Merge tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Introduce a config option to tweak MAX_SKB_FRAGS. Increasing the
     default value allows for better BIG TCP performances

   - Reduce compound page head access for zero-copy data transfers

   - RPS/RFS improvements, avoiding unneeded NET_RX_SOFTIRQ when
     possible

   - Threaded NAPI improvements, adding defer skb free support and
     unneeded softirq avoidance

   - Address dst_entry reference count scalability issues, via false
     sharing avoidance and optimize refcount tracking

   - Add lockless accesses annotation to sk_err[_soft]

   - Optimize again the skb struct layout

   - Extends the skb drop reasons to make it usable by multiple
     subsystems

   - Better const qualifier awareness for socket casts

  BPF:

   - Add skb and XDP typed dynptrs which allow BPF programs for more
     ergonomic and less brittle iteration through data and
     variable-sized accesses

   - Add a new BPF netfilter program type and minimal support to hook
     BPF programs to netfilter hooks such as prerouting or forward

   - Add more precise memory usage reporting for all BPF map types

   - Adds support for using {FOU,GUE} encap with an ipip device
     operating in collect_md mode and add a set of BPF kfuncs for
     controlling encap params

   - Allow BPF programs to detect at load time whether a particular
     kfunc exists or not, and also add support for this in light
     skeleton

   - Bigger batch of BPF verifier improvements to prepare for upcoming
     BPF open-coded iterators allowing for less restrictive looping
     capabilities

   - Rework RCU enforcement in the verifier, add kptr_rcu and enforce
     BPF programs to NULL-check before passing such pointers into kfunc

   - Add support for kptrs in percpu hashmaps, percpu LRU hashmaps and
     in local storage maps

   - Enable RCU semantics for task BPF kptrs and allow referenced kptr
     tasks to be stored in BPF maps

   - Add support for refcounted local kptrs to the verifier for allowing
     shared ownership, useful for adding a node to both the BPF list and
     rbtree

   - Add BPF verifier support for ST instructions in
     convert_ctx_access() which will help new -mcpu=v4 clang flag to
     start emitting them

   - Add ARM32 USDT support to libbpf

   - Improve bpftool's visual program dump which produces the control
     flow graph in a DOT format by adding C source inline annotations

  Protocols:

   - IPv4: Allow adding to IPv4 address a 'protocol' tag. Such value
     indicates the provenance of the IP address

   - IPv6: optimize route lookup, dropping unneeded R/W lock acquisition

   - Add the handshake upcall mechanism, allowing the user-space to
     implement generic TLS handshake on kernel's behalf

   - Bridge: support per-{Port, VLAN} neighbor suppression, increasing
     resilience to nodes failures

   - SCTP: add support for Fair Capacity and Weighted Fair Queueing
     schedulers

   - MPTCP: delay first subflow allocation up to its first usage. This
     will allow for later better LSM interaction

   - xfrm: Remove inner/outer modes from input/output path. These are
     not needed anymore

   - WiFi:
      - reduced neighbor report (RNR) handling for AP mode
      - HW timestamping support
      - support for randomized auth/deauth TA for PASN privacy
      - per-link debugfs for multi-link
      - TC offload support for mac80211 drivers
      - mac80211 mesh fast-xmit and fast-rx support
      - enable Wi-Fi 7 (EHT) mesh support

  Netfilter:

   - Add nf_tables 'brouting' support, to force a packet to be routed
     instead of being bridged

   - Update bridge netfilter and ovs conntrack helpers to handle IPv6
     Jumbo packets properly, i.e. fetch the packet length from
     hop-by-hop extension header. This is needed for BIT TCP support

   - The iptables 32bit compat interface isn't compiled in by default
     anymore

   - Move ip(6)tables builtin icmp matches to the udptcp one. This has
     the advantage that icmp/icmpv6 match doesn't load the
     iptables/ip6tables modules anymore when iptables-nft is used

   - Extended netlink error report for netdevice in flowtables and
     netdev/chains. Allow for incrementally add/delete devices to netdev
     basechain. Allow to create netdev chain without device

