From b49feacbeffc7635cc6692cbcc6a1eae2c17da6f Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Sun, 8 May 2022 10:09:05 +0300 Subject: [PATCH 1/3] e1000e: Enable GPT clock before sending message to CSME On corporate (CSME) ADL systems, the Ethernet Controller may stop working ("HW unit hang") after exiting from the s0ix state. The reason is that CSME misses the message sent by the host. Enabling the dynamic GPT clock solves this problem. This clock is cleared upon HW initialization. Fixes: 3e55d231716e ("e1000e: Add handshake with the CSME to support S0ix") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=214821 Reviewed-by: Dima Ruinskiy Signed-off-by: Sasha Neftin Tested-by: Chia-Lin Kao (AceLan) Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000e/netdev.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fa06f68c8c80..c64102b29862 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6494,6 +6494,10 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && hw->mac.type >= e1000_pch_adp) { + /* Keep the GPT clock enabled for CSME */ + mac_data = er32(FEXTNVM); + mac_data |= BIT(3); + ew32(FEXTNVM, mac_data); /* Request ME unconfigure the device from S0ix */ mac_data = er32(H2ME); mac_data &= ~E1000_H2ME_START_DPG; From 6cfa45361d3eac31ba67d7d0bbef547151450106 Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Mon, 9 May 2022 11:52:54 +0300 Subject: [PATCH 2/3] Revert "e1000e: Fix possible HW unit hang after an s0ix exit" This reverts commit 1866aa0d0d6492bc2f8d22d0df49abaccf50cddd. Commit 1866aa0d0d64 ("e1000e: Fix possible HW unit hang after an s0ix exit") was a workaround for CSME problem to handle messages comes via H2ME mailbox. This problem has been fixed by patch "e1000e: Enable the GPT clock before sending message to the CSME". Fixes: 3e55d231716e ("e1000e: Add handshake with the CSME to support S0ix") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=214821 Signed-off-by: Sasha Neftin Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000e/hw.h | 1 - drivers/net/ethernet/intel/e1000e/ich8lan.c | 4 ---- drivers/net/ethernet/intel/e1000e/ich8lan.h | 1 - drivers/net/ethernet/intel/e1000e/netdev.c | 26 --------------------- 4 files changed, 32 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 13382df2f2ef..bcf680e83811 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -630,7 +630,6 @@ struct e1000_phy_info { bool disable_polarity_correction; bool is_mdix; bool polarity_correction; - bool reset_disable; bool speed_downgraded; bool autoneg_wait_to_complete; }; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index e6c8e6d5234f..9466f65a6da7 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2050,10 +2050,6 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) bool blocked = false; int i = 0; - /* Check the PHY (LCD) reset flag */ - if (hw->phy.reset_disable) - return true; - while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) && (i++ < 30)) usleep_range(10000, 11000); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 638a3ddd7ada..2504b11c3169 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -271,7 +271,6 @@ #define I217_CGFREG_ENABLE_MTA_RESET 0x0002 #define I217_MEMPWR PHY_REG(772, 26) #define I217_MEMPWR_DISABLE_SMB_RELEASE 0x0010 -#define I217_MEMPWR_MOEM 0x1000 /* Receive Address Initial CRC Calculation */ #define E1000_PCH_RAICC(_n) (0x05F50 + ((_n) * 4)) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index c64102b29862..f1729940e46c 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6991,21 +6991,8 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); - struct e1000_hw *hw = &adapter->hw; - u16 phy_data; int rc; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && - hw->mac.type >= e1000_pch_adp) { - /* Mask OEM Bits / Gig Disable / Restart AN (772_26[12] = 1) */ - e1e_rphy(hw, I217_MEMPWR, &phy_data); - phy_data |= I217_MEMPWR_MOEM; - e1e_wphy(hw, I217_MEMPWR, phy_data); - - /* Disable LCD reset */ - hw->phy.reset_disable = true; - } - e1000e_flush_lpic(pdev); e1000e_pm_freeze(dev); @@ -7027,8 +7014,6 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); - struct