diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 62c3a8bc83b3..f599d321c881 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4951,6 +4951,8 @@ static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, if (active) msleep(20); ret = pcie_wait_for_link_status(pdev, false, active); + if (active && !ret) + ret = pcie_failed_link_retrain(pdev); if (active && ret) msleep(delay); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 6c257acbae90..e3a468a58cd2 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -543,6 +543,7 @@ void pci_acs_init(struct pci_dev *dev); int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); int pci_dev_specific_enable_acs(struct pci_dev *dev); int pci_dev_specific_disable_acs_redir(struct pci_dev *dev); +bool pcie_failed_link_retrain(struct pci_dev *dev); #else static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags) @@ -557,6 +558,10 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) { return -ENOTTY; } +static inline bool pcie_failed_link_retrain(struct pci_dev *dev) +{ + return false; +} #endif /* PCI error reporting and recovery */ diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 782925bac64a..f547db0a728f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2550,6 +2550,8 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dma_set_max_seg_size(&dev->dev, 65536); dma_set_seg_boundary(&dev->dev, 0xffffffff); + pcie_failed_link_retrain(dev); + /* Fix up broken headers */ pci_fixup_device(pci_fixup_header, dev); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 5c0a438f7e64..a46678563b33 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -33,6 +33,99 @@ #include #include "pci.h" +/* + * Retrain the link of a downstream PCIe port by hand if necessary. + * + * This is needed at least where a downstream port of the ASMedia ASM2824 + * Gen 3 switch is wired to the upstream port of the Pericom PI7C9X2G304 + * Gen 2 switch, and observed with the Delock Riser Card PCI Express x1 > + * 2 x PCIe x1 device, P/N 41433, plugged into the SiFive HiFive Unmatched + * board. + * + * In such a configuration the switches are supposed to negotiate the link + * speed of preferably 5.0GT/s, falling back to 2.5GT/s. However the link + * continues switching between the two speeds indefinitely and the data + * link layer never reaches the active state, with link training reported + * repeatedly active ~84% of the time. Forcing the target link speed to + * 2.5GT/s with the upstream ASM2824 device makes the two switches talk to + * each other correctly however. And more interestingly retraining with a + * higher target link speed afterwards lets the two successfully negotiate + * 5.0GT/s. + * + * With the ASM2824 we can rely on the otherwise optional Data Link Layer + * Link Active status bit and in the failed link training scenario it will + * be off along with the Link Bandwidth Management Status indicating that + * hardware has changed the link speed or width in an attempt to correct + * unreliable link operation. For a port that has been left unconnected + * both bits will be clear. So use this information to detect the problem + * rather than polling the Link Training bit and watching out for flips or + * at least the active status. + * + * Since the exact nature of the problem isn't known and in principle this + * could trigger where an ASM2824 device is downstream rather upstream, + * apply this erratum workaround to any downstream ports as long as they + * support Link Active reporting and have the Link Control 2 register. + * Restrict the speed to 2.5GT/s then with the Target Link Speed field, + * request a retrain and wait 200ms for the data link to go up. + * + * If this turns out successful and we know by the Vendor:Device ID it is + * safe to do so, then lift the restriction, letting the devices negotiate + * a higher speed. Also check for a similar 2.5GT/s speed restriction the + * firmware may have already arranged and lift it with ports that already + * report their data link being up. + * + * Return TRUE if the link has been successfully retrained, otherwise FALSE. + */ +bool pcie_failed_link_retrain(struct pci_dev *dev) +{ + static const struct pci_device_id ids[] = { + { PCI_VDEVICE(ASMEDIA, 0x2824) }, /* ASMedia ASM2824 */ + {} + }; + u16 lnksta, lnkctl2; + + if (!pci_is_pcie(dev) || !pcie_downstream_port(dev) || + !pcie_cap_has_lnkctl2(dev) || !dev->link_active_reporting) + return false; + + pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &lnkctl2); + pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); + if ((lnksta & (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_DLLLA)) == + PCI_EXP_LNKSTA_LBMS) { + pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n"); + + lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS; + lnkctl2 |= PCI_EXP_LNKCTL2_TLS_2_5GT; + pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2); + + if (!pcie_retrain_link(dev, false)) { + pci_info(dev, "retraining failed\n"); + return false; + } + + pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); + } + + if ((lnksta & PCI_EXP_LNKSTA_DLLLA) && + (lnkctl2 & PCI_EXP_LNKCTL2_TLS) == PCI_EXP_LNKCTL2_TLS_2_5GT && + pci_match_id(ids, dev)) { + u32 lnkcap; + + pci_info(dev, "removing 2.5GT/s downstream link speed restriction\n"); + pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); + lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS; + lnkctl2 |= lnkcap & PCI_EXP_LNKCAP_SLS; + pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2); + + if (!pcie_retrain_link(dev, false)) { + pci_info(dev, "retraining failed\n"); + return false; + } + } + + return true; +} + static ktime_t fixup_debug_start(struct pci_dev *dev, void (*fn)(struct pci_dev *dev)) {