-}
-
 /**
  * ice_ptp_init_phy_e825 - initialize PHY parameters
  * @hw: pointer to the HW struct
@@ -2763,12 +2743,8 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw)
 
 	ice_sb_access_ena_eth56g(hw, true);
 	err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev);
-	if (err || phy_rev != PHY_REVISION_ETH56G) {
+	if (err || phy_rev != PHY_REVISION_ETH56G)
 		ptp->phy_model = ICE_PHY_UNSUP;
-		return;
-	}
-
-	ptp->is_2x50g_muxed_topo = ice_is_muxed_topo(hw);
 }
 
 /* E822 family functions
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index a61026970be5..4a9ef722635f 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -880,7 +880,6 @@ struct ice_ptp_hw {
 	union ice_phy_params phy;
 	u8 num_lports;
 	u8 ports_per_phy;
-	bool is_2x50g_muxed_topo;
 };
 
 /* Port hardware description */
-- 
cgit v1.2.3


From c37dd67c423308c5a58c1a6e5b53229a95e19c3f Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Wed, 2 Oct 2024 13:50:21 +0200
Subject: ice: c827: move wait for FW to ice_init_hw()

Move call to ice_wait_for_fw() from ice_init_dev() into ice_init_hw(),
where it fits better. This requires also to move ice_wait_for_fw()
to ice_common.c.

ice_is_pf_c827() is now used only in ice_common.c, so it could be static.

CC: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 110 +++++++++++++++++++---------
 drivers/net/ethernet/intel/ice/ice_common.h |   1 -
 drivers/net/ethernet/intel/ice/ice_main.c   |  37 ----------
 3 files changed, 75 insertions(+), 73 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index f89bc6ede315..64871ecfe8ef 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -308,6 +308,42 @@ bool ice_is_e825c(struct ice_hw *hw)
 	}
 }
 
+/**
+ * ice_is_pf_c827 - check if pf contains c827 phy
+ * @hw: pointer to the hw struct
+ *
+ * Return: true if the device has c827 phy.
+ */
+static bool ice_is_pf_c827(struct ice_hw *hw)
+{
+	struct ice_aqc_get_link_topo cmd = {};
+	u8 node_part_number;
+	u16 node_handle;
+	int status;
+
+	if (hw->mac_type != ICE_MAC_E810)
+		return false;
+
+	if (hw->device_id != ICE_DEV_ID_E810C_QSFP)
+		return true;
+
+	cmd.addr.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) |
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT);
+	cmd.addr.topo_params.index = 0;
+
+	status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number,
+					 &node_handle);
+
+	if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827)
+		return false;
+
+	if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE)
+		return true;
+
+	return false;
+}
+
 /**
  * ice_clear_pf_cfg - Clear PF configuration
  * @hw: pointer to the hardware structure
@@ -1025,6 +1061,33 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw)
 	}
 }
 
+/**
+ * ice_wait_for_fw - wait for full FW readiness
+ * @hw: pointer to the hardware structure
+ * @timeout: milliseconds that can elapse before timing out
+ *
+ * Return: 0 on success, -ETIMEDOUT on timeout.
+ */
+static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
+{
+	int fw_loading;
+	u32 elapsed = 0;
+
+	while (elapsed <= timeout) {
+		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
+
+		/* firmware was not yet loaded, we have to wait more */
+		if (fw_loading) {
+			elapsed += 100;
+			msleep(100);
+			continue;
+		}
+		return 0;
+	}
+
+	return -ETIMEDOUT;
+}
+
 /**
  * ice_init_hw - main hardware initialization routine
  * @hw: pointer to the hardware structure
@@ -1174,8 +1237,19 @@ int ice_init_hw(struct ice_hw *hw)
 	mutex_init(&hw->tnl_lock);
 	ice_init_chk_recipe_reuse_support(hw);
 
-	return 0;
+	/* Some cards require longer initialization times
+	 * due to necessity of loading FW from an external source.
+	 * This can take even half a minute.
+	 */
+	if (ice_is_pf_c827(hw)) {
+		status = ice_wait_for_fw(hw, 30000);
+		if (status) {
+			dev_err(ice_hw_to_dev(hw), "ice_wait_for_fw timed out");
+			goto err_unroll_fltr_mgmt_struct;
+		}
+	}
 
+	return 0;
 err_unroll_fltr_mgmt_struct:
 	ice_cleanup_fltr_mgmt_struct(hw);
 err_unroll_sched:
@@ -2728,40 +2802,6 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 	ice_recalc_port_limited_caps(hw, &dev_p->common_cap);
 }
 
