[PATCH 3/3][SRU][Unstable] r8169: Implement dynamic ASPM mechanism

[AceLan Kao]

From: Kai-Heng Feng <kai.heng.feng at canonical.com>

BugLink: https://bugs.launchpad.net/bugs/1946433

r8169 NICs on some platforms have abysmal speed when ASPM is enabled.
Same issue can be observed with older vendor drivers.

The issue is however solved by the latest vendor driver. There's a new
mechanism, which disables r8169's internal ASPM when the NIC traffic has
more than 10 packets per second, and vice versa. The possible reason for
this is likely because the buffer on the chip is too small for its ASPM
exit latency.

Realtek confirmed that all their PCIe LAN NICs, r8106, r8168 and r8125
use dynamic ASPM under Windows. So implement the same mechanism here to
resolve the issue.

Also introduce a lock to prevent race on accessing config registers.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=214307
Signed-off-by: Kai-Heng Feng <kai.heng.feng at canonical.com>
(cherry picked from
https://patchwork.ozlabs.org/project/linux-pci/patch/20211007161552.272771-4-kai.heng.feng@canonical.com/)
Signed-off-by: Chia-Lin Kao (AceLan) <acelan.kao at canonical.com>
---
 drivers/net/ethernet/realtek/r8169_main.c | 58 +++++++++++++++++++++--
 1 file changed, 53 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 08dd74e3f796..166444871f0b 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -623,6 +623,11 @@ struct rtl8169_private {
 	} wk;
 
 	unsigned supports_gmii:1;
+	unsigned rtl_aspm_enabled:1;
+	struct delayed_work aspm_toggle;
+	atomic_t aspm_packet_count;
+	struct mutex config_lock;
+
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
@@ -671,12 +676,14 @@ static inline struct device *tp_to_dev(struct rtl8169_private *tp)
 
 static void rtl_lock_config_regs(struct rtl8169_private *tp)
 {
+	mutex_lock(&tp->config_lock);
 	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
 }
 
 static void rtl_unlock_config_regs(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	mutex_unlock(&tp->config_lock);
 }
 
 static void rtl_pci_commit(struct rtl8169_private *tp)
@@ -2704,6 +2711,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 	if (!pcie_aspm_support_enabled() || !pcie_aspm_capable(pdev))
 		return;
 
+	tp->rtl_aspm_enabled = enable;
+
 	if (enable) {
 		RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
@@ -4445,6 +4454,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
 
 	dirty_tx = tp->dirty_tx;
 
+	atomic_add(tp->cur_tx - dirty_tx, &tp->aspm_packet_count);
 	while (READ_ONCE(tp->cur_tx) != dirty_tx) {
 		unsigned int entry = dirty_tx % NUM_TX_DESC;
 		u32 status;
@@ -4589,6 +4599,8 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, int budget
 		rtl8169_mark_to_asic(desc);
 	}
 
+	atomic_add(count, &tp->aspm_packet_count);
+
 	return count;
 }
 
@@ -4696,8 +4708,39 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 	return 0;
 }
 
+#define ASPM_PACKET_THRESHOLD 10
+#define ASPM_TOGGLE_INTERVAL 1000
+
+static void rtl8169_aspm_toggle(struct work_struct *work)
+{
+	struct rtl8169_private *tp = container_of(work, struct rtl8169_private,
+						  aspm_toggle.work);
+	int packet_count;
+	bool enable;
+
+	packet_count = atomic_xchg(&tp->aspm_packet_count, 0);
+
+	if (pcie_aspm_enabled(tp->pci_dev)) {
+		enable = packet_count <= ASPM_PACKET_THRESHOLD;
+
+		if (tp->rtl_aspm_enabled != enable) {
+			rtl_unlock_config_regs(tp);
+			rtl_hw_aspm_clkreq_enable(tp, enable);
+			rtl_lock_config_regs(tp);
+		}
+	} else if (tp->rtl_aspm_enabled) {
+		rtl_unlock_config_regs(tp);
+		rtl_hw_aspm_clkreq_enable(tp, false);
+		rtl_lock_config_regs(tp);
+	}
+
+	schedule_delayed_work(&tp->aspm_toggle, msecs_to_jiffies(ASPM_TOGGLE_INTERVAL));
+}
+
 static void rtl8169_down(struct rtl8169_private *tp)
 {
+	cancel_delayed_work_sync(&tp->aspm_toggle);
+
 	/* Clear all task flags */
 	bitmap_zero(tp->wk.flags, RTL_FLAG_MAX);
 
@@ -4724,6 +4767,10 @@ static void rtl8169_up(struct rtl8169_private *tp)
 	rtl_reset_work(tp);
 
 	phy_start(tp->phydev);
+
+	/* pcie_aspm_capable may change after system resume */
+	if (pcie_aspm_support_enabled() && pcie_aspm_capable(tp->pci_dev))
+		schedule_delayed_work(&tp->aspm_toggle, 0);
 }
 
 static int rtl8169_close(struct net_device *dev)
@@ -5311,11 +5358,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
-	/* Disable ASPM L1 as that cause random device stop working
-	 * problems as well as full system hangs for some PCIe devices users.
-	 */
-	pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
-
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
 	if (rc < 0) {
@@ -5345,6 +5387,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return rc;
 	}
 
+	mutex_init(&tp->config_lock);
+
 	tp->mmio_addr = pcim_iomap_table(pdev)[region];
 
 	xid = (RTL_R32(tp, TxConfig) >> 20) & 0xfcf;
@@ -5382,6 +5426,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&tp->wk.work, rtl_task);
 
+	INIT_DELAYED_WORK(&tp->aspm_toggle, rtl8169_aspm_toggle);
+
+	atomic_set(&tp->aspm_packet_count, 0);
+
 	rtl_init_mac_address(tp);
 
 	dev->ethtool_ops = &rtl8169_ethtool_ops;
-- 
2.25.1