From 4ebe0599fc36ea3ff51e76e8554a2127e8126778 Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Wed, 11 Sep 2024 13:46:00 +0530 Subject: [PATCH 01/16] net: ti: icssg-prueth: Stop hardcoding def_inc The def_inc is stored in icss_iep structure. Currently default increment (ns per clock tick) is hardcoded to 4 (Clock frequency being 250 MHz). Change this to use the iep->def_inc variable as the iep structure is now accessible to the driver files. Reviewed-by: Roger Quadros Signed-off-by: MD Danish Anwar Link: https://patch.msgid.link/20240911081603.2521729-3-danishanwar@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 6644203d6bb7..5343d8754edd 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -365,7 +365,8 @@ static void prueth_iep_settime(void *clockops_data, u64 ns) sc_desc.cyclecounter0_set = cyclecount & GENMASK(31, 0); sc_desc.cyclecounter1_set = (cyclecount & GENMASK(63, 32)) >> 32; sc_desc.iepcount_set = ns % cycletime; - sc_desc.CMP0_current = cycletime - 4; //Count from 0 to (cycle time)-4 + /* Count from 0 to (cycle time) - emac->iep->def_inc */ + sc_desc.CMP0_current = cycletime - emac->iep->def_inc; memcpy_toio(sc_descp, &sc_desc, sizeof(sc_desc)); -- 2.51.0 From 95540ad6747c09225e21800d9ce325921645dda2 Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Wed, 11 Sep 2024 13:46:01 +0530 Subject: [PATCH 02/16] net: ti: icssg-prueth: Add support for HSR frame forward offload Add support for offloading HSR port-to-port frame forward to hardware. When the slave interfaces are added to the HSR interface, the PRU cores will be stopped and ICSSG HSR firmwares will be loaded to them. Similarly, when HSR interface is deleted, the PRU cores will be restarted and the last used firmwares will be reloaded. PRUeth interfaces will be back to the last used mode. This commit also renames some APIs that are common between switch and hsr mode with '_fw_offload' suffix. Signed-off-by: MD Danish Anwar Reviewed-by: Roger Quadros Link: https://patch.msgid.link/20240911081603.2521729-4-danishanwar@ti.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/ti/icssg/icssg_classifier.c | 1 + drivers/net/ethernet/ti/icssg/icssg_config.c | 18 +-- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 106 +++++++++++++++++- drivers/net/ethernet/ti/icssg/icssg_prueth.h | 6 + 4 files changed, 119 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c index 9ec504d976d6..833ca86d0b71 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c +++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c @@ -290,6 +290,7 @@ void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac) mac[2] << 16 | mac[3] << 24)); regmap_write(miig_rt, MAC_INTERFACE_1, (u32)(mac[4] | mac[5] << 8)); } +EXPORT_SYMBOL_GPL(icssg_class_set_host_mac_addr); void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac) { diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index dae52a83a378..7b2e6c192ff3 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -107,7 +107,7 @@ static const struct map hwq_map[2][ICSSG_NUM_OTHER_QUEUES] = { }, }; -static void icssg_config_mii_init_switch(struct prueth_emac *emac) +static void icssg_config_mii_init_fw_offload(struct prueth_emac *emac) { struct prueth *prueth = emac->prueth; int mii = prueth_emac_slice(emac); @@ -278,7 +278,7 @@ static int emac_r30_is_done(struct prueth_emac *emac) return 1; } -static int prueth_switch_buffer_setup(struct prueth_emac *emac) +static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac) { struct icssg_buffer_pool_cfg __iomem *bpool_cfg; struct icssg_rxq_ctx __iomem *rxq_ctx; @@ -424,7 +424,7 @@ static void icssg_init_emac_mode(struct prueth *prueth) icssg_class_set_host_mac_addr(prueth->miig_rt, mac); } -static void icssg_init_switch_mode(struct prueth *prueth) +static void icssg_init_fw_offload_mode(struct prueth *prueth) { u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET; int i; @@ -455,8 +455,8 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) struct icssg_flow_cfg __iomem *flow_cfg; int ret; - if (prueth->is_switch_mode) - icssg_init_switch_mode(prueth); + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) + icssg_init_fw_offload_mode(prueth); else icssg_init_emac_mode(prueth); @@ -472,8 +472,8 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) regmap_update_bits(prueth->miig_rt, ICSSG_CFG_OFFSET, ICSSG_CFG_DEFAULT, ICSSG_CFG_DEFAULT); icssg_miig_set_interface_mode(prueth->miig_rt, slice, emac->phy_if); - if (prueth->is_switch_mode) - icssg_config_mii_init_switch(emac); + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) + icssg_config_mii_init_fw_offload(emac); else icssg_config_mii_init(emac); icssg_config_ipg(emac); @@ -498,8 +498,8 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) writeb(0, config + SPL_PKT_DEFAULT_PRIORITY); writeb(0, config + QUEUE_NUM_UNTAGGED); - if (prueth->is_switch_mode) - ret = prueth_switch_buffer_setup(emac); + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) + ret = prueth_fw_offload_buffer_setup(emac); else ret = prueth_emac_buffer_setup(emac); if (ret) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 5343d8754edd..b38a4a6072c4 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -40,6 +41,8 @@ #define DEFAULT_PORT_MASK 1 #define DEFAULT_UNTAG_MASK 1 +#define NETIF_PRUETH_HSR_OFFLOAD_FEATURES NETIF_F_HW_HSR_FWD + /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) @@ -118,6 +121,19 @@ static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id) return IRQ_HANDLED; } +static struct icssg_firmwares icssg_hsr_firmwares[] = { + { + .pru = "ti-pruss/am65x-sr2-pru0-pruhsr-fw.elf", + .rtu = "ti-pruss/am65x-sr2-rtu0-pruhsr-fw.elf", + .txpru = "ti-pruss/am65x-sr2-txpru0-pruhsr-fw.elf", + }, + { + .pru = "ti-pruss/am65x-sr2-pru1-pruhsr-fw.elf", + .rtu = "ti-pruss/am65x-sr2-rtu1-pruhsr-fw.elf", + .txpru = "ti-pruss/am65x-sr2-txpru1-pruhsr-fw.elf", + } +}; + static struct icssg_firmwares icssg_switch_firmwares[] = { { .pru = "ti-pruss/am65x-sr2-pru0-prusw-fw.elf", @@ -152,6 +168,8 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) if (prueth->is_switch_mode) firmwares = icssg_switch_firmwares; + else if (prueth->is_hsr_offload_mode) + firmwares = icssg_hsr_firmwares; else firmwares = icssg_emac_firmwares; @@ -865,6 +883,7 @@ static int prueth_netdev_init(struct prueth *prueth, ndev->ethtool_ops = &icssg_ethtool_ops; ndev->hw_features = NETIF_F_SG; ndev->features = ndev->hw_features; + ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES; netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll); hrtimer_init(&emac->rx_hrtimer, CLOCK_MONOTONIC, @@ -953,7 +972,7 @@ static void prueth_emac_restart(struct prueth *prueth) netif_device_attach(emac1->ndev); } -static void icssg_enable_switch_mode(struct prueth *prueth) +static void icssg_change_mode(struct prueth *prueth) { struct prueth_emac *emac; int mac; @@ -973,8 +992,13 @@ static void icssg_enable_switch_mode(struct prueth *prueth) BIT(emac->port_id) | DEFAULT_PORT_MASK, BIT(emac->port_id) | DEFAULT_UNTAG_MASK, true); + if (prueth->is_hsr_offload_mode) + icssg_vtbl_modify(emac, DEFAULT_VID, + DEFAULT_PORT_MASK, + DEFAULT_UNTAG_MASK, true); icssg_set_pvid(prueth, emac->port_vlan, emac->port_id); - icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE); + if (prueth->is_switch_mode) + icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE); } } } @@ -1012,7 +1036,7 @@ static int prueth_netdevice_port_link(struct net_device *ndev, prueth->is_switch_mode = true; prueth->default_vlan = 1; emac->port_vlan = prueth->default_vlan; - icssg_enable_switch_mode(prueth); + icssg_change_mode(prueth); } } @@ -1040,6 +1064,61 @@ static void prueth_netdevice_port_unlink(struct net_device *ndev) prueth->hw_bridge_dev = NULL; } +static int prueth_hsr_port_link(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + struct prueth_emac *emac0; + struct prueth_emac *emac1; + + emac0 = prueth->emac[PRUETH_MAC0]; + emac1 = prueth->emac[PRUETH_MAC1]; + + if (prueth->is_switch_mode) + return -EOPNOTSUPP; + + prueth->hsr_members |= BIT(emac->port_id); + if (!prueth->is_hsr_offload_mode) { + if (prueth->hsr_members & BIT(PRUETH_PORT_MII0) && + prueth->hsr_members & BIT(PRUETH_PORT_MII1)) { + if (!(emac0->ndev->features & + NETIF_PRUETH_HSR_OFFLOAD_FEATURES) && + !(emac1->ndev->features & + NETIF_PRUETH_HSR_OFFLOAD_FEATURES)) + return -EOPNOTSUPP; + prueth->is_hsr_offload_mode = true; + prueth->default_vlan = 1; + emac0->port_vlan = prueth->default_vlan; + emac1->port_vlan = prueth->default_vlan; + icssg_change_mode(prueth); + netdev_dbg(ndev, "Enabling HSR offload mode\n"); + } + } + + return 0; +} + +static void prueth_hsr_port_unlink(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + struct prueth_emac *emac0; + struct prueth_emac *emac1; + + emac0 = prueth->emac[PRUETH_MAC0]; + emac1 = prueth->emac[PRUETH_MAC1]; + + prueth->hsr_members &= ~BIT(emac->port_id); + if (prueth->is_hsr_offload_mode) { + prueth->is_hsr_offload_mode = false; + emac0->port_vlan = 0; + emac1->port_vlan = 0; + prueth->hsr_dev = NULL; + prueth_emac_restart(prueth); + netdev_dbg(ndev, "Disabling HSR Offload mode\n"); + } +} + /* netdev notifier */ static int prueth_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) @@ -1047,6 +1126,8 @@ static int prueth_netdevice_event(struct notifier_block *unused, struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *info; + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; int ret = NOTIFY_DONE; if (ndev->netdev_ops != &emac_netdev_ops) @@ -1056,6 +1137,25 @@ static int prueth_netdevice_event(struct notifier_block *unused, case NETDEV_CHANGEUPPER: info = ptr; + if ((ndev->features & NETIF_PRUETH_HSR_OFFLOAD_FEATURES) && + is_hsr_master(info->upper_dev)) { + if (info->linking) { + if (!prueth->hsr_dev) { + prueth->hsr_dev = info->upper_dev; + icssg_class_set_host_mac_addr(prueth->miig_rt, + prueth->hsr_dev->dev_addr); + } else { + if (prueth->hsr_dev != info->upper_dev) { + netdev_dbg(ndev, "Both interfaces must be linked to same upper device\n"); + return -EOPNOTSUPP; + } + } + prueth_hsr_port_link(ndev); + } else { + prueth_hsr_port_unlink(ndev); + } + } + if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) ret = prueth_netdevice_port_link(ndev, info->upper_dev, extack); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 786bd1ba34ab..a4b025fae797 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -243,11 +243,14 @@ struct icssg_firmwares { * @iep1: pointer to IEP1 device * @vlan_tbl: VLAN-FID table pointer * @hw_bridge_dev: pointer to HW bridge net device + * @hsr_dev: pointer to the HSR net device * @br_members: bitmask of bridge member ports + * @hsr_members: bitmask of hsr member ports * @prueth_netdevice_nb: netdevice notifier block * @prueth_switchdev_nb: switchdev notifier block * @prueth_switchdev_bl_nb: switchdev blocking notifier block * @is_switch_mode: flag to indicate if device is in Switch mode + * @is_hsr_offload_mode: flag to indicate if device is in hsr offload mode * @is_switchmode_supported: indicates platform support for switch mode * @switch_id: ID for mapping switch ports to bridge * @default_vlan: Default VLAN for host @@ -279,11 +282,14 @@ struct prueth { struct prueth_vlan_tbl *vlan_tbl; struct net_device *hw_bridge_dev; + struct net_device *hsr_dev; u8 br_members; + u8 hsr_members; struct notifier_block prueth_netdevice_nb; struct notifier_block prueth_switchdev_nb; struct notifier_block prueth_switchdev_bl_nb; bool is_switch_mode; + bool is_hsr_offload_mode; bool is_switchmode_supported; unsigned char switch_id[MAX_PHYS_ITEM_ID_LEN]; int default_vlan; -- 2.51.0 From 56375086d093478d67366bdbafee4db657b9d1b1 Mon Sep 17 00:00:00 2001 From: Ravi Gunasekaran Date: Wed, 11 Sep 2024 13:46:02 +0530 Subject: [PATCH 03/16] net: ti: icssg-prueth: Enable HSR Tx duplication, Tx Tag and Rx Tag offload The HSR stack allows to offload its Tx packet duplication functionality to the hardware. Enable this offloading feature for ICSSG driver. Add support to offload HSR Tx Tag Insertion and Rx Tag Removal and duplicate discard. hsr tag insertion offload and hsr dup offload are tightly coupled in firmware implementation. Both these features need to be enabled / disabled together. Duplicate discard is done as part of RX tag removal and it is done by the firmware. When driver sends the r30 command ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE, firmware does RX tag removal as well as duplicate discard. Signed-off-by: Ravi Gunasekaran Signed-off-by: MD Danish Anwar Reviewed-by: Roger Quadros Link: https://patch.msgid.link/20240911081603.2521729-5-danishanwar@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/icssg/icssg_common.c | 18 ++++++++-- drivers/net/ethernet/ti/icssg/icssg_config.c | 4 ++- drivers/net/ethernet/ti/icssg/icssg_config.h | 2 ++ drivers/net/ethernet/ti/icssg/icssg_prueth.c | 36 +++++++++++++++++++- drivers/net/ethernet/ti/icssg/icssg_prueth.h | 3 ++ 5 files changed, 58 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index b9d8a93d1680..fdebeb2f84e0 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -660,14 +660,15 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev { struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc; struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; struct netdev_queue *netif_txq; struct prueth_tx_chn *tx_chn; dma_addr_t desc_dma, buf_dma; + u32 pkt_len, dst_tag_id; int i, ret = 0, q_idx; bool in_tx_ts = 0; int tx_ts_cookie; void **swdata; - u32 pkt_len; u32 *epib; pkt_len = skb_headlen(skb); @@ -712,9 +713,20 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev /* set dst tag to indicate internal qid at the firmware which is at * bit8..bit15. bit0..bit7 indicates port num for directed - * packets in case of switch mode operation + * packets in case of switch mode operation and port num 0 + * for undirected packets in case of HSR offload mode */ - cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8))); + dst_tag_id = emac->port_id | (q_idx << 8); + + if (prueth->is_hsr_offload_mode && + (ndev->features & NETIF_F_HW_HSR_DUP)) + dst_tag_id = PRUETH_UNDIRECTED_PKT_DST_TAG; + + if (prueth->is_hsr_offload_mode && + (ndev->features & NETIF_F_HW_HSR_TAG_INS)) + epib[1] |= PRUETH_UNDIRECTED_PKT_TAG_INS; + + cppi5_desc_set_tags_ids(&first_desc->hdr, 0, dst_tag_id); k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len); swdata = cppi5_hdesc_get_swdata(first_desc); diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index 7b2e6c192ff3..72ace151d8e9 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -531,7 +531,9 @@ static const struct icssg_r30_cmd emac_r32_bitmask[] = { {{EMAC_NONE, 0xffff4000, EMAC_NONE, EMAC_NONE}}, /* Preemption on Tx ENABLE*/ {{EMAC_NONE, 0xbfff0000, EMAC_NONE, EMAC_NONE}}, /* Preemption on Tx DISABLE*/ {{0xffff0010, EMAC_NONE, 0xffff0010, EMAC_NONE}}, /* VLAN AWARE*/ - {{0xffef0000, EMAC_NONE, 0xffef0000, EMAC_NONE}} /* VLAN UNWARE*/ + {{0xffef0000, EMAC_NONE, 0xffef0000, EMAC_NONE}}, /* VLAN UNWARE*/ + {{0xffff2000, EMAC_NONE, EMAC_NONE, EMAC_NONE}}, /* HSR_RX_OFFLOAD_ENABLE */ + {{0xdfff0000, EMAC_NONE, EMAC_NONE, EMAC_NONE}} /* HSR_RX_OFFLOAD_DISABLE */ }; int icssg_set_port_state(struct prueth_emac *emac, diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index 1ac60283923b..92c2deaa3068 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -80,6 +80,8 @@ enum icssg_port_state_cmd { ICSSG_EMAC_PORT_PREMPT_TX_DISABLE, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE, ICSSG_EMAC_PORT_VLAN_AWARE_DISABLE, + ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE, + ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE, ICSSG_EMAC_PORT_MAX_COMMANDS }; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index b38a4a6072c4..d128764982ae 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -41,7 +41,10 @@ #define DEFAULT_PORT_MASK 1 #define DEFAULT_UNTAG_MASK 1 -#define NETIF_PRUETH_HSR_OFFLOAD_FEATURES NETIF_F_HW_HSR_FWD +#define NETIF_PRUETH_HSR_OFFLOAD_FEATURES (NETIF_F_HW_HSR_FWD | \ + NETIF_F_HW_HSR_DUP | \ + NETIF_F_HW_HSR_TAG_INS | \ + NETIF_F_HW_HSR_TAG_RM) /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) @@ -744,6 +747,29 @@ static void emac_ndo_set_rx_mode(struct net_device *ndev) queue_work(emac->cmd_wq, &emac->rx_mode_work); } +static netdev_features_t emac_ndo_fix_features(struct net_device *ndev, + netdev_features_t features) +{ + /* hsr tag insertion offload and hsr dup offload are tightly coupled in + * firmware implementation. Both these features need to be enabled / + * disabled together. + */ + if (!