-/**
- * ice_is_pf_c827 - check if pf contains c827 phy
- * @hw: pointer to the hw struct
- */
-bool ice_is_pf_c827(struct ice_hw *hw)
-{
-	struct ice_aqc_get_link_topo cmd = {};
-	u8 node_part_number;
-	u16 node_handle;
-	int status;
-
-	if (hw->mac_type != ICE_MAC_E810)
-		return false;
-
-	if (hw->device_id != ICE_DEV_ID_E810C_QSFP)
-		return true;
-
-	cmd.addr.topo_params.node_type_ctx =
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) |
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT);
-	cmd.addr.topo_params.index = 0;
-
-	status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number,
-					 &node_handle);
-
-	if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827)
-		return false;
-
-	if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE)
-		return true;
-
-	return false;
-}
-
 /**
  * ice_is_phy_rclk_in_netlist
  * @hw: pointer to the hw struct
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index a68bea3934e3..d12424735686 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -112,7 +112,6 @@ int
 ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 		    struct ice_aqc_get_phy_caps_data *caps,
 		    struct ice_sq_cd *cd);
-bool ice_is_pf_c827(struct ice_hw *hw);
 bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw);
 bool ice_is_clock_mux_in_netlist(struct ice_hw *hw);
 bool ice_is_cgu_in_netlist(struct ice_hw *hw);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1701f7143f24..f0a637cf3d87 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4749,31 +4749,6 @@ static void ice_decfg_netdev(struct ice_vsi *vsi)
 	vsi->netdev = NULL;
 }
 
-/**
- * ice_wait_for_fw - wait for full FW readiness
- * @hw: pointer to the hardware structure
- * @timeout: milliseconds that can elapse before timing out
- */
-static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
-{
-	int fw_loading;
-	u32 elapsed = 0;
-
-	while (elapsed <= timeout) {
-		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
-
-		/* firmware was not yet loaded, we have to wait more */
-		if (fw_loading) {
-			elapsed += 100;
-			msleep(100);
-			continue;
-		}
-		return 0;
-	}
-
-	return -ETIMEDOUT;
-}
-
 int ice_init_dev(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
@@ -4786,18 +4761,6 @@ int ice_init_dev(struct ice_pf *pf)
 		return err;
 	}
 
-	/* Some cards require longer initialization times
-	 * due to necessity of loading FW from an external source.
-	 * This can take even half a minute.
-	 */
-	if (ice_is_pf_c827(hw)) {
-		err = ice_wait_for_fw(hw, 30000);
-		if (err) {
-			dev_err(dev, "ice_wait_for_fw timed out");
-			return err;
-		}
-	}
-
 	ice_init_feature_support(pf);
 
 	err = ice_init_ddp_config(hw, pf);
-- 
cgit v1.2.3


From 4d3f59bfa2cd3193b8bbe724df0a9cd41bdc507d Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Wed, 2 Oct 2024 13:50:22 +0200
Subject: ice: split ice_init_hw() out from ice_init_dev()

Split ice_init_hw() call out from ice_init_dev(). Such move enables
pulling the former to be even earlier on call path, what would enable
moving ice_adapter init to be between the two (in subsequent commit).
Such move enables ice_adapter to know about number of PFs.

Do the same for ice_deinit_hw(), so the init and deinit calls could
be easily mirrored.
Next commit will rename unrelated goto labels to unroll prefix.

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink.c | 10 +++++++++-
 drivers/net/ethernet/intel/ice/ice_main.c        | 22 +++++++++++-----------
 2 files changed, 20 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 1b10682c00b8..d1b9ccec5e05 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1207,9 +1207,15 @@ static int ice_devlink_reinit_up(struct ice_pf *pf)
 	struct ice_vsi *vsi = ice_get_main_vsi(pf);
 	int err;
 
+	err = ice_init_hw(&pf->hw);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err);
+		return err;
+	}
+
 	err = ice_init_dev(pf);
 	if (err)
-		return err;
+		goto unroll_hw_init;
 
 	vsi->flags = ICE_VSI_FLAG_INIT;
 
@@ -1232,6 +1238,8 @@ err_load:
 	rtnl_unlock();
 err_vsi_cfg:
 	ice_deinit_dev(pf);
+unroll_hw_init:
+	ice_deinit_hw(&pf->hw);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f0a637cf3d87..5d7d4a66fbcd 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4755,12 +4755,6 @@ int ice_init_dev(struct ice_pf *pf)
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	err = ice_init_hw(hw);
-	if (err) {
-		dev_err(dev, "ice_init_hw failed: %d\n", err);
-		return err;
-	}
-
 	ice_init_feature_support(pf);
 
 	err = ice_init_ddp_config(hw, pf);
@@ -4781,7 +4775,7 @@ int ice_init_dev(struct ice_pf *pf)
 	err = ice_init_pf(pf);
 	if (err) {
 		dev_err(dev, "ice_init_pf failed: %d\n", err);
-		goto err_init_pf;
+		return err;
 	}
 
 	pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
@@ -4825,8 +4819,6 @@ err_req_irq_msix_misc:
 	ice_clear_interrupt_scheme(pf);
 err_init_interrupt_scheme:
 	ice_deinit_pf(pf);
-err_init_pf:
-	ice_deinit_hw(hw);
 	return err;
 }
 
@@ -5319,9 +5311,15 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		hw->debug_mask = debug;
 #endif
 
+	err = ice_init_hw(hw);
+	if (err) {
+		dev_err(dev, "ice_init_hw failed: %d\n", err);
+		goto unroll_adapter;
+	}
+
 	err = ice_init(pf);
 	if (err)
-		goto err_init;
+		goto unroll_hw_init;
 
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
@@ -5340,7 +5338,9 @@ err_init_devlink:
 err_load:
 	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
-err_init:
+unroll_hw_init:
+	ice_deinit_hw(hw);
+unroll_adapter:
 	ice_adapter_put(pdev);
 	return err;
 }
-- 
cgit v1.2.3


From 5d5d9c2c0fb9d2028f52ed67e7db86a4be03f342 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Wed, 2 Oct 2024 13:50:23 +0200
Subject: ice: minor: rename goto labels from err to unroll

Clean up goto labels after previous commit, to conform to single naming
scheme in ice_probe() and ice_init_dev().

