Merge pull request torvalds#200 from zandrey/5.4.x+fslc

Update 5.4.x+fslc to v5.4.85

Author: otavio

Documentation/admin-guide/kernel-parameters.txt

@@ -5151,6 +5151,7 @@
 					device);
 				j = NO_REPORT_LUNS (don't use report luns
 					command, uas only);
+				k = NO_SAME (do not use WRITE_SAME, uas only)
 				l = NOT_LOCKABLE (don't try to lock and
 					unlock ejectable media, not on uas);
 				m = MAX_SECTORS_64 (don't transfer more

Documentation/virt/kvm/mmu.txt

@@ -420,7 +420,7 @@ If the generation number of the spte does not equal the global generation
 number, it will ignore the cached MMIO information and handle the page
 fault through the slow path.
 
-Since only 19 bits are used to store generation-number on mmio spte, all
+Since only 18 bits are used to store generation-number on mmio spte, all
 pages are zapped when there is an overflow.
 
 Unfortunately, a single memory access might access kvm_memslots(kvm) multiple

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 84
+SUBLEVEL = 85
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 

arch/x86/kernel/cpu/resctrl/internal.h

@@ -276,7 +276,6 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
  * @prev_msr	Value of IA32_QM_CTR for this RMID last time we read it
- * @chunks_bw	Total local data moved. Used for bandwidth calculation
  * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
  * @prev_bw	The most recent bandwidth in MBps
  * @delta_bw	Difference between the current and previous bandwidth
@@ -285,7 +284,6 @@ struct rftype {
 struct mbm_state {
 	u64	chunks;
 	u64	prev_msr;
-	u64	chunks_bw;
 	u64	prev_bw_msr;
 	u32	prev_bw;
 	u32	delta_bw;

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -280,8 +280,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 		return;
 
 	chunks = mbm_overflow_count(m->prev_bw_msr, tval);
-	m->chunks_bw += chunks;
-	m->chunks = m->chunks_bw;
 	cur_bw = (chunks * r->mon_scale) >> 20;
 
 	if (m->delta_comp)
@@ -451,15 +449,14 @@ static void mbm_update(struct rdt_domain *d, int rmid)
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+		__mon_event_count(rmid, &rr);
 
 		/*
 		 * Call the MBA software controller only for the
 		 * control groups and when user has enabled
 		 * the software controller explicitly.
 		 */
-		if (!is_mba_sc(NULL))
-			__mon_event_count(rmid, &rr);
-		else
+		if (is_mba_sc(NULL))
 			mbm_bw_count(rmid, &rr);
 	}
 }

arch/x86/kvm/mmu.c

@@ -407,11 +407,11 @@ static inline bool is_access_track_spte(u64 spte)
 }
 
 /*
- * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of
+ * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of
  * the memslots generation and is derived as follows:
  *
  * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
- * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61
+ * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62
  *
  * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
  * the MMIO generation number, as doing so would require stealing a bit from
@@ -420,36 +420,47 @@ static inline bool is_access_track_spte(u64 spte)
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(17, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
-#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
-						    MMIO_SPTE_GEN_LOW_START)
 
 #define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
 #define MMIO_SPTE_GEN_HIGH_END		62
+
+#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
+						    MMIO_SPTE_GEN_LOW_START)
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
 
+#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
+#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)
+
+/* remember to adjust the comment above as well if you change these */
+static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9);
+
+#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
+#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)
+
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+
 static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
 	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
-	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
-	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
+	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
 	return mask;
 }
 
 static u64 get_mmio_spte_generation(u64 spte)
 {
 	u64 gen;
 
-	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
-	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
 	return gen;
 }
 

drivers/net/ethernet/freescale/enetc/enetc_ethtool.c

@@ -141,8 +141,8 @@ static const struct {
 	{ ENETC_PM0_R255,   "MAC rx 128-255 byte packets" },
 	{ ENETC_PM0_R511,   "MAC rx 256-511 byte packets" },
 	{ ENETC_PM0_R1023,  "MAC rx 512-1023 byte packets" },
-	{ ENETC_PM0_R1518,  "MAC rx 1024-1518 byte packets" },
-	{ ENETC_PM0_R1519X, "MAC rx 1519 to max-octet packets" },
+	{ ENETC_PM0_R1522,  "MAC rx 1024-1522 byte packets" },
+	{ ENETC_PM0_R1523X, "MAC rx 1523 to max-octet packets" },
 	{ ENETC_PM0_ROVR,   "MAC rx oversized packets" },
 	{ ENETC_PM0_RJBR,   "MAC rx jabber packets" },
 	{ ENETC_PM0_RFRG,   "MAC rx fragment packets" },
@@ -161,9 +161,13 @@ static const struct {
 	{ ENETC_PM0_TBCA,   "MAC tx broadcast frames" },
 	{ ENETC_PM0_TPKT,   "MAC tx packets" },
 	{ ENETC_PM0_TUND,   "MAC tx undersized packets" },
+	{ ENETC_PM0_T64,    "MAC tx 64 byte packets" },
 	{ ENETC_PM0_T127,   "MAC tx 65-127 byte packets" },
+	{ ENETC_PM0_T255,   "MAC tx 128-255 byte packets" },
+	{ ENETC_PM0_T511,   "MAC tx 256-511 byte packets" },
 	{ ENETC_PM0_T1023,  "MAC tx 512-1023 byte packets" },
-	{ ENETC_PM0_T1518,  "MAC tx 1024-1518 byte packets" },
+	{ ENETC_PM0_T1522,  "MAC tx 1024-1522 byte packets" },
+	{ ENETC_PM0_T1523X, "MAC tx 1523 to max-octet packets" },
 	{ ENETC_PM0_TCNP,   "MAC tx control packets" },
 	{ ENETC_PM0_TDFR,   "MAC tx deferred packets" },
 	{ ENETC_PM0_TMCOL,  "MAC tx multiple collisions" },