  Driver API:

   - Remove redundant Device Control Error Reporting Enable, as PCI core
     has already error reporting enabled at enumeration time

   - Move Multicast DB netlink handlers to core, allowing devices other
     then bridge to use them

   - Allow the page_pool to directly recycle the pages from safely
     localized NAPI

   - Implement lockless TX queue stop/wake combo macros, allowing for
     further code de-duplication and sanitization

   - Add YNL support for user headers and struct attrs

   - Add partial YNL specification for devlink

   - Add partial YNL specification for ethtool

   - Add tc-mqprio and tc-taprio support for preemptible traffic classes

   - Add tx push buf len param to ethtool, specifies the maximum number
     of bytes of a transmitted packet a driver can push directly to the
     underlying device

   - Add basic LED support for switch/phy

   - Add NAPI documentation, stop relaying on external links

   - Convert dsa_master_ioctl() to netdev notifier. This is a
     preparatory work to make the hardware timestamping layer selectable
     by user space

   - Add transceiver support and improve the error messages for CAN-FD
     controllers

  New hardware / drivers:

   - Ethernet:
      - AMD/Pensando core device support
      - MediaTek MT7981 SoC
      - MediaTek MT7988 SoC
      - Broadcom BCM53134 embedded switch
      - Texas Instruments CPSW9G ethernet switch
      - Qualcomm EMAC3 DWMAC ethernet
      - StarFive JH7110 SoC
      - NXP CBTX ethernet PHY

   - WiFi:
      - Apple M1 Pro/Max devices
      - RealTek rtl8710bu/rtl8188gu
      - RealTek rtl8822bs, rtl8822cs and rtl8821cs SDIO chipset

   - Bluetooth:
      - Realtek RTL8821CS, RTL8851B, RTL8852BS
      - Mediatek MT7663, MT7922
      - NXP w8997
      - Actions Semi ATS2851
      - QTI WCN6855
      - Marvell 88W8997

   - Can:
      - STMicroelectronics bxcan stm32f429

  Drivers:

   - Ethernet NICs:
      - Intel (1G, icg):
         - add tracking and reporting of QBV config errors
         - add support for configuring max SDU for each Tx queue
      - Intel (100G, ice):
         - refactor mailbox overflow detection to support Scalable IOV
         - GNSS interface optimization
      - Intel (i40e):
         - support XDP multi-buffer
      - nVidia/Mellanox:
         - add the support for linux bridge multicast offload
         - enable TC offload for egress and engress MACVLAN over bond
         - add support for VxLAN GBP encap/decap flows offload
         - extend packet offload to fully support libreswan
         - support tunnel mode in mlx5 IPsec packet offload
         - extend XDP multi-buffer support
         - support MACsec VLAN offload
         - add support for dynamic msix vectors allocation
         - drop RX page_cache and fully use page_pool
         - implement thermal zone to report NIC temperature
      - Netronome/Corigine:
         - add support for multi-zone conntrack offload
      - Solarflare/Xilinx:
         - support offloading TC VLAN push/pop actions to the MAE
         - support TC decap rules
         - support unicast PTP

   - Other NICs:
      - Broadcom (bnxt): enforce software based freq adjustments only on
        shared PHC NIC
      - RealTek (r8169): refactor to addess ASPM issues during NAPI poll
      - Micrel (lan8841): add support for PTP_PF_PEROUT
      - Cadence (macb): enable PTP unicast
      - Engleder (tsnep): add XDP socket zero-copy support
      - virtio-net: implement exact header length guest feature
      - veth: add page_pool support for page recycling
      - vxlan: add MDB data path support
      - gve: add XDP support for GQI-QPL format
      - geneve: accept every ethertype
      - macvlan: allow some packets to bypass broadcast queue
      - mana: add support for jumbo frame

   - Ethernet high-speed switches:
      - Microchip (sparx5): Add support for TC flower templates