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 5d7d4a66fbcd..7fd79482116f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4799,7 +4799,7 @@ int ice_init_dev(struct ice_pf *pf)
 	if (err) {
 		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
-		goto err_init_interrupt_scheme;
+		goto unroll_pf_init;
 	}
 
 	/* In case of MSIX we are going to setup the misc vector right here
@@ -4810,14 +4810,14 @@ int ice_init_dev(struct ice_pf *pf)
 	err = ice_req_irq_msix_misc(pf);
 	if (err) {
 		dev_err(dev, "setup of misc vector failed: %d\n", err);
-		goto err_req_irq_msix_misc;
+		goto unroll_irq_scheme_init;
 	}
 
 	return 0;
 
-err_req_irq_msix_misc:
+unroll_irq_scheme_init:
 	ice_clear_interrupt_scheme(pf);
-err_init_interrupt_scheme:
+unroll_pf_init:
 	ice_deinit_pf(pf);
 	return err;
 }
@@ -5324,18 +5324,18 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
 	if (err)
-		goto err_load;
+		goto unroll_init;
 
 	err = ice_init_devlink(pf);
 	if (err)
-		goto err_init_devlink;
+		goto unroll_load;
 	devl_unlock(priv_to_devlink(pf));
 
 	return 0;
 
-err_init_devlink:
+unroll_load:
 	ice_unload(pf);
-err_load:
+unroll_init:
 	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
 unroll_hw_init:
-- 
cgit v1.2.3


From fb59a520bbb1055e403c831ab9ff1a88a4848847 Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Wed, 2 Oct 2024 13:50:24 +0200
Subject: ice: ice_probe: init ice_adapter after HW init

Move ice_adapter initialization to be after HW init, so it could use HW
capabilities, like number of PFs. This is needed for devlink-resource
based RSS LUT size management for PF/VF (not in this series).

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 7fd79482116f..f63e485e65f6 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5277,13 +5277,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	}
 
 	pci_set_master(pdev);
-
-	adapter = ice_adapter_get(pdev);
-	if (IS_ERR(adapter))
-		return PTR_ERR(adapter);
-
 	pf->pdev = pdev;
-	pf->adapter = adapter;
 	pci_set_drvdata(pdev, pf);
 	set_bit(ICE_DOWN, pf->state);
 	/* Disable service task until DOWN bit is cleared */
@@ -5314,12 +5308,19 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	err = ice_init_hw(hw);
 	if (err) {
 		dev_err(dev, "ice_init_hw failed: %d\n", err);
-		goto unroll_adapter;
+		return err;
 	}
 
+	adapter = ice_adapter_get(pdev);
+	if (IS_ERR(adapter)) {
+		err = PTR_ERR(adapter);
+		goto unroll_hw_init;
+	}
+	pf->adapter = adapter;
+
 	err = ice_init(pf);
 	if (err)
-		goto unroll_hw_init;
+		goto unroll_adapter;
 
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
@@ -5338,10 +5339,10 @@ unroll_load:
 unroll_init:
 	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
-unroll_hw_init:
-	ice_deinit_hw(hw);
 unroll_adapter:
 	ice_adapter_put(pdev);
+unroll_hw_init:
+	ice_deinit_hw(hw);
 	return err;
 }
 
-- 
cgit v1.2.3


From 85d6164ec56deef2e5692cf8b132115f9317cdf6 Mon Sep 17 00:00:00 2001
From: Konrad Knitter <konrad.knitter@intel.com>
Date: Wed, 11 Dec 2024 12:03:57 +0100
Subject: ice: add fw and port health reporters

Firmware generates events for global events or port specific events.

Driver shall subscribe for health status events from firmware on supported
FW versions >= 1.7.6.
Driver shall expose those under specific health reporter, two new
reporters are introduced:
- FW health reporter shall represent global events (problems with the
image, recovery mode);
- Port health reporter shall represent port-specific events (module
failure).

Firmware only reports problems when those are detected, it does not store
active fault list.
Driver will hold only last global and last port-specific event.
Driver will report all events via devlink health report,
so in case of multiple events of the same source they can be reviewed
using devlink autodump feature.