(ndev->features & (NETIF_F_HW_HSR_DUP | NETIF_F_HW_HSR_TAG_INS))) + if ((features & NETIF_F_HW_HSR_DUP) || + (features & NETIF_F_HW_HSR_TAG_INS)) + features |= NETIF_F_HW_HSR_DUP | + NETIF_F_HW_HSR_TAG_INS; + + if ((ndev->features & NETIF_F_HW_HSR_DUP) || + (ndev->features & NETIF_F_HW_HSR_TAG_INS)) + if (!(features & NETIF_F_HW_HSR_DUP) || + !(features & NETIF_F_HW_HSR_TAG_INS)) + features &= ~(NETIF_F_HW_HSR_DUP | + NETIF_F_HW_HSR_TAG_INS); + + return features; +} + static const struct net_device_ops emac_netdev_ops = { .ndo_open = emac_ndo_open, .ndo_stop = emac_ndo_stop, @@ -755,6 +781,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_eth_ioctl = icssg_ndo_ioctl, .ndo_get_stats64 = icssg_ndo_get_stats64, .ndo_get_phys_port_name = icssg_ndo_get_phys_port_name, + .ndo_fix_features = emac_ndo_fix_features, }; static int prueth_netdev_init(struct prueth *prueth, @@ -981,6 +1008,13 @@ static void icssg_change_mode(struct prueth *prueth) for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { emac = prueth->emac[mac]; + if (prueth->is_hsr_offload_mode) { + if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM) + icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE); + else + icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE); + } + if (netif_running(emac->ndev)) { icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan, ICSSG_FDB_ENTRY_P0_MEMBERSHIP | diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index a4b025fae797..bba6da2e6bd8 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -59,6 +59,9 @@ #define IEP_DEFAULT_CYCLE_TIME_NS 1000000 /* 1 ms */ +#define PRUETH_UNDIRECTED_PKT_DST_TAG 0 +#define PRUETH_UNDIRECTED_PKT_TAG_INS BIT(30) + /* Firmware status codes */ #define ICSS_HS_FW_READY 0x55555555 #define ICSS_HS_FW_DEAD 0xDEAD0000 /* lower 16 bits contain error code */ -- 2.51.0 From 1d6ae9652780e97302b7e02610d9b6b74020b9ff Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Wed, 11 Sep 2024 13:46:03 +0530 Subject: [PATCH 04/16] net: ti: icssg-prueth: Add multicast filtering support in HSR mode Add support for multicast filtering in HSR mode Reviewed-by: Roger Quadros Signed-off-by: MD Danish Anwar Link: https://patch.msgid.link/20240911081603.2521729-6-danishanwar@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 42 +++++++++++++++++++- 1 file changed, 40 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index d128764982ae..5fd9902ab181 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -492,6 +492,36 @@ static int icssg_prueth_del_mcast(struct net_device *ndev, const u8 *addr) return 0; } +static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + + icssg_fdb_add_del(emac, addr, prueth->default_vlan, + ICSSG_FDB_ENTRY_P0_MEMBERSHIP | + ICSSG_FDB_ENTRY_P1_MEMBERSHIP | + ICSSG_FDB_ENTRY_P2_MEMBERSHIP | + ICSSG_FDB_ENTRY_BLOCK, true); + + icssg_vtbl_modify(emac, emac->port_vlan, BIT(emac->port_id), + BIT(emac->port_id), true); + return 0; +} + +static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + + icssg_fdb_add_del(emac, addr, prueth->default_vlan, + ICSSG_FDB_ENTRY_P0_MEMBERSHIP | + ICSSG_FDB_ENTRY_P1_MEMBERSHIP | + ICSSG_FDB_ENTRY_P2_MEMBERSHIP | + ICSSG_FDB_ENTRY_BLOCK, false); + + return 0; +} + /** * emac_ndo_open - EMAC device open * @ndev: network adapter device @@ -652,7 +682,10 @@ static int emac_ndo_stop(struct net_device *ndev) icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac)); - __dev_mc_unsync(ndev, icssg_prueth_del_mcast); + if (emac->prueth->is_hsr_offload_mode) + __dev_mc_unsync(ndev, icssg_prueth_hsr_del_mcast); + else + __dev_mc_unsync(ndev, icssg_prueth_del_mcast); atomic_set(&emac->tdown_cnt, emac->tx_ch_num); /* ensure new tdown_cnt value is visible */ @@ -730,7 +763,12 @@ static void emac_ndo_set_rx_mode_work(struct work_struct *work) return; } - __dev_mc_sync(ndev, icssg_prueth_add_mcast, icssg_prueth_del_mcast); + if (emac->prueth->is_hsr_offload_mode) + __dev_mc_sync(ndev, icssg_prueth_hsr_add_mcast, + icssg_prueth_hsr_del_mcast); + else + __dev_mc_sync(ndev, icssg_prueth_add_mcast, + icssg_prueth_del_mcast); } /** -- 2.51.0 From 9d70f3fec14421e793ffbc0ec2f739b24e534900 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sun, 15 Sep 2024 02:49:33 -0400 Subject: [PATCH 05/16] Revert "KVM: VMX: Always honor guest PAT on CPUs that support self-snoop" This reverts commit 377b2f359d1f71c75f8cc352b5c81f2210312d83. This caused a regression with the bochsdrm driver, which used ioremap() instead of ioremap_wc() to map the video RAM. After the commit, the WB memory type is used without the IGNORE_PAT, resulting in the slower UC memory type. In fact, UC is slow enough to basically cause guests to not boot... but only on new processors such as Sapphire Rapids and Cascade Lake. Coffee Lake for example works properly, though that might also be an effect of being on a larger, more NUMA system. The driver has been fixed but that does not help older guests. Until we figure out whether Cascade Lake and newer processors are working as intended, revert the commit. Long term we might add a quirk, but the details depend on whether the processors are working as intended: for example if they are, the quirk might reference bochs-compatible devices, e.g. in the name and documentation, so that userspace can disable the quirk by default and only leave it enabled if such a device is being exposed to the guest. If instead this is actually a bug in CLX+, then the actions we need to take are different and depend on the actual cause of the bug. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 8 +++----- arch/x86/kvm/vmx/vmx.c | 10 ++++------ 2 files changed, 7 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index de05a26b0b7d..7813d28b082f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4674,16 +4674,14 @@ out_unlock: bool kvm_mmu_may_ignore_guest_pat(void) { /* - * When EPT is enabled (shadow_memtype_mask is non-zero), the CPU does - * not support self-snoop (or is affected by an erratum), and the VM + * When EPT is enabled (shadow_memtype_mask is non-zero), and the VM * has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is to * honor the memtype from the guest's PAT so that guest accesses to * memory that is DMA'd aren't cached against the guest's wishes. As a * result, KVM _may_ ignore guest PAT, whereas without non-coherent DMA, - * KVM _always_ ignores or honors guest PAT, i.e. doesn't toggle SPTE - * bits in response to non-coherent device (un)registration. + * KVM _always_ ignores guest PAT (when EPT is enabled). */ - return !static_cpu_has(X86_FEATURE_SELFSNOOP) && shadow_memtype_mask; + return shadow_memtype_mask; } int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f18c2d8c7476..733a0c45d1a6 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7659,13 +7659,11 @@ u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) /* * Force WB and ignore guest PAT if the VM does NOT have a non-coherent - * device attached and the CPU doesn't support self-snoop. Letting the - * guest control memory types on Intel CPUs without self-snoop may - * result in unexpected behavior, and so KVM's (historical) ABI is to - * trust the guest to behave only as a last resort. + * device attached. Letting the guest control memory types on Intel + * CPUs may result in unexpected behavior, and so KVM's ABI is to trust + * the guest to behave only as a last resort. */ - if (!static_cpu_has(X86_FEATURE_SELFSNOOP) && - !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT); -- 2.51.0 From 98f7e32f20d28ec452afb208f9cffc08448a2652 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 15 Sep 2024 16:57:56 +0200 Subject: [PATCH 06/16] Linux 6.11 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 2966d5fbbf17..34bd1d5f9672 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0 From c209847b8974d2d5e784e3105d4683835673b18d Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Sat, 14 Sep 2024 10:18:20 +0200 Subject: [PATCH 07/16] net: ethernet: fs_enet: Make the per clock optional Some platforms that use fs_enet don't have the PER register clock. This optional dependency on the clock was incorrectly made mandatory when switching to devm_ accessors. Reported-by: Christophe JAILLET Closes: https://lore.kernel.org/netdev/4e4defa9-ef2f-4ff1-95ca-6627c24db20c@wanadoo.fr/ Fixes: c614acf6e8e1 ("net: ethernet: fs_enet: simplify clock handling with devm accessors") Signed-off-by: Maxime Chevallier Reviewed-by: Christophe JAILLET Link: https://patch.msgid.link/20240914081821.209130-1-maxime.chevallier@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index d300b01859a1..3425c4a6abcb 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -895,7 +895,7 @@ static int fs_enet_probe(struct platform_device *ofdev) * but require enable to succeed when a clock was specified/found, * keep a reference to the clock upon successful acquisition */ - clk = devm_clk_get_enabled(&ofdev->dev, "per"); + clk = devm_clk_get_optional_enabled(&ofdev->dev, "per"); if (IS_ERR(clk)) goto out_free_fpi; -- 2.51.0 From 75834577c0870c9087274f015887b6f4106b3a24 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 14 Sep 2024 12:57:28 +0300 Subject: [PATCH 08/16] ice: Fix a couple NULL vs IS_ERR() bugs The ice_repr_create() function returns error pointers. It never returns NULL. Fix the callers to check for IS_ERR(). Fixes: 977514fb0fa8 ("ice: create port representor for SF") Fixes: 415db8399d06 ("ice: make representor code generic") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Link: https://patch.msgid.link/7f7aeb91-8771-47b8-9275-9d9f64f947dd@stanley.mountain Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_repr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index 00d4a9125dfa..970a99a52bf1 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -452,8 +452,8 @@ struct ice_repr *ice_repr_create_vf(struct ice_vf *vf) return ERR_PTR(-EINVAL); repr = ice_repr_create(vsi); - if (!repr) - return ERR_PTR(-ENOMEM); + if (IS_ERR(repr)) + return repr; repr->type = ICE_REPR_TYPE_VF; repr->vf = vf; @@ -501,8 +501,8 @@ struct ice_repr *ice_repr_create_sf(struct ice_dynamic_port *sf) { struct ice_repr *repr = ice_repr_create(sf->vsi); - if (!repr) - return ERR_PTR(-ENOMEM); + if (IS_ERR(repr)) + return repr; repr->type = ICE_REPR_TYPE_SF; repr->sf = sf; -- 2.51.0 From 472d455e7c6f32e6ae4738de8e6ba212db372661 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 14 Sep 2024 12:57:56 +0300 Subject: [PATCH 09/16] ice: Fix a NULL vs IS_ERR() check in probe() The ice_allocate_sf() function returns error pointers on error. It doesn't return NULL. Update the check to match. Fixes: 177ef7f1e2a0 ("ice: base subfunction aux driver") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Link: https://patch.msgid.link/6951d217-ac06-4482-a35d-15d757fd90a3@stanley.mountain Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_sf_eth.