   - Ethernet embedded switches:
      - Broadcom (b54):
         - configure 6318 and 63268 RGMII ports
      - Marvell (mv88e6xxx):
         - faster C45 bus scan
      - Microchip:
         - lan966x:
            - add support for IS1 VCAP
            - better TX/RX from/to CPU performances
         - ksz9477: add ETS Qdisc support
         - ksz8: enhance static MAC table operations and error handling
         - sama7g5: add PTP capability
      - NXP (ocelot):
         - add support for external ports
         - add support for preemptible traffic classes
      - Texas Instruments:
         - add CPSWxG SGMII support for J7200 and J721E

   - Intel WiFi (iwlwifi):
      - preparation for Wi-Fi 7 EHT and multi-link support
      - EHT (Wi-Fi 7) sniffer support
      - hardware timestamping support for some devices/firwmares
      - TX beacon protection on newer hardware

   - Qualcomm 802.11ax WiFi (ath11k):
      - MU-MIMO parameters support
      - ack signal support for management packets

   - RealTek WiFi (rtw88):
      - SDIO bus support
      - better support for some SDIO devices (e.g. MAC address from
        efuse)

   - RealTek WiFi (rtw89):
      - HW scan support for 8852b
      - better support for 6 GHz scanning
      - support for various newer firmware APIs
      - framework firmware backwards compatibility

   - MediaTek WiFi (mt76):
      - P2P support
      - mesh A-MSDU support
      - EHT (Wi-Fi 7) support
      - coredump support"

* tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2078 commits)
  net: phy: hide the PHYLIB_LEDS knob
  net: phy: marvell-88x2222: remove unnecessary (void*) conversions
  tcp/udp: Fix memleaks of sk and zerocopy skbs with TX timestamp.
  net: amd: Fix link leak when verifying config failed
  net: phy: marvell: Fix inconsistent indenting in led_blink_set
  lan966x: Don't use xdp_frame when action is XDP_TX
  tsnep: Add XDP socket zero-copy TX support
  tsnep: Add XDP socket zero-copy RX support
  tsnep: Move skb receive action to separate function
  tsnep: Add functions for queue enable/disable
  tsnep: Rework TX/RX queue initialization
  tsnep: Replace modulo operation with mask
  net: phy: dp83867: Add led_brightness_set support
  net: phy: Fix reading LED reg property
  drivers: nfc: nfcsim: remove return value check of `dev_dir`
  net: phy: dp83867: Remove unnecessary (void*) conversions
  net: ethtool: coalesce: try to make user settings stick twice
  net: mana: Check if netdev/napi_alloc_frag returns single page
  net: mana: Rename mana_refill_rxoob and remove some empty lines
  net: veth: add page_pool stats
  ...

1 files changed, 116 insertions, 122 deletions

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 45147a1016be..a7e376e7e689 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -30,6 +30,7 @@
 #include <linux/ipv6.h>
 #include <asm/unaligned.h>
 #include <net/ip6_checksum.h>
+#include <net/netdev_queues.h>
 
 #include "r8169.h"
 #include "r8169_firmware.h"
@@ -68,6 +69,8 @@
 #define NUM_RX_DESC	256	/* Number of Rx descriptor registers */
 #define R8169_TX_RING_BYTES	(NUM_TX_DESC * sizeof(struct TxDesc))
 #define R8169_RX_RING_BYTES	(NUM_RX_DESC * sizeof(struct RxDesc))
+#define R8169_TX_STOP_THRS	(MAX_SKB_FRAGS + 1)
+#define R8169_TX_START_THRS	(2 * R8169_TX_STOP_THRS)
 
 #define OCP_STD_PHY_BASE	0xa400
 
@@ -613,8 +616,13 @@ struct rtl8169_private {
 		struct work_struct work;
 	} wk;
 