$ devlink health

pci/0000:b1:00.3:
  reporter fw
    state healthy error 0 recover 0 auto_dump true
  reporter port
    state error error 1 recover 0 last_dump_date 2024-03-17
	last_dump_time 09:29:29 auto_dump true

$ devlink health diagnose pci/0000:b1:00.3 reporter port

  Syndrome: 262
  Description: Module is not present.
  Possible Solution: Check that the module is inserted correctly.
  Port Number: 0

Tested on Intel Corporation Ethernet Controller E810-C for SFP

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Co-developed-by: Sharon Haroni <sharon.haroni@intel.com>
Signed-off-by: Sharon Haroni <sharon.haroni@intel.com>
Co-developed-by: Nicholas Nunley <nicholas.d.nunley@intel.com>
Signed-off-by: Nicholas Nunley <nicholas.d.nunley@intel.com>
Co-developed-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Konrad Knitter <konrad.knitter@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/health.c | 295 +++++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/devlink/health.h |  15 +-
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h |  87 +++++++
 drivers/net/ethernet/intel/ice/ice_common.c     |  38 +++
 drivers/net/ethernet/intel/ice/ice_common.h     |   2 +
 drivers/net/ethernet/intel/ice/ice_main.c       |   3 +
 drivers/net/ethernet/intel/ice/ice_type.h       |   5 +
 7 files changed, 437 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c
index d23ae3aafaa7..ea40f7941259 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.c
+++ b/drivers/net/ethernet/intel/ice/devlink/health.c
@@ -1,12 +1,270 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2024, Intel Corporation. */
 
-#include "health.h"
 #include "ice.h"
+#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */
+#include "health.h"
 
 #define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \
 	devlink_fmsg_put(fmsg, #name, (obj)->name)
 
+#define ICE_HEALTH_STATUS_DATA_SIZE 2
+
+struct ice_health_status {
+	enum ice_aqc_health_status code;
+	const char *description;
+	const char *solution;
+	const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE];
+};
+
+/*
+ * In addition to the health status codes provided below, the firmware might
+ * generate Health Status Codes that are not pertinent to the end-user.
+ * For instance, Health Code 0x1002 is triggered when the command fails.
+ * Such codes should be disregarded by the end-user.
+ * The below lookup requires to be sorted by code.
+ */
+
+static const char *const ice_common_port_solutions =
+	"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.";
+static const char *const ice_port_number_label = "Port Number";
+static const char *const ice_update_nvm_solution = "Update to the latest NVM image.";
+
+static const struct ice_health_status ice_health_status_lookup[] = {
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.",
+		"Change or replace the module or cable.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM,
+		"Device cannot communicate with the module.",
+		"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.",
+		"Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.",
+		"Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.",
+		"Change or replace the module or cable. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.",
+		ice_common_port_solutions, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.",
+		NULL, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.",
+		"Change the module or configure the port option to match the current module speed. Change the port option.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT,
+		"All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.",
+		"Check link partner connection and configuration.",
+		{ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED,
+		"Port speed is limited by PHY capabilities.",
+		"Change the module to align to port option.", {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.",
+		"Change the port option. Update to the latest NVM image."},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD,
+		"Failed to load the firmware image in the external PHY.",
+		ice_update_nvm_solution, {ice_port_number_label}},
+	{ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.",
+		ice_update_nvm_solution, {"Extended Error"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.",
+		"If issue persists, call customer support.", {"Access Type"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.",
+		"Update to latest base driver and DDP package."},
+	{ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.",
+		ice_update_nvm_solution},
+	{ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.",
+		ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}},
+	{ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB,
+		"Supplied MIB file is invalid. DCB reverted to default configuration.",
+		"Disable FW-LLDP and check DCBx system configuration.",
+		{ice_port_number_label, "MIB ID"}},
+};
+
+static int ice_health_status_lookup_compare(const void *a, const void *b)
+{
+	return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code;
+}
+
+static const struct ice_health_status *ice_get_health_status(u16 code)
+{
+	struct ice_health_status key = { .code = code };
+
+	return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup),
+		       sizeof(struct ice_health_status), ice_health_status_lookup_compare);
+}
+
+static void ice_describe_status_code(struct devlink_fmsg *fmsg,
+				     struct ice_aqc_health_status_elem *hse)
+{
+	static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" };
+	const struct ice_health_status *health_code;
+	u32 internal_data[2];
+	u16 status_code;
+
+	status_code = le16_to_cpu(hse->health_status_code);
+
+	devlink_fmsg_put(fmsg, "Syndrome", status_code);
+	if (status_code) {
+		internal_data[0] = le32_to_cpu(hse->internal_data1);
+		internal_data[1] = le32_to_cpu(hse->internal_data2);
+
+		health_code = ice_get_health_status(status_code);
+		if (!health_code)
+			return;
+
+		devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description);
+		if (health_code->solution)
+			devlink_fmsg_string_pair_put(fmsg, "Possible Solution",
+						     health_code->solution);
+
+		for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) {
+			if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA)
+				devlink_fmsg_u32_pair_put(fmsg,
+							  health_code->data_label[i] ?
+							  health_code->data_label[i] :
+							  aux_label[i],
+							  internal_data[i]);
+		}
+	}
+}
+
+static int
+ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			   struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		       void *priv_ctx, struct netlink_ext_ack __always_unused *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.port_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+			 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static int
+ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg,
+		     void *priv_ctx, struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_health_reporter_priv(reporter);
+
+	ice_describe_status_code(fmsg, &pf->health_reporters.fw_status);
+	return 0;
+}
+
+static void ice_config_health_events(struct ice_pf *pf, bool enable)
+{
+	u8 enable_bits = 0;
+	int ret;
+
+	if (enable)
+		enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK |
+			      ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK;
+
+	ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits);
+	if (ret)
+		dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n",
+			str_enable_disable(enable), ret,
+			ice_aq_str(pf->hw.adminq.sq_last_status));
+}
+
+/**
+ * ice_process_health_status_event - Process the health status event from FW
+ * @pf: pointer to the PF structure
+ * @event: event structure containing the Health Status Event opcode
+ *
+ * Decode the Health Status Events and print the associated messages
+ */
+void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	const struct ice_aqc_health_status_elem *health_info;
+	u16 count;
+
+	health_info = (struct ice_aqc_health_status_elem *)event->msg_buf;
+	count = le16_to_cpu(event->desc.params.get_health_status.health_status_count);
+
+	if (count > (event->buf_len / sizeof(*health_info))) {
+		dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n");
+		return;
+	}
+
+	for (size_t i = 0; i < count; i++) {
+		const struct ice_health_status *health_code;
+		u16 status_code;
+
+		status_code = le16_to_cpu(health_info->health_status_code);
+		health_code = ice_get_health_status(status_code);
+
+		if (health_code) {
+			switch (le16_to_cpu(health_info->event_source)) {
+			case ICE_AQC_HEALTH_STATUS_GLOBAL:
+				pf->health_reporters.fw_status = *health_info;
+				devlink_health_report(pf->health_reporters.fw,
+						      "FW syndrome reported", NULL);
+				break;
+			case ICE_AQC_HEALTH_STATUS_PF:
+			case ICE_AQC_HEALTH_STATUS_PORT:
+				pf->health_reporters.port_status = *health_info;
+				devlink_health_report(pf->health_reporters.port,
+						      "Port syndrome reported", NULL);
+				break;
+			default:
+				dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n");
+			}
+		} else {
+			u32 data1, data2;
+			u16 source;
+
+			source = le16_to_cpu(health_info->event_source);
+			data1 = le32_to_cpu(health_info->internal_data1);
+			data2 = le32_to_cpu(health_info->internal_data2);
+			dev_dbg(ice_pf_to_dev(pf),
+				"Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x",
+				status_code, source, data1, data2);
+		}
+		health_info++;
+	}
+}
+
 /**
  * ice_devlink_health_report - boilerplate to call given @reporter
  *
@@ -203,14 +461,26 @@ ice_init_devlink_rep(struct ice_pf *pf,
 	return rep;
 }
 
