This is a note to let you know that I've just added the patch titled PCI: tegra: Revert tegra124 raw_violation_fixup to the 5.7-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: pci-tegra-revert-tegra124-raw_violation_fixup.patch and it can be found in the queue-5.7 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From e7b856dfcec6d3bf028adee8c65342d7035914a1 Mon Sep 17 00:00:00 2001 From: Nicolas Chauvet <kwizart@xxxxxxxxx> Date: Sat, 18 Jul 2020 12:07:10 +0200 Subject: PCI: tegra: Revert tegra124 raw_violation_fixup From: Nicolas Chauvet <kwizart@xxxxxxxxx> commit e7b856dfcec6d3bf028adee8c65342d7035914a1 upstream. As reported in https://bugzilla.kernel.org/206217 , raw_violation_fixup is causing more harm than good in some common use-cases. This patch is a partial revert of commit: 191cd6fb5d2c ("PCI: tegra: Add SW fixup for RAW violations") and fixes the following regression since then. * Description: When both the NIC and MMC are used one can see the following message: NETDEV WATCHDOG: enp1s0 (r8169): transmit queue 0 timed out and pcieport 0000:00:02.0: AER: Uncorrected (Non-Fatal) error received: 0000:01:00.0 r8169 0000:01:00.0: AER: PCIe Bus Error: severity=Uncorrected (Non-Fatal), type=Transaction Layer, (Requester ID) r8169 0000:01:00.0: AER: device [10ec:8168] error status/mask=00004000/00400000 r8169 0000:01:00.0: AER: [14] CmpltTO (First) r8169 0000:01:00.0: AER: can't recover (no error_detected callback) pcieport 0000:00:02.0: AER: device recovery failed After that, the ethernet NIC is not functional anymore even after reloading the r8169 module. After a reboot, this is reproducible by copying a large file over the NIC to the MMC. For some reason this is not reproducible when files are copied to a tmpfs. * Little background on the fixup, by Manikanta Maddireddy: "In the internal testing with dGPU on Tegra124, CmplTO is reported by dGPU. This happened because FIFO queue in AFI(AXI to PCIe) module get full by upstream posted writes. Back to back upstream writes interleaved with infrequent reads, triggers RAW violation and CmpltTO. This is fixed by reducing the posted write credits and by changing updateFC timer frequency. These settings are fixed after stress test. In the current case, RTL NIC is also reporting CmplTO. These settings seems to be aggravating the issue instead of fixing it." Link: https://lore.kernel.org/r/20200718100710.15398-1-kwizart@xxxxxxxxx Fixes: 191cd6fb5d2c ("PCI: tegra: Add SW fixup for RAW violations") Signed-off-by: Nicolas Chauvet <kwizart@xxxxxxxxx> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@xxxxxxx> Reviewed-by: Manikanta Maddireddy <mmaddireddy@xxxxxxxxxx> Cc: stable@xxxxxxxxxxxxxxx Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/pci/controller/pci-tegra.c | 32 -------------------------------- 1 file changed, 32 deletions(-) --- a/drivers/pci/controller/pci-tegra.c +++ b/drivers/pci/controller/pci-tegra.c @@ -181,13 +181,6 @@ #define AFI_PEXBIAS_CTRL_0 0x168 -#define RP_PRIV_XP_DL 0x00000494 -#define RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD (0x1ff << 1) - -#define RP_RX_HDR_LIMIT 0x00000e00 -#define RP_RX_HDR_LIMIT_PW_MASK (0xff << 8) -#define RP_RX_HDR_LIMIT_PW (0x0e << 8) - #define RP_ECTL_2_R1 0x00000e84 #define RP_ECTL_2_R1_RX_CTLE_1C_MASK 0xffff @@ -323,7 +316,6 @@ struct tegra_pcie_soc { bool program_uphy; bool update_clamp_threshold; bool program_deskew_time; - bool raw_violation_fixup; bool update_fc_timer; bool has_cache_bars; struct { @@ -659,23 +651,6 @@ static void tegra_pcie_apply_sw_fixup(st writel(value, port->base + RP_VEND_CTL0); } - /* Fixup for read after write violation. */ - if (soc->raw_violation_fixup) { - value = readl(port->base + RP_RX_HDR_LIMIT); - value &= ~RP_RX_HDR_LIMIT_PW_MASK; - value |= RP_RX_HDR_LIMIT_PW; - writel(value, port->base + RP_RX_HDR_LIMIT); - - value = readl(port->base + RP_PRIV_XP_DL); - value |= RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD; - writel(value, port->base + RP_PRIV_XP_DL); - - value = readl(port->base + RP_VEND_XP); - value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK; - value |= soc->update_fc_threshold; - writel(value, port->base + RP_VEND_XP); - } - if (soc->update_fc_timer) { value = readl(port->base + RP_VEND_XP); value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK; @@ -2416,7 +2391,6 @@ static const struct tegra_pcie_soc tegra .program_uphy = true, .update_clamp_threshold = false, .program_deskew_time = false, - .raw_violation_fixup = false, .update_fc_timer = false, .has_cache_bars = true, .ectl.enable = false, @@ -2446,7 +2420,6 @@ static const struct tegra_pcie_soc tegra .program_uphy = true, .update_clamp_threshold = false, .program_deskew_time = false, - .raw_violation_fixup = false, .update_fc_timer = false, .has_cache_bars = false, .ectl.enable = false, @@ -2459,8 +2432,6 @@ static const struct tegra_pcie_soc tegra .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, .pads_refclk_cfg0 = 0x44ac44ac, - /* FC threshold is bit[25:18] */ - .update_fc_threshold = 0x03fc0000, .has_pex_clkreq_en = true, .has_pex_bias_ctrl = true, .has_intr_prsnt_sense = true, @@ -2470,7 +2441,6 @@ static const struct tegra_pcie_soc tegra .program_uphy = true, .update_clamp_threshold = true, .program_deskew_time = false, - .raw_violation_fixup = true, .update_fc_timer = false, .has_cache_bars = false, .ectl.enable = false, @@ -2494,7 +2464,6 @@ static const struct tegra_pcie_soc tegra .program_uphy = true, .update_clamp_threshold = true, .program_deskew_time = true, - .raw_violation_fixup = false, .update_fc_timer = true, .has_cache_bars = false, .ectl = { @@ -2536,7 +2505,6 @@ static const struct tegra_pcie_soc tegra .program_uphy = false, .update_clamp_threshold = false, .program_deskew_time = false, - .raw_violation_fixup = false, .update_fc_timer = false, .has_cache_bars = false, .ectl.enable = false, Patches currently in stable-queue which might be from kwizart@xxxxxxxxx are queue-5.7/pci-tegra-revert-tegra124-raw_violation_fixup.patch