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c index d00389c405c4..75d7147e1c01 100644 --- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c +++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c @@ -108,9 +108,9 @@ static int ice_sf_dev_probe(struct auxiliary_device *adev, vsi->flags = ICE_VSI_FLAG_INIT; priv = ice_allocate_sf(&adev->dev, pf); - if (!priv) { + if (IS_ERR(priv)) { dev_err(dev, "Subfunction devlink alloc failed"); - return -ENOMEM; + return PTR_ERR(priv); } priv->dev = sf_dev; -- 2.51.0 From 7052622fccb1efb850c6b55de477f65d03525a30 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 14 Sep 2024 12:56:51 +0300 Subject: [PATCH 10/16] netfilter: nft_socket: Fix a NULL vs IS_ERR() bug in nft_socket_cgroup_subtree_level() The cgroup_get_from_path() function never returns NULL, it returns error pointers. Update the error handling to match. Fixes: 7f3287db6543 ("netfilter: nft_socket: make cgroupsv2 matching work with namespaces") Signed-off-by: Dan Carpenter Acked-by: Florian Westphal Acked-by: Pablo Neira Ayuso Link: https://patch.msgid.link/bbc0c4e0-05cc-4f44-8797-2f4b3920a820@stanley.mountain Signed-off-by: Jakub Kicinski --- net/netfilter/nft_socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 12cdff640492..0a8883a93e83 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -61,8 +61,8 @@ static noinline int nft_socket_cgroup_subtree_level(void) struct cgroup *cgrp = cgroup_get_from_path("/"); int level; - if (!cgrp) - return -ENOENT; + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); level = cgrp->level; -- 2.51.0 From be461814aa4cb32aae061404b9a6a83ef3895018 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 14 Sep 2024 12:58:26 +0300 Subject: [PATCH 11/16] net/mlx5: HWS, check the correct variable in hws_send_ring_alloc_sq() There is a copy and paste bug so this code checks "sq->dep_wqe" where "sq->wr_priv" was intended. It could result in a NULL pointer dereference. Fixes: 2ca62599aa0b ("net/mlx5: HWS, added send engine and context handling") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Link: https://patch.msgid.link/da822315-02b7-4f5b-9c86-0d5176c5069d@stanley.mountain Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c index fb97a15c041a..a1adbb48735c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c @@ -584,7 +584,7 @@ static int hws_send_ring_alloc_sq(struct mlx5_core_dev *mdev, } sq->wr_priv = kzalloc(sizeof(*sq->wr_priv) * buf_sz, GFP_KERNEL); - if (!sq->dep_wqe) { + if (!sq->wr_priv) { err = -ENOMEM; goto free_dep_wqe; } -- 2.51.0 From dc1a456dc1870942d19e8cea257554d9d8d1597a Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 16 Sep 2024 14:50:16 +0100 Subject: [PATCH 12/16] cifs: Fix cifs readv callback merge resolution issue Fix an upstream merge resolution issue[1]. Prior to the netfs read healpers, the SMB1 asynchronous read callback, cifs_readv_worker() performed the cleanup for the operation in the network message processing loop, potentially slowing down the processing of incoming SMB messages. With commit a68c74865f51 ("cifs: Fix SMB1 readv/writev callback in the same way as SMB2/3"), this was moved to a worker thread (as is done in the SMB2/3 transport variant). However, the "was_async" argument to netfs_subreq_terminated (which was originally incorrectly "false" got flipped to "true" - which was then incorrect because, being in a kernel thread, it's not in an async context). This got corrected in the sample merge[2], but Linus, not unreasonably, switched it back to its previous value. Note that this value tells netfslib whether or not it can run sleepable stuff or stuff that takes a long time, such as retries and cleanups, in the calling thread, or whether it should offload to a worker thread. Fix this so that it is "false". The callback to netfslib in both SMB1 and SMB2/3 now gets offloaded from the network message thread to a separate worker thread and thus it's fine to do the slow work in this thread. Fixes: 35219bc5c71f ("Merge tag 'vfs-6.12.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs") Signed-off-by: David Howells cc: Steve French cc: Paulo Alcantara cc: Christian Brauner cc: Jeff Layton cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/CAHk-=wjr8fxk20-wx=63mZruW1LTvBvAKya1GQ1EhyzXb-okMA@mail.gmail.com/ [1] Link: https://lore.kernel.org/linux-fsdevel/20240913-vfs-netfs-39ef6f974061@brauner/ [2] Signed-off-by: Linus Torvalds --- fs/smb/client/cifssmb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index d81da161d3ed..7f3b37120a21 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1266,7 +1266,7 @@ static void cifs_readv_worker(struct work_struct *work) struct cifs_io_subrequest *rdata = container_of(work, struct cifs_io_subrequest, subreq.work); - netfs_read_subreq_terminated(&rdata->subreq, rdata->result, true); + netfs_read_subreq_terminated(&rdata->subreq, rdata->result, false); } static void -- 2.51.0 From 