-#define ICE_DEFINE_HEALTH_REPORTER_OPS(_name) \
-	static const struct devlink_health_reporter_ops ice_ ## _name ## _reporter_ops = { \
+#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \
+	._field = ice_##_name##_reporter_##_field,
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
 	.name = #_name, \
-	.dump = ice_ ## _name ## _reporter_dump, \
-}
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	}
+
+#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \
+	static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \
+	.name = #_name, \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \
+	ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \
+	}
 
-ICE_DEFINE_HEALTH_REPORTER_OPS(mdd);
-ICE_DEFINE_HEALTH_REPORTER_OPS(tx_hang);
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose);
+ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose);
 
 /**
  * ice_health_init - allocate and init all ice devlink health reporters and
@@ -224,6 +494,12 @@ void ice_health_init(struct ice_pf *pf)
 
 	reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops);
 	reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops);
+
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops);
+		reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops);
+		ice_config_health_events(pf, true);
+	}
 }
 
 /**
@@ -246,6 +522,11 @@ void ice_health_deinit(struct ice_pf *pf)
 {
 	ice_deinit_devl_reporter(pf->health_reporters.mdd);
 	ice_deinit_devl_reporter(pf->health_reporters.tx_hang);
+	if (ice_is_fw_health_report_supported(&pf->hw)) {
+		ice_deinit_devl_reporter(pf->health_reporters.fw);
+		ice_deinit_devl_reporter(pf->health_reporters.port);
+		ice_config_health_events(pf, false);
+	}
 }
 
 static
diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h
index 532277fc57d7..5edfc4d2adce 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.h
+++ b/drivers/net/ethernet/intel/ice/devlink/health.h
@@ -13,8 +13,10 @@
  * devlink health mechanism for ice driver.
  */
 
+struct ice_aqc_health_status_elem;
 struct ice_pf;
 struct ice_tx_ring;
+struct ice_rq_event_info;
 
 enum ice_mdd_src {
 	ICE_MDD_SRC_TX_PQM,
@@ -25,17 +27,23 @@ enum ice_mdd_src {
 
 /**
  * struct ice_health - stores ice devlink health reporters and accompanied data
- * @tx_hang: devlink health reporter for tx_hang event
+ * @fw: devlink health reporter for FW Health Status events
  * @mdd: devlink health reporter for MDD detection event
+ * @port: devlink health reporter for Port Health Status events
+ * @tx_hang: devlink health reporter for tx_hang event
  * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from
  *               non-sleeping context
  * @tx_ring: ring that the hang occurred on
  * @head: descriptor head
  * @intr: interrupt register value
  * @vsi_num: VSI owning the queue that the hang occurred on
+ * @fw_status: buffer for last received FW Status event
+ * @port_status: buffer for last received Port Status event
  */
 struct ice_health {
+	struct devlink_health_reporter *fw;
 	struct devlink_health_reporter *mdd;
+	struct devlink_health_reporter *port;
 	struct devlink_health_reporter *tx_hang;
 	struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf,
 		struct ice_tx_ring *tx_ring;
@@ -43,8 +51,13 @@ struct ice_health {
 		u32 intr;
 		u16 vsi_num;
 	);
+	struct ice_aqc_health_status_elem fw_status;
+	struct ice_aqc_health_status_elem port_status;
 };
 