e1000_hw *hw = &adapter->hw; - u16 phy_data; int rc; /* Introduce S0ix implementation */ @@ -7039,17 +7024,6 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) if (rc) return rc; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && - hw->mac.type >= e1000_pch_adp) { - /* Unmask OEM Bits / Gig Disable / Restart AN 772_26[12] = 0 */ - e1e_rphy(hw, I217_MEMPWR, &phy_data); - phy_data &= ~I217_MEMPWR_MOEM; - e1e_wphy(hw, I217_MEMPWR, phy_data); - - /* Enable LCD reset */ - hw->phy.reset_disable = false; - } - return e1000e_pm_thaw(dev); } From 7c1ddcee5311f3315096217881d2dbe47cc683f9 Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Thu, 2 Jun 2022 18:58:11 +0300 Subject: [PATCH 3/3] igc: Reinstate IGC_REMOVED logic and implement it properly The initially merged version of the igc driver code (via commit 146740f9abc4, "igc: Add support for PF") contained the following IGC_REMOVED checks in the igc_rd32/wr32() MMIO accessors: u32 igc_rd32(struct igc_hw *hw, u32 reg) { u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr); u32 value = 0; if (IGC_REMOVED(hw_addr)) return ~value; value = readl(&hw_addr[reg]); /* reads should not return all F's */ if (!(~value) && (!reg || !(~readl(hw_addr)))) hw->hw_addr = NULL; return value; } And: #define wr32(reg, val) \ do { \ u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \ if (!IGC_REMOVED(hw_addr)) \ writel((val), &hw_addr[(reg)]); \ } while (0) E.g. igb has similar checks in its MMIO accessors, and has a similar macro E1000_REMOVED, which is implemented as follows: #define E1000_REMOVED(h) unlikely(!(h)) These checks serve to detect and take note of an 0xffffffff MMIO read return from the device, which can be caused by a PCIe link flap or some other kind of PCI bus error, and to avoid performing MMIO reads and writes from that point onwards. However, the IGC_REMOVED macro was not originally implemented: #ifndef IGC_REMOVED #define IGC_REMOVED(a) (0) #endif /* IGC_REMOVED */ This led to the IGC_REMOVED logic to be removed entirely in a subsequent commit (commit 3c215fb18e70, "igc: remove IGC_REMOVED function"), with the rationale that such checks matter only for virtualization and that igc does not support virtualization -- but a PCIe device can become detached even without virtualization being in use, and without proper checks, a PCIe bus error affecting an igc adapter will lead to various NULL pointer dereferences, as the first access after the error will set hw->hw_addr to NULL, and subsequent accesses will blindly dereference this now-NULL pointer. This patch reinstates the IGC_REMOVED checks in igc_rd32/wr32(), and implements IGC_REMOVED the way it is done for igb, by checking for the unlikely() case of hw_addr being NULL. This change prevents the oopses seen when a PCIe link flap occurs on an igc adapter. Fixes: 146740f9abc4 ("igc: Add support for PF") Signed-off-by: Lennert Buytenhek Tested-by: Naama Meir Acked-by: Sasha Neftin Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 3 +++ drivers/net/ethernet/intel/igc/igc_regs.h | 5 ++++- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index ae17af44fe02..a5ebee7df4a8 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6171,6 +6171,9 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg) u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr); u32 value = 0; + if (IGC_REMOVED(hw_addr)) + return ~value; + value = readl(&hw_addr[reg]); /* reads should not return all F's */ diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index e197a33d93a0..026c3b65fc37 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -306,7 +306,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg); #define wr32(reg, val) \ do { \ u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \ - writel((val), &hw_addr[(reg)]); \ + if (!IGC_REMOVED(hw_addr)) \ + writel((val), &hw_addr[(reg)]); \ } while (0) #define rd32(reg) (igc_rd32(hw, reg)) @@ -318,4 +319,6 @@ do { \ #define array_rd32(reg, offset) (igc_rd32(hw, (reg) + ((offset) << 2))) +#define IGC_REMOVED(h) unlikely(!(h)) + #endif