43a64bd02f9369be02c4c9312fc0965f78f65ad5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 16 Sep 2024 15:02:06 +0100 Subject: [PATCH 13/16] cifs: Remove redundant setting of NETFS_SREQ_HIT_EOF Fix an upstream merge resolution issue[1]. The NETFS_SREQ_HIT_EOF flag, and code to set it, got added via two different paths. The original path saw it added in the netfslib read improvements[2], but it was also added, and slightly differently, in a fix that was committed before v6.11: 1da29f2c39b67b846b74205c81bf0ccd96d34727 netfs, cifs: Fix handling of short DIO read However, the code added to smb2_readv_callback() to set the flag in didn't get removed when the netfs read improvements series was rebased to take account of the cifs fixes. The proposed merge resolution[2] deleted it rather than rebase the patches. Fix this by removing the redundant lines. Code to set the bit that derives from the fix patch is still there, a few lines above in the source. Fixes: 35219bc5c71f ("Merge tag 'vfs-6.12.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs") Signed-off-by: David Howells cc: Steve French cc: Paulo Alcantara cc: Christian Brauner cc: Jeff Layton cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/CAHk-=wjr8fxk20-wx=63mZruW1LTvBvAKya1GQ1EhyzXb-okMA@mail.gmail.com/ [1] Link: https://lore.kernel.org/linux-fsdevel/20240913-vfs-netfs-39ef6f974061@brauner/ [2] Signed-off-by: Linus Torvalds --- fs/smb/client/smb2pdu.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 95377bb91950..bb8ecbbe78af 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4614,8 +4614,6 @@ smb2_readv_callback(struct mid_q_entry *mid) 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; rdata->subreq.transferred += rdata->got_bytes; - if (rdata->subreq.start + rdata->subreq.transferred >= rdata->subreq.rreq->i_size) - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress); INIT_WORK(&rdata->subreq.work, smb2_readv_worker); queue_work(cifsiod_wq, &rdata->subreq.work); -- 2.51.0 From ed76c07c6885b249ce8486dac22fb97151a83185 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Tue, 5 Nov 2024 16:45:08 -0300 Subject: [PATCH 14/16] printk: Introduce FORCE_CON flag Introduce FORCE_CON flag to printk. The new flag will make it possible to create a context where printk messages will never be suppressed. This mechanism will be used in the next patch to create a force_con context on sysrq handling, removing an existing workaround on the loglevel global variable. The workaround existed to make sure that sysrq header messages were sent to all consoles, but this doesn't work with deferred messages because the loglevel might be restored to its original value before a console flushes the messages. Signed-off-by: Marcos Paulo de Souza Reviewed-by: John Ogness Reviewed-by: Petr Mladek Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20241105-printk-loud-con-v2-1-bd3ecdf7b0e4@suse.com Signed-off-by: Petr Mladek --- include/linux/printk.h | 3 +++ kernel/printk/internal.h | 3 +++ kernel/printk/printk.c | 21 ++++++++++++++++----- kernel/printk/printk_safe.c | 18 ++++++++++++++++++ 4 files changed, 40 insertions(+), 5 deletions(-) diff --git a/include/linux/printk.h b/include/linux/printk.h index eca9bb2ee637..232e5fd06701 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -166,6 +166,9 @@ __printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); extern void __printk_deferred_enter(void); extern void __printk_deferred_exit(void); +extern void printk_force_console_enter(void); +extern void printk_force_console_exit(void); + /* * The printk_deferred_enter/exit macros are available only as a hack for * some code paths that need to defer all printk console printing. Interrupts diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 3fcb48502adb..c6bb47666aef 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -53,6 +53,8 @@ int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, /* Flags for a single printk record. */ enum printk_info_flags { + /* always show on console, ignore console_loglevel */ + LOG_FORCE_CON = 1, LOG_NEWLINE = 2, /* text ended with a newline */ LOG_CONT = 8, /* text is a fragment of a continuation line */ }; @@ -90,6 +92,7 @@ bool printk_percpu_data_ready(void); void defer_console_output(void); bool is_printk_legacy_deferred(void); +bool is_printk_force_console(void); u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 71e4fe6f9b85..7cb44f9f3825 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1319,11 +1319,11 @@ static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; + bool suppress = !is_printk_force_console() && + suppress_message_printing(level); - if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) - || suppress_message_printing(level)) { + if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress) return; - } k = (unsigned long long)loops_per_msec * boot_delay; @@ -2273,6 +2273,9 @@ int vprintk_store(int facility, int level, if (dev_info) flags |= LOG_NEWLINE; + if (is_printk_force_console()) + flags |= LOG_FORCE_CON; + if (flags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); if (prb_reserve_in_last(&e, prb, &r, caller_id, PRINTKRB_RECORD_MAX)) { @@ -2280,6 +2283,9 @@ int vprintk_store(int facility, int level, facility, &flags, fmt, args); r.info->text_len += text_len; + if (flags & LOG_FORCE_CON) + r.info->flags |= LOG_FORCE_CON; + if (flags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); @@ -2947,6 +2953,7 @@ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, struct printk_info info; struct printk_record r; size_t len = 0; + bool force_con; /* * Formatting extended messages requires a separate buffer, so use the @@ -2965,9 +2972,13 @@ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, pmsg->seq = r.info->seq; pmsg->dropped = r.info->seq - seq; + force_con = r.info->flags & LOG_FORCE_CON; - /* Skip record that has level above the console loglevel. */ - if (may_suppress && suppress_message_printing(r.info->level)) + /* + * Skip records that are not forced to be printed on consoles and that + * has level above the console loglevel. + */ + if (!force_con && may_suppress && suppress_message_printing(r.info->level)) goto out; if (is_extended) { diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 2b35a9d3919d..6f94418d53ff 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -12,6 +12,24 @@ #include "internal.h" +/* Context where printk messages are never suppressed */ +static atomic_t force_con; + +void printk_force_console_enter(void) +{ + atomic_inc(&force_con); +} + +void printk_force_console_exit(void) +{ + atomic_dec(&force_con); +} + +bool is_printk_force_console(void) +{ + return atomic_read(&force_con); +} + static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ -- 2.51.0 From e3eea25e0b28ea06eb841ef1814ce7b7254f2fce Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Tue, 5 Nov 2024 16:45:09 -0300 Subject: [PATCH 15/16] tty: sysrq: Use printk_force_console context on __handle_sysrq By using the printk_force_console the loglevel workaround can be removed. The workaround existed to always send the sysrq header message to all consoles not matter what was the current loglevel, but it won't work for deferred messages, since the loglevel can be restore before the message is printed, suppressing the message that wasn't supposed to be suppressed by the workaround. Signed-off-by: Marcos Paulo de Souza Reviewed-by: John Ogness Reviewed-by: Petr Mladek Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20241105-printk-loud-con-v2-2-bd3ecdf7b0e4@suse.com Signed-off-by: Petr Mladek --- drivers/tty/sysrq.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 14f8f00fdcf9..4a8405478ad8 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -582,7 +582,6 @@ static void __sysrq_put_key_op(u8 key, const struct sysrq_key_op *op_p) void __handle_sysrq(u8 key, bool check_mask) { const struct sysrq_key_op *op_p; - int orig_log_level; int orig_suppress_printk; int i; @@ -592,13 +591,12 @@ void __handle_sysrq(u8 key, bool check_mask) rcu_sysrq_start(); rcu_read_lock(); /* - * Raise the apparent loglevel to maximum so that the sysrq header - * is shown to provide the user with positive feedback. We do not - * simply emit this at KERN_EMERG as that would change message - * routing in the consumers of /proc/kmsg. + * Enter in the force_console context so that sysrq header is shown to + * provide the user with positive feedback. We do not simply emit this + * at KERN_EMERG as that would change message routing in the consumers + * of /proc/kmsg. */ - orig_log_level = console_loglevel; - console_loglevel = CONSOLE_LOGLEVEL_DEFAULT; + printk_force_console_enter(); op_p = __sysrq_get_key_op(key); if (op_p) { @@ -608,11 +606,11 @@ void __handle_sysrq(u8 key, bool check_mask) */ if (!check_mask || sysrq_on_mask(op_p->enable_mask)) { pr_info("%s\n", op_p->action_msg); - console_loglevel = orig_log_level; + printk_force_console_exit(); op_p->handler(key); } else { pr_info("This sysrq operation is disabled.\n"); - console_loglevel = orig_log_level; + printk_force_console_exit(); } } else { pr_info("HELP : "); @@ -630,7 +628,7 @@ void __handle_sysrq(u8 key, bool check_mask) } } pr_cont("\n"); - console_loglevel = orig_log_level; + printk_force_console_exit(); } rcu_read_unlock(); rcu_sysrq_end(); -- 2.51.0 From da115c4ee29f589bb72ec2e86eb5e196b6bbcb41 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 12 Nov 2024 15:29:15 +0100 Subject: [PATCH 16/16] printk: add dummy printk_force_console_enter/exit helpers The newly added interface is broken when PRINTK is disabled: drivers/tty/sysrq.c: In function '__handle_sysrq': drivers/tty/sysrq.c:601:9: error: implicit declaration of function 'printk_force_console_enter' [-Wimplicit-function-declaration] 601 | printk_force_console_enter(); | ^~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/tty/sysrq.c:611:25: error: implicit declaration of function 'printk_force_console_exit' [-Wimplicit-function-declaration] 611 | printk_force_console_exit(); | ^~~~~~~~~~~~~~~~~~~~~~~~~ Add empty stub functions for both. Fixes: ed76c07c6885 ("printk: Introduce FORCE_CON flag") Signed-off-by: Arnd Bergmann Reviewed-by: Andy Shevchenko Reviewed-by: Marcos Paulo de Souza Tested-by: Marcos Paulo de Souza Link: https://lore.kernel.org/r/20241112142939.724093-1-arnd@kernel.org Signed-off-by: Petr Mladek --- include/linux/printk.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/linux/printk.h b/include/linux/printk.h index 232e5fd06701..4217a9f412b2 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -232,6 +232,14 @@ static inline void printk_deferred_exit(void) { } +static inline void printk_force_console_enter(void) +{ +} + +static inline void printk_force_console_exit(void) +{ +} + static inline int printk_ratelimit(void) { return 0; -- 2.51.0