+void ice_process_health_status_event(struct ice_pf *pf,
+				     struct ice_rq_event_info *event);
+
 void ice_health_init(struct ice_pf *pf);
 void ice_health_deinit(struct ice_pf *pf);
 void ice_health_clear(struct ice_pf *pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 73f5fddf3ee9..dd41a4dcc0b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -2517,6 +2517,87 @@ enum ice_aqc_fw_logging_mod {
 	ICE_AQC_FW_LOG_ID_MAX,
 };
 
+enum ice_aqc_health_status_mask {
+	ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0),
+	ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK      = BIT(1),
+	ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK      = BIT(2),
+};
+
+/* Set Health Status (direct 0xFF20) */
+struct ice_aqc_set_health_status_cfg {
+	u8 event_source;
+	u8 reserved[15];
+};
+
+enum ice_aqc_health_status {
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT		= 0x101,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE			= 0x102,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL			= 0x103,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM			= 0x104,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT			= 0x105,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT		= 0x106,
+	ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED		= 0x107,
+	ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT		= 0x108,
+	ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE	= 0x109,
+	ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG		= 0x10B,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS			= 0x10C,
+	ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE		= 0x10D,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED	= 0x10F,
+	ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT		= 0x110,
+	ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED	= 0x111,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO			= 0x112,
+	ICE_AQC_HEALTH_STATUS_ERR_NETLIST			= 0x113,
+	ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT			= 0x114,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS		= 0x115,
+	ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME			= 0x116,
+	ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT			= 0x117,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG			= 0x120,
+	ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD			= 0x121,
+	ICE_AQC_HEALTH_STATUS_INFO_RECOVERY			= 0x500,
+	ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS			= 0x501,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH			= 0x502,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH			= 0x503,
+	ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH			= 0x504,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT			= 0x505,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT			= 0x506,
+	ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION		= 0x507,
+	ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION		= 0x508,
+	ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB			= 0x509,
+	ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT			= 0x50A,
+	ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET			= 0x50B,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL			= 0x50C,
+	ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL		= 0x50D,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP			= 0x1000,
+	ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL			= 0x1001,
+	ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ			= 0x1002,
+};
+
+/* Get Health Status (indirect 0xFF22) */
+struct ice_aqc_get_health_status {
+	__le16 health_status_count;
+	u8 reserved[6];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+enum ice_aqc_health_status_scope {
+	ICE_AQC_HEALTH_STATUS_PF	= 0x1,
+	ICE_AQC_HEALTH_STATUS_PORT	= 0x2,
+	ICE_AQC_HEALTH_STATUS_GLOBAL	= 0x3,
+};
+
+#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA	0xDEADBEEF
+
+/* Get Health Status event buffer entry (0xFF22),
+ * repeated per reported health status.
+ */
+struct ice_aqc_health_status_elem {
+	__le16 health_status_code;
+	__le16 event_source;
+	__le32 internal_data1;
+	__le32 internal_data2;
+};
+
 /* Set FW Logging configuration (indirect 0xFF30)
  * Register for FW Logging (indirect 0xFF31)
  * Query FW Logging (indirect 0xFF32)
@@ -2657,6 +2738,8 @@ struct ice_aq_desc {
 		struct ice_aqc_get_link_status get_link_status;
 		struct ice_aqc_event_lan_overflow lan_overflow;
 		struct ice_aqc_get_link_topo get_link_topo;
+		struct ice_aqc_set_health_status_cfg set_health_status_cfg;
+		struct ice_aqc_get_health_status get_health_status;
 		struct ice_aqc_dnl_call_command dnl_call;
 		struct ice_aqc_i2c read_write_i2c;
 		struct ice_aqc_read_i2c_resp read_i2c_resp;
@@ -2859,6 +2942,10 @@ enum ice_adminq_opc {
 	/* Standalone Commands/Events */
 	ice_aqc_opc_event_lan_overflow			= 0x1001,
 
+	/* System Diagnostic commands */
+	ice_aqc_opc_set_health_status_cfg		= 0xFF20,
+	ice_aqc_opc_get_health_status			= 0xFF22,
+
 	/* FW Logging Commands */
 	ice_aqc_opc_fw_logs_config			= 0xFF30,
 	ice_aqc_opc_fw_logs_register			= 0xFF31,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 64871ecfe8ef..7af169466655 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -5892,6 +5892,44 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps)
 	return false;
 }
 