+	spinlock_t config25_lock;
+	spinlock_t mac_ocp_lock;
+
+	spinlock_t cfg9346_usage_lock;
+	int cfg9346_usage_count;
+
 	unsigned supports_gmii:1;
-	unsigned aspm_manageable:1;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
@@ -661,12 +669,22 @@ static inline struct device *tp_to_dev(struct rtl8169_private *tp)
 
 static void rtl_lock_config_regs(struct rtl8169_private *tp)
 {
-	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&tp->cfg9346_usage_lock, flags);
+	if (!--tp->cfg9346_usage_count)
+		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+	spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags);
 }
 
 static void rtl_unlock_config_regs(struct rtl8169_private *tp)
 {
-	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&tp->cfg9346_usage_lock, flags);
+	if (!tp->cfg9346_usage_count++)
+		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags);
 }
 
 static void rtl_pci_commit(struct rtl8169_private *tp)
@@ -675,6 +693,28 @@ static void rtl_pci_commit(struct rtl8169_private *tp)
 	RTL_R8(tp, ChipCmd);
 }
 
+static void rtl_mod_config2(struct rtl8169_private *tp, u8 clear, u8 set)
+{
+	unsigned long flags;
+	u8 val;
+
+	spin_lock_irqsave(&tp->config25_lock, flags);
+	val = RTL_R8(tp, Config2);
+	RTL_W8(tp, Config2, (val & ~clear) | set);
+	spin_unlock_irqrestore(&tp->config25_lock, flags);
+}
+
+static void rtl_mod_config5(struct rtl8169_private *tp, u8 clear, u8 set)
+{
+	unsigned long flags;
+	u8 val;
+
+	spin_lock_irqsave(&tp->config25_lock, flags);
+	val = RTL_R8(tp, Config5);
+	RTL_W8(tp, Config5, (val & ~clear) | set);
+	spin_unlock_irqrestore(&tp->config25_lock, flags);
+}
+
 static bool rtl_is_8125(struct rtl8169_private *tp)
 {
 	return tp->mac_version >= RTL_GIGA_MAC_VER_61;
@@ -847,7 +887,7 @@ static int r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
 		(RTL_R32(tp, GPHY_OCP) & 0xffff) : -ETIMEDOUT;
 }
 
-static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data)
+static void __r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data)
 {
 	if (rtl_ocp_reg_failure(reg))
 		return;
@@ -855,7 +895,16 @@ static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data)
 	RTL_W32(tp, OCPDR, OCPAR_FLAG | (reg << 15) | data);
 }
 
-static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg)
+static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&tp->mac_ocp_lock, flags);
+	__r8168_mac_ocp_write(tp, reg, data);
+	spin_unlock_irqrestore(&tp->mac_ocp_lock, flags);
+}
+
+static u16 __r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg)
 {
 	if (rtl_ocp_reg_failure(reg))
 		return 0;
@@ -865,12 +914,28 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg)
 	return RTL_R32(tp, OCPDR);
 }
 
+static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg)
+{
+	unsigned long flags;
+	u16 val;
+
+	spin_lock_irqsave(&tp->mac_ocp_lock, flags);
+	val = __r8168_mac_ocp_read(tp, reg);
+	spin_unlock_irqrestore(&tp->mac_ocp_lock, flags);
+
+	return val;
+}
+
 static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask,
 				 u16 set)
 {
-	u16 data = r8168_mac_ocp_read(tp, reg);
+	unsigned long flags;
+	u16 data;
 
-	r8168_mac_ocp_write(tp, reg, (data & ~mask) | set);
+	spin_lock_irqsave(&tp->mac_ocp_lock, flags);
+	data = __r8168_mac_ocp_read(tp, reg);
+	__r8168_mac_ocp_write(tp, reg, (data & ~mask) | set);
+	spin_unlock_irqrestore(&tp->mac_ocp_lock, flags);
 }
 
 /* Work around a hw issue with RTL8168g PHY, the quirk disables
@@ -1336,6 +1401,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		{ WAKE_MAGIC, Config3, MagicPacket }
 	};
 	unsigned int i, tmp = ARRAY_SIZE(cfg);
+	unsigned long flags;
 	u8 options;
 
 	rtl_unlock_config_regs(tp);
@@ -1354,12 +1420,14 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 			r8168_mac_ocp_modify(tp, 0xc0b6, BIT(0), 0);
 	}
 