drivers/net/ethernet/freescale/enetc/enetc_hw.h

@@ -239,8 +239,8 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PM0_R255		0x8180
 #define ENETC_PM0_R511		0x8188
 #define ENETC_PM0_R1023		0x8190
-#define ENETC_PM0_R1518		0x8198
-#define ENETC_PM0_R1519X	0x81A0
+#define ENETC_PM0_R1522		0x8198
+#define ENETC_PM0_R1523X	0x81A0
 #define ENETC_PM0_ROVR		0x81A8
 #define ENETC_PM0_RJBR		0x81B0
 #define ENETC_PM0_RFRG		0x81B8
@@ -259,9 +259,13 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PM0_TBCA		0x8250
 #define ENETC_PM0_TPKT		0x8260
 #define ENETC_PM0_TUND		0x8268
+#define ENETC_PM0_T64		0x8270
 #define ENETC_PM0_T127		0x8278
+#define ENETC_PM0_T255		0x8280
+#define ENETC_PM0_T511		0x8288
 #define ENETC_PM0_T1023		0x8290
-#define ENETC_PM0_T1518		0x8298
+#define ENETC_PM0_T1522		0x8298
+#define ENETC_PM0_T1523X	0x82A0
 #define ENETC_PM0_TCNP		0x82C0
 #define ENETC_PM0_TDFR		0x82D0
 #define ENETC_PM0_TMCOL		0x82D8

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h

@@ -35,8 +35,6 @@
 
 #define HCLGE_DBG_DFX_SSU_2_OFFSET 12
 
-#pragma pack(1)
-
 struct hclge_qos_pri_map_cmd {
 	u8 pri0_tc  : 4,
 	   pri1_tc  : 4;
@@ -85,8 +83,6 @@ struct hclge_dbg_reg_type_info {
 	struct hclge_dbg_reg_common_msg reg_msg;
 };
 
-#pragma pack()
-
 static struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
 	{false, "Reserved"},
 	{true,	"BP_CPU_STATE"},

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -1383,8 +1383,10 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
 	}
 
 	priv->port_stats.tx_timeout++;
-	en_dbg(DRV, priv, "Scheduling watchdog\n");
-	queue_work(mdev->workqueue, &priv->watchdog_task);
+	if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) {
+		en_dbg(DRV, priv, "Scheduling port restart\n");
+		queue_work(mdev->workqueue, &priv->restart_task);
+	}
 }
 
 
@@ -1738,6 +1740,7 @@ int mlx4_en_start_port(struct net_device *dev)
 				mlx4_en_deactivate_cq(priv, cq);
 				goto tx_err;
 			}
+			clear_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &tx_ring->state);
 			if (t != TX_XDP) {
 				tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
 				tx_ring->recycle_ring = NULL;
@@ -1834,6 +1837,7 @@ int mlx4_en_start_port(struct net_device *dev)
 		local_bh_enable();
 	}
 
+	clear_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state);
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
 
@@ -2004,7 +2008,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 static void mlx4_en_restart(struct work_struct *work)
 {
 	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
-						 watchdog_task);
+						 restart_task);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct net_device *dev = priv->dev;
 
@@ -2386,7 +2390,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 	if (netif_running(dev)) {
 		mutex_lock(&mdev->state_lock);
 		if (!mdev->device_up) {
-			/* NIC is probably restarting - let watchdog task reset
+			/* NIC is probably restarting - let restart task reset
 			 * the port */
 			en_dbg(DRV, priv, "Change MTU called with card down!?\n");
 		} else {
@@ -2395,7 +2399,9 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 			if (err) {
 				en_err(priv, "Failed restarting port:%d\n",
 					 priv->port);
-				queue_work(mdev->workqueue, &priv->watchdog_task);
+				if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING,
+						      &priv->state))
+					queue_work(mdev->workqueue, &priv->restart_task);
 			}
 		}
 		mutex_unlock(&mdev->state_lock);
@@ -2865,7 +2871,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 		if (err) {
 			en_err(priv, "Failed starting port %d for XDP change\n",
 			       priv->port);
-			queue_work(mdev->workqueue, &priv->watchdog_task);
+			if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state))
+				queue_work(mdev->workqueue, &priv->restart_task);
 		}
 	}
 