+/**
+ * ice_is_fw_health_report_supported - checks if firmware supports health events
+ * @hw: pointer to the hardware structure
+ *
+ * Return: true if firmware supports health status reports,
+ * false otherwise
+ */
+bool ice_is_fw_health_report_supported(struct ice_hw *hw)
+{
+	return ice_is_fw_api_min_ver(hw, ICE_FW_API_HEALTH_REPORT_MAJ,
+				     ICE_FW_API_HEALTH_REPORT_MIN,
+				     ICE_FW_API_HEALTH_REPORT_PATCH);
+}
+
+/**
+ * ice_aq_set_health_status_cfg - Configure FW health events
+ * @hw: pointer to the HW struct
+ * @event_source: type of diagnostic events to enable
+ *
+ * Configure the health status event types that the firmware will send to this
+ * PF. The supported event types are: PF-specific, all PFs, and global.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source)
+{
+	struct ice_aqc_set_health_status_cfg *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.set_health_status_cfg;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg);
+
+	cmd->event_source = event_source;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+}
+
 /**
  * ice_aq_set_lldp_mib - Set the LLDP MIB
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index d12424735686..0a35fcdc6eb5 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -141,6 +141,8 @@ int
 ice_get_link_default_override(struct ice_link_default_override_tlv *ldo,
 			      struct ice_port_info *pi);
 bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps);
+bool ice_is_fw_health_report_supported(struct ice_hw *hw);
+int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source);
 int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code,
 				u8 serdes_num, int *output);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f63e485e65f6..749b5e29e83a 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1567,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		case ice_aqc_opc_lldp_set_mib_change:
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
 			break;
+		case ice_aqc_opc_get_health_status:
+			ice_process_health_status_event(pf, &event);
+			break;
 		default:
 			dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n",
 				qtype, opcode);
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index adb168860711..ae5a26ea0d03 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1216,4 +1216,9 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_FW_API_REPORT_DFLT_CFG_MIN		7
 #define ICE_FW_API_REPORT_DFLT_CFG_PATCH	3
 
+/* AQ API version for Health Status support */
+#define ICE_FW_API_HEALTH_REPORT_MAJ		1
+#define ICE_FW_API_HEALTH_REPORT_MIN		7
+#define ICE_FW_API_HEALTH_REPORT_PATCH		6
+
 #endif /* _ICE_TYPE_H_ */
-- 
cgit v1.2.3


From 1de25c6b984d71a7961065e27514b4fd51b2daae Mon Sep 17 00:00:00 2001
From: Konrad Knitter <konrad.knitter@intel.com>
Date: Wed, 6 Nov 2024 10:36:43 +0100
Subject: ice: support FW Recovery Mode

Recovery Mode is intended to recover from a fatal failure scenario in
which the device is not accessible to the host, meaning the firmware is
non-responsive.

The purpose of the Firmware Recovery Mode is to enable software tools to
update firmware and/or device configuration so the fatal error can be
resolved.

Recovery Mode Firmware supports a limited set of admin commands required
for NVM update.
Recovery Firmware does not support hardware interrupts so a polling mode
is used.

The driver will expose only the minimum set of devlink commands required
for the recovery of the adapter.

Using an appropriate NVM image, the user can recover the adapter using
the devlink flash API.

Prior to 4.20 E810 Adapter Recovery Firmware supports only the update
and erase of the "fw.mgmt" component.

E810 Adapter Recovery Firmware doesn't support selected preservation of
cards settings or identifiers.

The following command can be used to recover the adapter:

$ devlink dev flash <pci-address> <update-image.bin> component fw.mgmt
  overwrite settings overwrite identifier

Newer FW versions (4.20 or newer) supports update of "fw.undi" and
"fw.netlist" components.

$ devlink dev flash <pci-address> <update-image.bin>

Tested on Intel Corporation Ethernet Controller E810-C for SFP
FW revision 3.20 and 4.30.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Konrad Knitter <konrad.knitter@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink.c |  8 +++-
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h  |  1 +
 drivers/net/ethernet/intel/ice/ice_fw_update.c   | 14 ++++++-
 drivers/net/ethernet/intel/ice/ice_lib.c         |  6 +++
 drivers/net/ethernet/intel/ice/ice_lib.h         |  1 +
 drivers/net/ethernet/intel/ice/ice_main.c        | 53 ++++++++++++++++++++++++
 6 files changed, 80 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet/intel/ice/ice_main.c')

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index d1b9ccec5e05..d116e2b10bce 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -368,14 +368,18 @@ static int ice_devlink_info_get(struct devlink *devlink,
 			}
 			break;
 		case ICE_VERSION_RUNNING:
-			err = devlink_info_version_running_put(req, key, ctx->buf);
+			err = devlink_info_version_running_put_ext(req, key,
+								   ctx->buf,
+								   DEVLINK_INFO_VERSION_TYPE_COMPONENT);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Unable to set running version");
 				goto out_free_ctx;
 			}
 			break;
 		case ICE_VERSION_STORED:
-			err = devlink_info_version_stored_put(req, key, ctx->buf);
+			err = devlink_info_version_stored_put_ext(req, key,
+								  ctx->buf,
+								  DEVLINK_INFO_VERSION_TYPE_COMPONENT);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Unable to set stored version");
 				goto out_free_ctx;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index dd41a4dcc0b9..1f65eedabf7c 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1814,6 +1814,7 @@ struct ice_aqc_nvm_pass_comp_tbl {
 #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED		0x0
 #define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE	0x1
 #define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED		0x2
+#define ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK		0x3
 	u8 component_response_code; /* Response only */
 #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE	0x0
 #define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE	0x1
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 2702a0da5c3e..70c201f569ce 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -6,6 +6,7 @@
 #include <linux/crc32.h>
 #include <linux/pldmfw.h>
 #include "ice.h"
+#include "ice_lib.h"
 #include "ice_fw_update.h"
 