+	spin_lock_irqsave(&tp->config25_lock, flags);
 	for (i = 0; i < tmp; i++) {
 		options = RTL_R8(tp, cfg[i].reg) & ~cfg[i].mask;
 		if (wolopts & cfg[i].opt)
 			options |= cfg[i].mask;
 		RTL_W8(tp, cfg[i].reg, options);
 	}
+	spin_unlock_irqrestore(&tp->config25_lock, flags);
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
@@ -1371,10 +1439,10 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_37:
 	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_63:
-		options = RTL_R8(tp, Config2) & ~PME_SIGNAL;
 		if (wolopts)
-			options |= PME_SIGNAL;
-		RTL_W8(tp, Config2, options);
+			rtl_mod_config2(tp, 0, PME_SIGNAL);
+		else
+			rtl_mod_config2(tp, PME_SIGNAL, 0);
 		break;
 	default:
 		break;
@@ -2675,10 +2743,12 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp)
 
 static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 {
-	/* Don't enable ASPM in the chip if OS can't control ASPM */
-	if (enable && tp->aspm_manageable) {
-		RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
-		RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
+	if (tp->mac_version < RTL_GIGA_MAC_VER_32)
+		return;
+
+	if (enable) {
+		rtl_mod_config5(tp, 0, ASPM_en);
+		rtl_mod_config2(tp, 0, ClkReqEn);
 
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
@@ -2701,11 +2771,9 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 			break;
 		}
 
-		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-		RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+		rtl_mod_config2(tp, ClkReqEn, 0);
+		rtl_mod_config5(tp, ASPM_en, 0);
 	}
-
-	udelay(10);
 }
 
 static void rtl_set_fifo_size(struct rtl8169_private *tp, u16 rx_stat,
@@ -2863,7 +2931,7 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp)
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | TXPLA_RST);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~TXPLA_RST);
 
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
+	rtl_mod_config5(tp, Spi_en, 0);
 }
 
 static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
@@ -2896,9 +2964,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
-
-	rtl_hw_aspm_clkreq_enable(tp, true);
+	rtl_mod_config5(tp, Spi_en, 0);
 }
 
 static void rtl_hw_start_8168f(struct rtl8169_private *tp)
@@ -2919,7 +2985,7 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
+	rtl_mod_config5(tp, Spi_en, 0);
 
 	rtl8168_config_eee_mac(tp);
 }
@@ -2989,11 +3055,7 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
 	};
 
 	rtl_hw_start_8168g(tp);
-
-	/* disable aspm and clock request before access ephy */
-	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168g_1);
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
@@ -3011,9 +3073,6 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
 	};
 
 	rtl_hw_start_8168g(tp);
-
-	/* disable aspm and clock request before access ephy */
-	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168g_2);
 }
 
@@ -3034,8 +3093,6 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 
 	rtl_hw_start_8168g(tp);
 
-	/* disable aspm and clock request before access ephy */
-	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8411_2);
 
 	/* The following Realtek-provided magic fixes an issue with the RX unit
@@ -3173,8 +3230,6 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 	r8168_mac_ocp_write(tp, 0xFC32, 0x0C25);
 	r8168_mac_ocp_write(tp, 0xFC34, 0x00A9);
 	r8168_mac_ocp_write(tp, 0xFC36, 0x012D);
-
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
@@ -3189,8 +3244,6 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	};
 	int rg_saw_cnt;
 
-	/* disable aspm and clock request before access ephy */
-	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168h_1);
 
 	rtl_set_fifo_size(tp, 0x08, 0x10, 0x02, 0x06);
@@ -3238,8 +3291,6 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	r8168_mac_ocp_write(tp, 0xe63e, 0x0000);
 	r8168_mac_ocp_write(tp, 0xc094, 0x0000);
 	r8168_mac_ocp_write(tp, 0xc09e, 0x0000);
-
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
@@ -3278,8 +3329,6 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 		{ 0x1e, 0x0000,	0x2000 },
 	};
 