@@ -3263,7 +3270,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev);
 	spin_lock_init(&priv->stats_lock);
 	INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode);
-	INIT_WORK(&priv->watchdog_task, mlx4_en_restart);
+	INIT_WORK(&priv->restart_task, mlx4_en_restart);
 	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
 	INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
 	INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -392,6 +392,35 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	return cnt;
 }
 
+static void mlx4_en_handle_err_cqe(struct mlx4_en_priv *priv, struct mlx4_err_cqe *err_cqe,
+				   u16 cqe_index, struct mlx4_en_tx_ring *ring)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_tx_info *tx_info;
+	struct mlx4_en_tx_desc *tx_desc;
+	u16 wqe_index;
+	int desc_size;
+
+	en_err(priv, "CQE error - cqn 0x%x, ci 0x%x, vendor syndrome: 0x%x syndrome: 0x%x\n",
+	       ring->sp_cqn, cqe_index, err_cqe->vendor_err_syndrome, err_cqe->syndrome);
+	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, err_cqe, sizeof(*err_cqe),
+		       false);
+
+	wqe_index = be16_to_cpu(err_cqe->wqe_index) & ring->size_mask;
+	tx_info = &ring->tx_info[wqe_index];
+	desc_size = tx_info->nr_txbb << LOG_TXBB_SIZE;
+	en_err(priv, "Related WQE - qpn 0x%x, wqe index 0x%x, wqe size 0x%x\n", ring->qpn,
+	       wqe_index, desc_size);
+	tx_desc = ring->buf + (wqe_index << LOG_TXBB_SIZE);
+	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, tx_desc, desc_size, false);
+
+	if (test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state))
+		return;
+
+	en_err(priv, "Scheduling port restart\n");
+	queue_work(mdev->workqueue, &priv->restart_task);
+}
+
 bool mlx4_en_process_tx_cq(struct net_device *dev,
 			   struct mlx4_en_cq *cq, int napi_budget)
 {
@@ -438,13 +467,10 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 		dma_rmb();
 
 		if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
-			     MLX4_CQE_OPCODE_ERROR)) {
-			struct mlx4_err_cqe *cqe_err = (struct mlx4_err_cqe *)cqe;
-
-			en_err(priv, "CQE error - vendor syndrome: 0x%x syndrome: 0x%x\n",
-			       cqe_err->vendor_err_syndrome,
-			       cqe_err->syndrome);
-		}
+			     MLX4_CQE_OPCODE_ERROR))
+			if (!test_and_set_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &ring->state))
+				mlx4_en_handle_err_cqe(priv, (struct mlx4_err_cqe *)cqe, index,
+						       ring);
 
 		/* Skip over last polled CQE */
 		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -271,6 +271,10 @@ struct mlx4_en_page_cache {
 	} buf[MLX4_EN_CACHE_SIZE];
 };
 
+enum {
+	MLX4_EN_TX_RING_STATE_RECOVERING,
+};
+
 struct mlx4_en_priv;
 
 struct mlx4_en_tx_ring {
@@ -317,6 +321,7 @@ struct mlx4_en_tx_ring {
 	 * Only queue_stopped might be used if BQL is not properly working.
 	 */
 	unsigned long		queue_stopped;
+	unsigned long		state;
 	struct mlx4_hwq_resources sp_wqres;
 	struct mlx4_qp		sp_qp;
 	struct mlx4_qp_context	sp_context;
@@ -530,6 +535,10 @@ struct mlx4_en_stats_bitmap {
 	struct mutex mutex; /* for mutual access to stats bitmap */
 };
 
+enum {
+	MLX4_EN_STATE_FLAG_RESTARTING,
+};
+
 struct mlx4_en_priv {
 	struct mlx4_en_dev *mdev;
 	struct mlx4_en_port_profile *prof;
@@ -595,7 +604,7 @@ struct mlx4_en_priv {
 	struct mlx4_en_cq *rx_cq[MAX_RX_RINGS];
 	struct mlx4_qp drop_qp;
 	struct work_struct rx_mode_task;
-	struct work_struct watchdog_task;
+	struct work_struct restart_task;
 	struct work_struct linkstate_task;
 	struct delayed_work stats_task;
 	struct delayed_work service_task;
@@ -643,6 +652,7 @@ struct mlx4_en_priv {
 	u32 pflags;
 	u8 rss_key[MLX4_EN_RSS_KEY_SIZE];
 	u8 rss_hash_fn;
+	unsigned long state;
 };
 
 enum mlx4_en_wol {