 struct ice_fwu_priv {
@@ -125,6 +126,10 @@ ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code,
 	case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED:
 		dev_info(dev, "firmware has rejected updating %s\n", component);
 		break;
+	case ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK:
+		if (ice_is_recovery_mode(&pf->hw))
+			return 0;
+		break;
 	}
 
 	switch (code) {
@@ -1004,13 +1009,20 @@ int ice_devlink_flash_update(struct devlink *devlink,
 		return -EOPNOTSUPP;
 	}
 
-	if (!hw->dev_caps.common_cap.nvm_unified_update) {
+	if (!hw->dev_caps.common_cap.nvm_unified_update && !ice_is_recovery_mode(hw)) {
 		NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update");
 		return -EOPNOTSUPP;
 	}
 
 	memset(&priv, 0, sizeof(priv));
 
+	if (params->component && strcmp(params->component, "fw.mgmt") == 0) {
+		priv.context.mode = PLDMFW_UPDATE_MODE_SINGLE_COMPONENT;
+		priv.context.component_identifier = NVM_COMP_ID_NVM;
+	} else if (params->component) {
+		return -EOPNOTSUPP;
+	}
+
 	/* the E822 device needs a slightly different ops */
 	if (hw->mac_type == ICE_MAC_GENERIC)
 		priv.context.ops = &ice_fwu_ops_e822;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a7d45a8ce7ac..38a1c8372180 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1700,6 +1700,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf)
 	return true;
 }
 
+#define ICE_FW_MODE_REC_M BIT(1)
+bool ice_is_recovery_mode(struct ice_hw *hw)
+{
+	return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M;
+}
+
 /**
  * ice_update_eth_stats - Update VSI-specific ethernet statistics counters
  * @vsi: the VSI to be updated
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 10d6fc479a32..eabb35834a24 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -90,6 +90,7 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector);
 
 bool ice_is_safe_mode(struct ice_pf *pf);
 bool ice_is_rdma_ena(struct ice_pf *pf);
+bool ice_is_recovery_mode(struct ice_hw *hw);
 bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi);
 bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi);
 int ice_set_dflt_vsi(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 749b5e29e83a..2205ea871209 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2364,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf)
 	}
 }
 
+static void ice_service_task_recovery_mode(struct work_struct *work)
+{
+	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
+
+	set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state);
+	ice_clean_adminq_subtask(pf);
+
+	ice_service_task_complete(pf);
+
+	mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100));
+}
+
 /**
  * ice_service_task - manage and run subtasks
  * @work: pointer to work_struct contained by the PF struct
@@ -5217,6 +5229,36 @@ void ice_unload(struct ice_pf *pf)
 	ice_decfg_netdev(vsi);
 }
 
+static int ice_probe_recovery_mode(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
+
+	dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n");
+
+	INIT_HLIST_HEAD(&pf->aq_wait_list);
+	spin_lock_init(&pf->aq_wait_lock);
+	init_waitqueue_head(&pf->aq_wait_queue);
+
+	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
+	pf->serv_tmr_period = HZ;
+	INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode);
+	clear_bit(ICE_SERVICE_SCHED, pf->state);
+	err = ice_create_all_ctrlq(&pf->hw);
+	if (err)
+		return err;
+
+	scoped_guard(devl, priv_to_devlink(pf)) {
+		err = ice_init_devlink(pf);
+		if (err)
+			return err;
+	}
+
+	ice_service_task_restart(pf);
+
+	return 0;
+}
+
 /**
  * ice_probe - Device initialization routine
  * @pdev: PCI device information struct
@@ -5308,6 +5350,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		hw->debug_mask = debug;
 #endif
 
+	if (ice_is_recovery_mode(hw))
+		return ice_probe_recovery_mode(pf);
+
 	err = ice_init_hw(hw);
 	if (err) {
 		dev_err(dev, "ice_init_hw failed: %d\n", err);
@@ -5425,6 +5470,14 @@ static void ice_remove(struct pci_dev *pdev)
 		msleep(100);
 	}
 
+	if (ice_is_recovery_mode(&pf->hw)) {
+		ice_service_task_stop(pf);
+		scoped_guard(devl, priv_to_devlink(pf)) {
+			ice_deinit_devlink(pf);
+		}
+		return;
+	}
+
 	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(ICE_VF_RESETS_DISABLED, pf->state);
 		ice_free_vfs(pf);
-- 
cgit v1.2.3