-	/* disable aspm and clock request before access ephy */
-	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168ep_3);
 
 	rtl_hw_start_8168ep(tp);
@@ -3290,8 +3339,6 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 	r8168_mac_ocp_modify(tp, 0xd3e2, 0x0fff, 0x0271);
 	r8168_mac_ocp_modify(tp, 0xd3e4, 0x00ff, 0x0000);
 	r8168_mac_ocp_modify(tp, 0xe860, 0x0000, 0x0080);
-
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8117(struct rtl8169_private *tp)
@@ -3303,9 +3350,6 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
 	int rg_saw_cnt;
 
 	rtl8168ep_stop_cmac(tp);
-
-	/* disable aspm and clock request before access ephy */
-	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8117);
 
 	rtl_set_fifo_size(tp, 0x08, 0x10, 0x02, 0x06);
@@ -3355,8 +3399,6 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
 
 	/* firmware is for MAC only */
 	r8169_apply_firmware(tp);
-
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
@@ -3479,8 +3521,6 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8106(struct rtl8169_private *tp)
 {
-	rtl_hw_aspm_clkreq_enable(tp, false);
-
 	/* Force LAN exit from ASPM if Rx/Tx are not idle */
 	RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800);
 
@@ -3497,7 +3537,6 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
 
 	rtl_pcie_state_l2l3_disable(tp);
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond)
@@ -3585,13 +3624,8 @@ static void rtl_hw_start_8125a_2(struct rtl8169_private *tp)
 	};
 
 	rtl_set_def_aspm_entry_latency(tp);
-
-	/* disable aspm and clock request before access ephy */
-	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8125a_2);
-
 	rtl_hw_start_8125_common(tp);
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8125b(struct rtl8169_private *tp)
@@ -3606,12 +3640,8 @@ static void rtl_hw_start_8125b(struct rtl8169_private *tp)
 	};
 
 	rtl_set_def_aspm_entry_latency(tp);
-	rtl_hw_aspm_clkreq_enable(tp, false);
-
 	rtl_ephy_init(tp, e_info_8125b);
 	rtl_hw_start_8125_common(tp);
-
-	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_config(struct rtl8169_private *tp)
@@ -3707,7 +3737,8 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp)
 static void rtl_hw_start(struct  rtl8169_private *tp)
 {
 	rtl_unlock_config_regs(tp);
-
+	/* disable aspm and clock request before ephy access */
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
@@ -3718,6 +3749,7 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 		rtl_hw_start_8168(tp);
 
 	rtl_enable_exit_l1(tp);
+	rtl_hw_aspm_clkreq_enable(tp, true);
 	rtl_set_rx_max_size(tp);
 	rtl_set_rx_tx_desc_registers(tp);
 	rtl_lock_config_regs(tp);
@@ -4133,13 +4165,9 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
 	return true;
 }
 
-static bool rtl_tx_slots_avail(struct rtl8169_private *tp)
+static unsigned int rtl_tx_slots_avail(struct rtl8169_private *tp)
 {
-	unsigned int slots_avail = READ_ONCE(tp->dirty_tx) + NUM_TX_DESC
-					- READ_ONCE(tp->cur_tx);
-
-	/* A skbuff with nr_frags needs nr_frags+1 entries in the tx queue */
-	return slots_avail > MAX_SKB_FRAGS;
+	return READ_ONCE(tp->dirty_tx) + NUM_TX_DESC - READ_ONCE(tp->cur_tx);
 }
 
 /* Versions RTL8102e and from RTL8168c onwards support csum_v2 */
@@ -4216,27 +4244,10 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	WRITE_ONCE(tp->cur_tx, tp->cur_tx + frags + 1);
 
-	stop_queue = !rtl_tx_slots_avail(tp);
-	if (unlikely(stop_queue)) {
-		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
-		 * not miss a ring update when it notices a stopped queue.
-		 */
-		smp_wmb();
-		netif_stop_queue(dev);
-		/* Sync with rtl_tx:
-		 * - publish queue status and cur_tx ring index (write barrier)
-		 * - refresh dirty_tx ring index (read barrier).
-		 * May the current thread have a pessimistic view of the ring
-		 * status and forget to wake up queue, a racing rtl_tx thread
-		 * can't.
-		 */
-		smp_mb__after_atomic();
-		if (rtl_tx_slots_avail(tp))
-			netif_start_queue(dev);
-		door_bell = true;
-	}
-
-	if (door_bell)
+	stop_queue = !netif_subqueue_maybe_stop(dev, 0, rtl_tx_slots_avail(tp),
+						R8169_TX_STOP_THRS,
+						R8169_TX_START_THRS);
+	if (door_bell || stop_queue)
 		rtl8169_doorbell(tp);
 
 	return NETDEV_TX_OK;
@@ -4360,19 +4371,12 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
 	}
 
 	if (tp->dirty_tx != dirty_tx) {
-		netdev_completed_queue(dev, pkts_compl, bytes_compl);
 		dev_sw_netstats_tx_add(dev, pkts_compl, bytes_compl);
+		WRITE_ONCE(tp->dirty_tx, dirty_tx);
 
-		/* Sync with rtl8169_start_xmit:
-		 * - publish dirty_tx ring index (write barrier)
-		 * - refresh cur_tx ring index and queue status (read barrier)
-		 * May the current thread miss the stopped queue condition,
-		 * a racing xmit thread can only have a right view of the
-		 * ring status.
-		 */
-		smp_store_mb(tp->dirty_tx, dirty_tx);
-		if (netif_queue_stopped(dev) && rtl_tx_slots_avail(tp))
-			netif_wake_queue(dev);
+		netif_subqueue_completed_wake(dev, 0, pkts_compl, bytes_compl,
+					      rtl_tx_slots_avail(tp),
+					      R8169_TX_START_THRS);
 		/*
 		 * 8168 hack: TxPoll requests are lost when the Tx packets are
 		 * too close. Let's kick an extra TxPoll request when a burst
@@ -4510,6 +4514,10 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 	}
 
 	if (napi_schedule_prep(&tp->napi)) {
+		rtl_unlock_config_regs(tp);
+		rtl_hw_aspm_clkreq_enable(tp, false);
+		rtl_lock_config_regs(tp);
+
 		rtl_irq_disable(tp);
 		__napi_schedule(&tp->napi);
 	}
@@ -4569,9 +4577,14 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 
 	work_done = rtl_rx(dev, tp, budget);
 
-	if (work_done < budget && napi_complete_done(napi, work_done))
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
 		rtl_irq_enable(tp);
 
+		rtl_unlock_config_regs(tp);
+		rtl_hw_aspm_clkreq_enable(tp, true);
+		rtl_lock_config_regs(tp);
+	}
+
 	return work_done;
 }
 
@@ -5145,16 +5158,6 @@ done:
 	rtl_rar_set(tp, mac_addr);
 }
 
-/* register is set if system vendor successfully tested ASPM 1.2 */
-static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
-{
-	if (tp->mac_version >= RTL_GIGA_MAC_VER_61 &&
-	    r8168_mac_ocp_read(tp, 0xc0b2) & 0xf)
-		return true;
-
-	return false;
-}
-
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct rtl8169_private *tp;
@@ -5176,6 +5179,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->eee_adv = -1;
 	tp->ocp_base = OCP_STD_PHY_BASE;
 
+	spin_lock_init(&tp->cfg9346_usage_lock);
+	spin_lock_init(&tp->config25_lock);
+	spin_lock_init(&tp->mac_ocp_lock);
+
 	dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev,
 						   struct pcpu_sw_netstats);
 	if (!dev->tstats)
@@ -5222,19 +5229,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->mac_version = chipset;
 
-	/* Disable ASPM L1 as that cause random device stop working
-	 * problems as well as full system hangs for some PCIe devices users.
-	 * Chips from RTL8168h partially have issues with L1.2, but seem
-	 * to work fine with L1 and L1.1.
-	 */
-	if (rtl_aspm_is_safe(tp))
-		rc = 0;
-	else if (tp->mac_version >= RTL_GIGA_MAC_VER_46)
-		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
-	else
-		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
-	tp->aspm_manageable = !rc;
-
 	tp->dash_type = rtl_check_dash(tp);
 
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK;