diff options
Diffstat (limited to 'drivers/pci')
29 files changed, 550 insertions, 193 deletions
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 0d94e4a967d8..7cef00d9d7ab 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -194,6 +194,12 @@ config PCI_P2PDMA P2P DMA transactions must be between devices behind the same root port. + Enabling this option will reduce the entropy of x86 KASLR memory + regions. For example - on a 46 bit system, the entropy goes down + from 16 bits to 15 bits. The actual reduction in entropy depends + on the physical address bits, on processor features, kernel config + (5 level page table) and physical memory present on the system. + If unsure, say N. config PCI_LABEL diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 6afff1f1b143..c331b108e71d 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -538,4 +538,37 @@ int pci_max_pasids(struct pci_dev *pdev) return (1 << FIELD_GET(PCI_PASID_CAP_WIDTH, supported)); } EXPORT_SYMBOL_GPL(pci_max_pasids); + +/** + * pci_pasid_status - Check the PASID status + * @pdev: PCI device structure + * + * Returns a negative value when no PASID capability is present. + * Otherwise the value of the control register is returned. + * Status reported are: + * + * PCI_PASID_CTRL_ENABLE - PASID enabled + * PCI_PASID_CTRL_EXEC - Execute permission enabled + * PCI_PASID_CTRL_PRIV - Privileged mode enabled + */ +int pci_pasid_status(struct pci_dev *pdev) +{ + int pasid; + u16 ctrl; + + if (pdev->is_virtfn) + pdev = pci_physfn(pdev); + + pasid = pdev->pasid_cap; + if (!pasid) + return -EINVAL; + + pci_read_config_word(pdev, pasid + PCI_PASID_CTRL, &ctrl); + + ctrl &= PCI_PASID_CTRL_ENABLE | PCI_PASID_CTRL_EXEC | + PCI_PASID_CTRL_PRIV; + + return ctrl; +} +EXPORT_SYMBOL_GPL(pci_pasid_status); #endif /* CONFIG_PCI_PASID */ diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c index 0bf4cde34f51..f700e8c49082 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-ep.c +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c @@ -292,13 +292,14 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, struct cdns_pcie *pcie = &ep->pcie; u32 cap = CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET; u32 val, reg; + u16 actual_interrupts = interrupts + 1; fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); reg = cap + PCI_MSIX_FLAGS; val = cdns_pcie_ep_fn_readw(pcie, fn, reg); val &= ~PCI_MSIX_FLAGS_QSIZE; - val |= interrupts; + val |= interrupts; /* 0's based value */ cdns_pcie_ep_fn_writew(pcie, fn, reg, val); /* Set MSIX BAR and offset */ @@ -308,7 +309,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, /* Set PBA BAR and offset. BAR must match MSIX BAR */ reg = cap + PCI_MSIX_PBA; - val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + val = (offset + (actual_interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; cdns_pcie_ep_fn_writel(pcie, fn, reg, val); return 0; diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c index 8af95e9da7ce..741e10a575ec 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-host.c +++ b/drivers/pci/controller/cadence/pcie-cadence-host.c @@ -570,14 +570,5 @@ int cdns_pcie_host_setup(struct cdns_pcie_rc *rc) if (!bridge->ops) bridge->ops = &cdns_pcie_host_ops; - ret = pci_host_probe(bridge); - if (ret < 0) - goto err_init; - - return 0; - - err_init: - pm_runtime_put_sync(dev); - - return ret; + return pci_host_probe(bridge); } diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index ad3028b755d1..3b24fed3177d 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -48,6 +48,8 @@ #define IMX95_PCIE_SS_RW_REG_0 0xf0 #define IMX95_PCIE_REF_CLKEN BIT(23) #define IMX95_PCIE_PHY_CR_PARA_SEL BIT(9) +#define IMX95_PCIE_SS_RW_REG_1 0xf4 +#define IMX95_PCIE_SYS_AUX_PWR_DET BIT(31) #define IMX95_PE0_GEN_CTRL_1 0x1050 #define IMX95_PCIE_DEVICE_TYPE GENMASK(3, 0) @@ -206,6 +208,19 @@ static unsigned int imx_pcie_grp_offset(const struct imx_pcie *imx_pcie) static int imx95_pcie_init_phy(struct imx_pcie *imx_pcie) { + /* + * ERR051624: The Controller Without Vaux Cannot Exit L23 Ready + * Through Beacon or PERST# De-assertion + * + * When the auxiliary power is not available, the controller + * cannot exit from L23 Ready with beacon or PERST# de-assertion + * when main power is not removed. + * + * Workaround: Set SS_RW_REG_1[SYS_AUX_PWR_DET] to 1. + */ + regmap_set_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_1, + IMX95_PCIE_SYS_AUX_PWR_DET); + regmap_update_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_0, IMX95_PCIE_PHY_CR_PARA_SEL, diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index dea19250598a..00289948f9c1 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -280,7 +280,7 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, u32 index; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - for (index = 0; index < pci->num_ob_windows; index++) { + for_each_set_bit(index, ep->ob_window_map, pci->num_ob_windows) { if (ep->outbound_addr[index] != addr) continue; *atu_index = index; @@ -398,6 +398,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct dw_pcie_ep_func *ep_func; u32 val, reg; + u16 actual_interrupts = interrupts + 1; ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); if (!ep_func || !ep_func->msix_cap) @@ -408,7 +409,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, reg = ep_func->msix_cap + PCI_MSIX_FLAGS; val = dw_pcie_ep_readw_dbi(ep, func_no, reg); val &= ~PCI_MSIX_FLAGS_QSIZE; - val |= interrupts; + val |= interrupts; /* 0's based value */ dw_pcie_writew_dbi(pci, reg, val); reg = ep_func->msix_cap + PCI_MSIX_TABLE; @@ -416,7 +417,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, dw_pcie_ep_writel_dbi(ep, func_no, reg, val); reg = ep_func->msix_cap + PCI_MSIX_PBA; - val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + val = (offset + (actual_interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; dw_pcie_ep_writel_dbi(ep, func_no, reg, val); dw_pcie_dbi_ro_wr_dis(pci); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 120e2aca5164..d428457d9c43 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -902,7 +902,7 @@ static int dw_pcie_pme_turn_off(struct dw_pcie *pci) if (ret) return ret; - mem = ioremap(atu.cpu_addr, pci->region_align); + mem = ioremap(pci->pp.msg_res->start, pci->region_align); if (!mem) return -ENOMEM; diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 6d6cbc8b5b2c..d40afe74ddd1 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -752,22 +752,19 @@ static void dw_pcie_link_set_max_link_width(struct dw_pcie *pci, u32 num_lanes) /* Set link width speed control register */ lwsc = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); lwsc &= ~PORT_LOGIC_LINK_WIDTH_MASK; + lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES; switch (num_lanes) { case 1: plc |= PORT_LINK_MODE_1_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES; break; case 2: plc |= PORT_LINK_MODE_2_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_2_LANES; break; case 4: plc |= PORT_LINK_MODE_4_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_4_LANES; break; case 8: plc |= PORT_LINK_MODE_8_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_8_LANES; break; default: dev_err(pci->dev, "num-lanes %u: invalid value\n", num_lanes); diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c index 1170e1107508..6b113a1212a9 100644 --- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -44,7 +44,6 @@ #define PCIE_LINKUP (PCIE_SMLH_LINKUP | PCIE_RDLH_LINKUP) #define PCIE_RDLH_LINK_UP_CHGED BIT(1) #define PCIE_LINK_REQ_RST_NOT_INT BIT(2) -#define PCIE_L0S_ENTRY 0x11 #define PCIE_CLIENT_GENERAL_CONTROL 0x0 #define PCIE_CLIENT_INTR_STATUS_LEGACY 0x8 #define PCIE_CLIENT_INTR_MASK_LEGACY 0x1c @@ -177,8 +176,7 @@ static int rockchip_pcie_link_up(struct dw_pcie *pci) struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); u32 val = rockchip_pcie_get_ltssm(rockchip); - if ((val & PCIE_LINKUP) == PCIE_LINKUP && - (val & PCIE_LTSSM_STATUS_MASK) == PCIE_L0S_ENTRY) + if ((val & PCIE_LINKUP) == PCIE_LINKUP) return 1; return 0; @@ -379,8 +377,8 @@ static int rockchip_pcie_phy_init(struct rockchip_pcie *rockchip) static void rockchip_pcie_phy_deinit(struct rockchip_pcie *rockchip) { - phy_exit(rockchip->phy); phy_power_off(rockchip->phy); + phy_exit(rockchip->phy); } static const struct dw_pcie_ops dw_pcie_ops = { diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c index 3a5511c3f7d9..5d77a0164860 100644 --- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c +++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c @@ -403,6 +403,7 @@ static const struct pci_epc_features rcar_gen4_pcie_epc_features = { .msix_capable = false, .bar[BAR_1] = { .type = BAR_RESERVED, }, .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256 }, .bar[BAR_5] = { .type = BAR_RESERVED, }, .align = SZ_1M, }; diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index fefab2758a06..16725f9536f6 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -541,7 +541,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK); /* Assert PERST# before setting up the clock */ - gpiod_set_value(reset, 1); + gpiod_set_value_cansleep(reset, 1); ret = apple_pcie_setup_refclk(pcie, port); if (ret < 0) @@ -552,7 +552,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, /* Deassert PERST# */ rmw_set(PORT_PERST_OFF, port->base + PORT_PERST); - gpiod_set_value(reset, 0); + gpiod_set_value_cansleep(reset, 0); /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ msleep(100); @@ -585,6 +585,9 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, list_add_tail(&port->entry, &pcie->ports); init_completion(&pcie->event); + /* In the success path, we keep a reference to np around */ + of_node_get(np); + ret = apple_pcie_port_register_irqs(port); WARN_ON(ret); @@ -764,7 +767,6 @@ static int apple_pcie_init(struct pci_config_window *cfg) { struct device *dev = cfg->parent; struct platform_device *platform = to_platform_device(dev); - struct device_node *of_port; struct apple_pcie *pcie; int ret; @@ -787,11 +789,10 @@ static int apple_pcie_init(struct pci_config_window *cfg) if (ret) return ret; - for_each_child_of_node(dev->of_node, of_port) { + for_each_available_child_of_node_scoped(dev->of_node, of_port) { ret = apple_pcie_setup_port(pcie, of_port); if (ret) { dev_err(pcie->dev, "Port %pOF setup fail: %d\n", of_port, ret); - of_node_put(of_port); return ret; } } diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index 792d24cea574..81f085cebf62 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -309,8 +309,8 @@ static int brcm_pcie_encode_ibar_size(u64 size) if (log2_in >= 12 && log2_in <= 15) /* Covers 4KB to 32KB (inclusive) */ return (log2_in - 12) + 0x1c; - else if (log2_in >= 16 && log2_in <= 35) - /* Covers 64KB to 32GB, (inclusive) */ + else if (log2_in >= 16 && log2_in <= 36) + /* Covers 64KB to 64GB, (inclusive) */ return log2_in - 15; /* Something is awry so disable */ return 0; @@ -1947,3 +1947,4 @@ module_platform_driver(brcm_pcie_driver); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Broadcom STB PCIe RC driver"); MODULE_AUTHOR("Broadcom"); +MODULE_SOFTDEP("pre: irq_bcm2712_mip"); diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index 481dcc476c55..18e65571c145 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -439,7 +439,7 @@ static irqreturn_t rockchip_pcie_subsys_irq_handler(int irq, void *arg) dev_dbg(dev, "malformed TLP received from the link\n"); if (sub_reg & PCIE_CORE_INT_UCR) - dev_dbg(dev, "malformed TLP received from the link\n"); + dev_dbg(dev, "Unexpected Completion received from the link\n"); if (sub_reg & PCIE_CORE_INT_FCE) dev_dbg(dev, "an error was observed in the flow control advertisements from the other side\n"); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 94ceec50a2b9..8df064b62a2f 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -17,6 +17,8 @@ #include <linux/rculist.h> #include <linux/rcupdate.h> +#include <xen/xen.h> + #include <asm/irqdomain.h> #define VMD_CFGBAR 0 @@ -970,6 +972,24 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) struct vmd_dev *vmd; int err; + if (xen_domain()) { + /* + * Xen doesn't have knowledge about devices in the VMD bus + * because the config space of devices behind the VMD bridge is + * not known to Xen, and hence Xen cannot discover or configure + * them in any way. + * + * Bypass of MSI remapping won't work in that case as direct + * write by Linux to the MSI entries won't result in functional + * interrupts, as Xen is the entity that manages the host + * interrupt controller and must configure interrupts. However + * multiplexing of interrupts by the VMD bridge will work under + * Xen, so force the usage of that mode which must always be + * supported by VMD bridges. + */ + features &= ~VMD_FEAT_CAN_BYPASS_MSI_REMAP; + } + if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) return -ENOMEM; diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c index 54286a40bdfb..6643a88c7a0c 100644 --- a/drivers/pci/endpoint/functions/pci-epf-mhi.c +++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c @@ -125,7 +125,7 @@ static const struct pci_epf_mhi_ep_info sm8450_info = { static struct pci_epf_header sa8775p_header = { .vendorid = PCI_VENDOR_ID_QCOM, - .deviceid = 0x0306, /* FIXME: Update deviceid for sa8775p EP */ + .deviceid = 0x0116, .baseclass_code = PCI_CLASS_OTHERS, .interrupt_pin = PCI_INTERRUPT_INTA, }; diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 14b4c68ab4e1..21aa3709e257 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -703,6 +703,7 @@ static int pci_epf_test_set_bar(struct pci_epf *epf) if (ret) { pci_epf_free_space(epf, epf_test->reg[bar], bar, PRIMARY_INTERFACE); + epf_test->reg[bar] = NULL; dev_err(dev, "Failed to set BAR%d\n", bar); if (bar == test_reg_bar) return ret; @@ -878,6 +879,7 @@ static void pci_epf_test_free_space(struct pci_epf *epf) pci_epf_free_space(epf, epf_test->reg[bar], bar, PRIMARY_INTERFACE); + epf_test->reg[bar] = NULL; } } diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c index 874cb097b093..62d09a528e68 100644 --- a/drivers/pci/endpoint/functions/pci-epf-vntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c @@ -530,7 +530,7 @@ static int epf_ntb_db_bar_init(struct epf_ntb *ntb) struct device *dev = &ntb->epf->dev; int ret; struct pci_epf_bar *epf_bar; - void __iomem *mw_addr; + void *mw_addr; enum pci_barno barno; size_t size = sizeof(u32) * ntb->db_count; @@ -700,7 +700,7 @@ static int epf_ntb_init_epc_bar(struct epf_ntb *ntb) barno = pci_epc_get_next_free_bar(epc_features, barno); if (barno < 0) { dev_err(dev, "Fail to get NTB function BAR\n"); - return barno; + return -ENOENT; } ntb->epf_ntb_bar[bar] = barno; } diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 50bc2892a36c..963d2f3aa5d4 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -236,12 +236,13 @@ void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, } dev = epc->dev.parent; - dma_free_coherent(dev, epf_bar[bar].size, addr, + dma_free_coherent(dev, epf_bar[bar].aligned_size, addr, epf_bar[bar].phys_addr); epf_bar[bar].phys_addr = 0; epf_bar[bar].addr = NULL; epf_bar[bar].size = 0; + epf_bar[bar].aligned_size = 0; epf_bar[bar].barno = 0; epf_bar[bar].flags = 0; } @@ -264,7 +265,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, enum pci_epc_interface_type type) { u64 bar_fixed_size = epc_features->bar[bar].fixed_size; - size_t align = epc_features->align; + size_t aligned_size, align = epc_features->align; struct pci_epf_bar *epf_bar; dma_addr_t phys_addr; struct pci_epc *epc; @@ -281,12 +282,18 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, return NULL; } size = bar_fixed_size; + } else { + /* BAR size must be power of two */ + size = roundup_pow_of_two(size); } - if (align) - size = ALIGN(size, align); - else - size = roundup_pow_of_two(size); + /* + * Allocate enough memory to accommodate the iATU alignment + * requirement. In most cases, this will be the same as .size but + * it might be different if, for example, the fixed size of a BAR + * is smaller than align. + */ + aligned_size = align ? ALIGN(size, align) : size; if (type == PRIMARY_INTERFACE) { epc = epf->epc; @@ -297,7 +304,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, } dev = epc->dev.parent; - space = dma_alloc_coherent(dev, size, &phys_addr, GFP_KERNEL); + space = dma_alloc_coherent(dev, aligned_size, &phys_addr, GFP_KERNEL); if (!space) { dev_err(dev, "failed to allocate mem space\n"); return NULL; @@ -306,6 +313,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, epf_bar[bar].phys_addr = phys_addr; epf_bar[bar].addr = space; epf_bar[bar].size = size; + epf_bar[bar].aligned_size = aligned_size; epf_bar[bar].barno = bar; if (upper_32_bits(size) || epc_features->bar[bar].only_64bit) epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64; diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 573a41869c15..4f85e7fe29ec 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -3,12 +3,15 @@ * PCI Hotplug Driver for PowerPC PowerNV platform. * * Copyright Gavin Shan, IBM Corporation 2016. + * Copyright (C) 2025 Raptor Engineering, LLC + * Copyright (C) 2025 Raptor Computing Systems, LLC */ #include <linux/bitfield.h> #include <linux/libfdt.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/delay.h> #include <linux/pci_hotplug.h> #include <linux/of_fdt.h> @@ -36,8 +39,10 @@ static void pnv_php_register(struct device_node *dn); static void pnv_php_unregister_one(struct device_node *dn); static void pnv_php_unregister(struct device_node *dn); +static void pnv_php_enable_irq(struct pnv_php_slot *php_slot); + static void pnv_php_disable_irq(struct pnv_php_slot *php_slot, - bool disable_device) + bool disable_device, bool disable_msi) { struct pci_dev *pdev = php_slot->pdev; u16 ctrl; @@ -53,19 +58,15 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot, php_slot->irq = 0; } - if (php_slot->wq) { - destroy_workqueue(php_slot->wq); - php_slot->wq = NULL; - } - - if (disable_device) { + if (disable_device || disable_msi) { if (pdev->msix_enabled) pci_disable_msix(pdev); else if (pdev->msi_enabled) pci_disable_msi(pdev); + } + if (disable_device) pci_disable_device(pdev); - } } static void pnv_php_free_slot(struct kref *kref) @@ -74,7 +75,8 @@ static void pnv_php_free_slot(struct kref *kref) struct pnv_php_slot, kref); WARN_ON(!list_empty(&php_slot->children)); - pnv_php_disable_irq(php_slot, false); + pnv_php_disable_irq(php_slot, false, false); + destroy_workqueue(php_slot->wq); kfree(php_slot->name); kfree(php_slot); } @@ -391,6 +393,20 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state) return 0; } +static int pcie_check_link_active(struct pci_dev *pdev) +{ + u16 lnk_status; + int ret; + + ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || PCI_POSSIBLE_ERROR(lnk_status)) + return -ENODEV; + + ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + + return ret; +} + static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) { struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); @@ -403,6 +419,19 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) */ ret = pnv_pci_get_presence_state(php_slot->id, &presence); if (ret >= 0) { + if (pci_pcie_type(php_slot->pdev) == PCI_EXP_TYPE_DOWNSTREAM && + presence == OPAL_PCI_SLOT_EMPTY) { + /* + * Similar to pciehp_hpc, check whether the Link Active + * bit is set to account for broken downstream bridges + * that don't properly assert Presence Detect State, as + * was observed on the Microsemi Switchtec PM8533 PFX + * [11f8:8533]. + */ + if (pcie_check_link_active(php_slot->pdev) > 0) + presence = OPAL_PCI_SLOT_PRESENT; + } + *state = presence; ret = 0; } else { @@ -442,6 +471,61 @@ static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state) return 0; } +static int pnv_php_activate_slot(struct pnv_php_slot *php_slot, + struct hotplug_slot *slot) +{ + int ret, i; + + /* + * Issue initial slot activation command to firmware + * + * Firmware will power slot on, attempt to train the link, and + * discover any downstream devices. If this process fails, firmware + * will return an error code and an invalid device tree. Failure + * can be caused for multiple reasons, including a faulty + * downstream device, poor connection to the downstream device, or + * a previously latched PHB fence. On failure, issue fundamental + * reset up to three times before aborting. + */ + ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON); + if (ret) { + SLOT_WARN( + php_slot, + "PCI slot activation failed with error code %d, possible frozen PHB", + ret); + SLOT_WARN( + php_slot, + "Attempting complete PHB reset before retrying slot activation\n"); + for (i = 0; i < 3; i++) { + /* + * Slot activation failed, PHB may be fenced from a + * prior device failure. + * + * Use the OPAL fundamental reset call to both try a + * device reset and clear any potentially active PHB + * fence / freeze. + */ + SLOT_WARN(php_slot, "Try %d...\n", i + 1); + pci_set_pcie_reset_state(php_slot->pdev, + pcie_warm_reset); + msleep(250); + pci_set_pcie_reset_state(php_slot->pdev, + pcie_deassert_reset); + + ret = pnv_php_set_slot_power_state( + slot, OPAL_PCI_SLOT_POWER_ON); + if (!ret) + break; + } + + if (i >= 3) + SLOT_WARN(php_slot, + "Failed to bring slot online, aborting!\n"); + } + + return ret; +} + static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan) { struct hotplug_slot *slot = &php_slot->slot; @@ -504,7 +588,7 @@ static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan) goto scan; /* Power is off, turn it on and then scan the slot */ - ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON); + ret = pnv_php_activate_slot(php_slot, slot); if (ret) return ret; @@ -561,8 +645,58 @@ static int pnv_php_reset_slot(struct hotplug_slot *slot, bool probe) static int pnv_php_enable_slot(struct hotplug_slot *slot) { struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); + u32 prop32; + int ret; + + ret = pnv_php_enable(php_slot, true); + if (ret) + return ret; + + /* (Re-)enable interrupt if the slot supports surprise hotplug */ + ret = of_property_read_u32(php_slot->dn, "ibm,slot-surprise-pluggable", + &prop32); + if (!ret && prop32) + pnv_php_enable_irq(php_slot); + + return 0; +} + +/* + * Disable any hotplug interrupts for all slots on the provided bus, as well as + * all downstream slots in preparation for a hot unplug. + */ +static int pnv_php_disable_all_irqs(struct pci_bus *bus) +{ + struct pci_bus *child_bus; + struct pci_slot *slot; + + /* First go down child buses */ + list_for_each_entry(child_bus, &bus->children, node) + pnv_php_disable_all_irqs(child_bus); + + /* Disable IRQs for all pnv_php slots on this bus */ + list_for_each_entry(slot, &bus->slots, list) { + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot->hotplug); - return pnv_php_enable(php_slot, true); + pnv_php_disable_irq(php_slot, false, true); + } + + return 0; +} + +/* + * Disable any hotplug interrupts for all downstream slots on the provided + * bus in preparation for a hot unplug. + */ +static int pnv_php_disable_all_downstream_irqs(struct pci_bus *bus) +{ + struct pci_bus *child_bus; + + /* Go down child buses, recursively deactivating their IRQs */ + list_for_each_entry(child_bus, &bus->children, node) + pnv_php_disable_all_irqs(child_bus); + + return 0; } static int pnv_php_disable_slot(struct hotplug_slot *slot) @@ -579,6 +713,13 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot) php_slot->state != PNV_PHP_STATE_REGISTERED) return 0; + /* + * Free all IRQ resources from all child slots before remove. + * Note that we do not disable the root slot IRQ here as that + * would also deactivate the slot hot (re)plug interrupt! + */ + pnv_php_disable_all_downstream_irqs(php_slot->bus); + /* Remove all devices behind the slot */ pci_lock_rescan_remove(); pci_hp_remove_devices(php_slot->bus); @@ -647,6 +788,15 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn) return NULL; } + /* Allocate workqueue for this slot's interrupt handling */ + php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name); + if (!php_slot->wq) { + SLOT_WARN(php_slot, "Cannot alloc workqueue\n"); + kfree(php_slot->name); + kfree(php_slot); + return NULL; + } + if (dn->child && PCI_DN(dn->child)) php_slot->slot_no = PCI_SLOT(PCI_DN(dn->child)->devfn); else @@ -745,16 +895,63 @@ static int pnv_php_enable_msix(struct pnv_php_slot *php_slot) return entry.vector; } +static void +pnv_php_detect_clear_suprise_removal_freeze(struct pnv_php_slot *php_slot) +{ + struct pci_dev *pdev = php_slot->pdev; + struct eeh_dev *edev; + struct eeh_pe *pe; + int i, rc; + + /* + * When a device is surprise removed from a downstream bridge slot, + * the upstream bridge port can still end up frozen due to related EEH + * events, which will in turn block the MSI interrupts for slot hotplug + * detection. + * + * Detect and thaw any frozen upstream PE after slot deactivation. + */ + edev = pci_dev_to_eeh_dev(pdev); + pe = edev ? edev->pe : NULL; + rc = eeh_pe_get_state(pe); + if ((rc == -ENODEV) || (rc == -ENOENT)) { + SLOT_WARN( + php_slot, + "Upstream bridge PE state unknown, hotplug detect may fail\n"); + } else { + if (pe->state & EEH_PE_ISOLATED) { + SLOT_WARN( + php_slot, + "Upstream bridge PE %02x frozen, thawing...\n", + pe->addr); + for (i = 0; i < 3; i++) + if (!eeh_unfreeze_pe(pe)) + break; + if (i >= 3) + SLOT_WARN( + php_slot, + "Unable to thaw PE %02x, hotplug detect will fail!\n", + pe->addr); + else + SLOT_WARN(php_slot, + "PE %02x thawed successfully\n", + pe->addr); + } + } +} + static void pnv_php_event_handler(struct work_struct *work) { struct pnv_php_event *event = container_of(work, struct pnv_php_event, work); struct pnv_php_slot *php_slot = event->php_slot; - if (event->added) + if (event->added) { pnv_php_enable_slot(&php_slot->slot); - else + } else { pnv_php_disable_slot(&php_slot->slot); + pnv_php_detect_clear_suprise_removal_freeze(php_slot); + } kfree(event); } @@ -843,14 +1040,6 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq) u16 sts, ctrl; int ret; - /* Allocate workqueue */ - php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name); - if (!php_slot->wq) { - SLOT_WARN(php_slot, "Cannot alloc workqueue\n"); - pnv_php_disable_irq(php_slot, true); - return; - } - /* Check PDC (Presence Detection Change) is broken or not */ ret = of_property_read_u32(php_slot->dn, "ibm,slot-broken-pdc", &broken_pdc); @@ -869,7 +1058,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq) ret = request_irq(irq, pnv_php_interrupt, IRQF_SHARED, php_slot->name, php_slot); if (ret) { - pnv_php_disable_irq(php_slot, true); + pnv_php_disable_irq(php_slot, true, true); SLOT_WARN(php_slot, "Error %d enabling IRQ %d\n", ret, irq); return; } diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index 055518ee354d..d9996516f49e 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -59,16 +59,15 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); if (pdev && pci_num_vf(pdev)) { - pci_dev_put(pdev); rc = -EBUSY; goto out; } rc = zpci_deconfigure_device(zdev); out: - mutex_unlock(&zdev->state_lock); if (pdev) pci_dev_put(pdev); + mutex_unlock(&zdev->state_lock); return rc; } diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 2f647cac4cae..8b8848788618 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -10,12 +10,12 @@ #include <linux/err.h> #include <linux/export.h> #include <linux/irq.h> +#include <linux/irqdomain.h> #include "../pci.h" #include "msi.h" int pci_msi_enable = 1; -int pci_msi_ignore_mask; /** * pci_msi_supported - check whether MSI may be enabled on a device @@ -295,8 +295,7 @@ static int msi_setup_msi_desc(struct pci_dev *dev, int nvec, /* Lies, damned lies, and MSIs */ if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING) control |= PCI_MSI_FLAGS_MASKBIT; - /* Respect XEN's mask disabling */ - if (pci_msi_ignore_mask) + if (pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY)) control &= ~PCI_MSI_FLAGS_MASKBIT; desc.nvec_used = nvec; @@ -609,12 +608,16 @@ void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc) desc->pci.msi_attrib.is_64 = 1; desc->pci.msi_attrib.default_irq = dev->irq; desc->pci.mask_base = dev->msix_base; - desc->pci.msi_attrib.can_mask = !pci_msi_ignore_mask && - !desc->pci.msi_attrib.is_virtual; - if (desc->pci.msi_attrib.can_mask) { + + if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY) && + !desc->pci.msi_attrib.is_virtual) { void __iomem *addr = pci_msix_desc_addr(desc); + desc->pci.msi_attrib.can_mask = 1; + /* Workaround for SUN NIU insanity, which requires write before read */ + if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST) + writel(0, addr + PCI_MSIX_ENTRY_DATA); desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } } @@ -659,9 +662,6 @@ static void msix_mask_all(void __iomem *base, int tsize) u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT; int i; - if (pci_msi_ignore_mask) - return; - for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE) writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); } @@ -744,15 +744,17 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, /* Disable INTX */ pci_intx_for_msi(dev, 0); - /* - * Ensure that all table entries are masked to prevent - * stale entries from firing in a crash kernel. - * - * Done late to deal with a broken Marvell NVME device - * which takes the MSI-X mask bits into account even - * when MSI-X is disabled, which prevents MSI delivery. - */ - msix_mask_all(dev->msix_base, tsize); + if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY)) { + /* + * Ensure that all table entries are masked to prevent + * stale entries from firing in a crash kernel. + * + * Done late to deal with a broken Marvell NVME device + * which takes the MSI-X mask bits into account even + * when MSI-X is disabled, which prevents MSI delivery. + */ + msix_mask_all(dev->msix_base, tsize); + } pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); pcibios_free_irq(dev); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index af370628e583..99c58ee09fbb 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -816,13 +816,11 @@ int pci_acpi_program_hp_params(struct pci_dev *dev) bool pciehp_is_native(struct pci_dev *bridge) { const struct pci_host_bridge *host; - u32 slot_cap; if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) return false; - pcie_capability_read_dword(bridge, PCI_EXP_SLTCAP, &slot_cap); - if (!(slot_cap & PCI_EXP_SLTCAP_HPC)) + if (!bridge->is_pciehp) return false; if (pcie_ports_native) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 25c07af1686b..3d1365f558d3 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3023,8 +3023,12 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { * pci_bridge_d3_possible - Is it possible to put the bridge into D3 * @bridge: Bridge to check * - * This function checks if it is possible to move the bridge to D3. - * Currently we only allow D3 for recent enough PCIe ports and Thunderbolt. + * Currently we only allow D3 for some PCIe ports and for Thunderbolt. + * + * Return: Whether it is possible to move the bridge to D3. + * + * The return value is guaranteed to be constant across the entire lifetime + * of the bridge, including its hot-removal. */ bool pci_bridge_d3_possible(struct pci_dev *bridge) { @@ -3068,10 +3072,10 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) return false; /* - * It should be safe to put PCIe ports from 2015 or newer - * to D3. + * Out of caution, we only allow PCIe ports from 2015 or newer + * into D3 on x86. */ - if (dmi_get_bios_year() >= 2015) + if (!IS_ENABLED(CONFIG_X86) || dmi_get_bios_year() >= 2015) return true; break; } @@ -4945,7 +4949,7 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type) delay); if (!pcie_wait_for_link_delay(dev, true, delay)) { /* Did not train, no need to wait any further */ - pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n"); + pci_info(dev, "Data Link Layer Link Active not set in %d msec\n", delay); return -ENOTTY; } @@ -5643,7 +5647,8 @@ static void pci_slot_unlock(struct pci_slot *slot) continue; if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } } @@ -6198,38 +6203,66 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, EXPORT_SYMBOL(pcie_bandwidth_available); /** - * pcie_get_speed_cap - query for the PCI device's link speed capability + * pcie_get_supported_speeds - query Supported Link Speed Vector * @dev: PCI device to query * - * Query the PCI device speed capability. Return the maximum link speed - * supported by the device. + * Query @dev supported link speeds. + * + * Implementation Note in PCIe r6.0 sec 7.5.3.18 recommends determining + * supported link speeds using the Supported Link Speeds Vector in the Link + * Capabilities 2 Register (when available). + * + * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18. + * + * Without Link Capabilities 2, i.e., prior to PCIe r3.0, Supported Link + * Speeds field in Link Capabilities is used and only 2.5 GT/s and 5.0 GT/s + * speeds were defined. + * + * For @dev without Supported Link Speed Vector, the field is synthesized + * from the Max Link Speed field in the Link Capabilities Register. + * + * Return: Supported Link Speeds Vector (+ reserved 0 at LSB). */ -enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) +u8 pcie_get_supported_speeds(struct pci_dev *dev) { u32 lnkcap2, lnkcap; + u8 speeds; /* - * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18. The - * implementation note there recommends using the Supported Link - * Speeds Vector in Link Capabilities 2 when supported. - * - * Without Link Capabilities 2, i.e., prior to PCIe r3.0, software - * should use the Supported Link Speeds field in Link Capabilities, - * where only 2.5 GT/s and 5.0 GT/s speeds were defined. + * Speeds retain the reserved 0 at LSB before PCIe Supported Link + * Speeds Vector to allow using SLS Vector bit defines directly. */ pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2); + speeds = lnkcap2 & PCI_EXP_LNKCAP2_SLS; + + /* Ignore speeds higher than Max Link Speed */ + pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); + speeds &= GENMASK(lnkcap & PCI_EXP_LNKCAP_SLS, 0); /* PCIe r3.0-compliant */ - if (lnkcap2) - return PCIE_LNKCAP2_SLS2SPEED(lnkcap2); + if (speeds) + return speeds; - pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); + /* Synthesize from the Max Link Speed field */ if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB) - return PCIE_SPEED_5_0GT; + speeds = PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_2_5GB; else if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_2_5GB) - return PCIE_SPEED_2_5GT; + speeds = PCI_EXP_LNKCAP2_SLS_2_5GB; - return PCI_SPEED_UNKNOWN; + return speeds; +} + +/** + * pcie_get_speed_cap - query for the PCI device's link speed capability + * @dev: PCI device to query + * + * Query the PCI device speed capability. + * + * Return: the maximum link speed supported by the device. + */ +enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) +{ + return PCIE_LNKCAP2_SLS2SPEED(dev->supported_speeds); } EXPORT_SYMBOL(pcie_get_speed_cap); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 65df6d2ac003..b65868e70951 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -390,6 +390,7 @@ static inline int pcie_dev_speed_mbps(enum pci_bus_speed speed) return -EINVAL; } +u8 pcie_get_supported_speeds(struct pci_dev *dev); const char *pci_speed_string(enum pci_bus_speed speed); enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev); enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev); diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 62650a2f00cc..b8289b6c395b 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -81,24 +81,44 @@ void pci_configure_aspm_l1ss(struct pci_dev *pdev) void pci_save_aspm_l1ss_state(struct pci_dev *pdev) { + struct pci_dev *parent = pdev->bus->self; struct pci_cap_saved_state *save_state; - u16 l1ss = pdev->l1ss; u32 *cap; /* + * If this is a Downstream Port, we never restore the L1SS state + * directly; we only restore it when we restore the state of the + * Upstream Port below it. + */ + if (pcie_downstream_port(pdev) || !parent) + return; + + if (!pdev->l1ss || !parent->l1ss) + return; + + /* * Save L1 substate configuration. The ASPM L0s/L1 configuration * in PCI_EXP_LNKCTL_ASPMC is saved by pci_save_pcie_state(). */ - if (!l1ss) + save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS); + if (!save_state) return; - save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS); + cap = &save_state->cap.data[0]; + pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2, cap++); + pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, cap++); + + /* + * Save parent's L1 substate configuration so we have it for + * pci_restore_aspm_l1ss_state(pdev) to restore. + */ + save_state = pci_find_saved_ext_cap(parent, PCI_EXT_CAP_ID_L1SS); if (!save_state) return; cap = &save_state->cap.data[0]; - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL2, cap++); - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, cap++); + pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, cap++); + pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, cap++); } void pci_restore_aspm_l1ss_state(struct pci_dev *pdev) @@ -805,6 +825,15 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &parent_lnkctl); pcie_capability_read_word(child, PCI_EXP_LNKCTL, &child_lnkctl); + /* Disable L0s/L1 before updating L1SS config */ + if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) || + FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) { + pcie_capability_write_word(child, PCI_EXP_LNKCTL, + child_lnkctl & ~PCI_EXP_LNKCTL_ASPMC); + pcie_capability_write_word(parent, PCI_EXP_LNKCTL, + parent_lnkctl & ~PCI_EXP_LNKCTL_ASPMC); + } + /* * Setup L0s state * @@ -829,6 +858,13 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) aspm_l1ss_init(link); + /* Restore L0s/L1 if they were enabled */ + if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) || + FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) { + pcie_capability_write_word(parent, PCI_EXP_LNKCTL, parent_lnkctl); + pcie_capability_write_word(child, PCI_EXP_LNKCTL, child_lnkctl); + } + /* Save default state */ link->aspm_default = link->aspm_enabled; @@ -845,25 +881,28 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) } } -/* Configure the ASPM L1 substates */ +/* Configure the ASPM L1 substates. Caller must disable L1 first. */ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) { - u32 val, enable_req; + u32 val; struct pci_dev *child = link->downstream, *parent = link->pdev; - enable_req = (link->aspm_enabled ^ state) & state; + val = 0; + if (state & PCIE_LINK_STATE_L1_1) + val |= PCI_L1SS_CTL1_ASPM_L1_1; + if (state & PCIE_LINK_STATE_L1_2) + val |= PCI_L1SS_CTL1_ASPM_L1_2; + if (state & PCIE_LINK_STATE_L1_1_PCIPM) + val |= PCI_L1SS_CTL1_PCIPM_L1_1; + if (state & PCIE_LINK_STATE_L1_2_PCIPM) + val |= PCI_L1SS_CTL1_PCIPM_L1_2; /* - * Here are the rules specified in the PCIe spec for enabling L1SS: - * - When enabling L1.x, enable bit at parent first, then at child - * - When disabling L1.x, disable bit at child first, then at parent - * - When enabling ASPM L1.x, need to disable L1 - * (at child followed by parent). - * - The ASPM/PCIPM L1.2 must be disabled while programming timing + * PCIe r6.2, sec 5.5.4, rules for enabling L1 PM Substates: + * - Clear L1.x enable bits at child first, then at parent + * - Set L1.x enable bits at parent first, then at child + * - ASPM/PCIPM L1.2 must be disabled while programming timing * parameters - * - * To keep it simple, disable all L1SS bits first, and later enable - * what is needed. */ /* Disable all L1 substates */ @@ -871,26 +910,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) PCI_L1SS_CTL1_L1SS_MASK, 0); pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, PCI_L1SS_CTL1_L1SS_MASK, 0); - /* - * If needed, disable L1, and it gets enabled later - * in pcie_config_aspm_link(). - */ - if (enable_req & (PCIE_LINK_STATE_L1_1 | PCIE_LINK_STATE_L1_2)) { - pcie_capability_clear_word(child, PCI_EXP_LNKCTL, - PCI_EXP_LNKCTL_ASPM_L1); - pcie_capability_clear_word(parent, PCI_EXP_LNKCTL, - PCI_EXP_LNKCTL_ASPM_L1); - } - - val = 0; - if (state & PCIE_LINK_STATE_L1_1) - val |= PCI_L1SS_CTL1_ASPM_L1_1; - if (state & PCIE_LINK_STATE_L1_2) - val |= PCI_L1SS_CTL1_ASPM_L1_2; - if (state & PCIE_LINK_STATE_L1_1_PCIPM) - val |= PCI_L1SS_CTL1_PCIPM_L1_1; - if (state & PCIE_LINK_STATE_L1_2_PCIPM) - val |= PCI_L1SS_CTL1_PCIPM_L1_2; /* Enable what we need to enable */ pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, @@ -937,21 +956,30 @@ static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state) dwstream |= PCI_EXP_LNKCTL_ASPM_L1; } + /* + * Per PCIe r6.2, sec 5.5.4, setting either or both of the enable + * bits for ASPM L1 PM Substates must be done while ASPM L1 is + * disabled. Disable L1 here and apply new configuration after L1SS + * configuration has been completed. + * + * Per sec 7.5.3.7, when disabling ASPM L1, software must disable + * it in the Downstream component prior to disabling it in the + * Upstream component, and ASPM L1 must be enabled in the Upstream + * component prior to enabling it in the Downstream component. + * + * Sec 7.5.3.7 also recommends programming the same ASPM Control + * value for all functions of a multi-function device. + */ + list_for_each_entry(child, &linkbus->devices, bus_list) + pcie_config_aspm_dev(child, 0); + pcie_config_aspm_dev(parent, 0); + if (link->aspm_capable & PCIE_LINK_STATE_L1SS) pcie_config_aspm_l1ss(link, state); - /* - * Spec 2.0 suggests all functions should be configured the - * same setting for ASPM. Enabling ASPM L1 should be done in - * upstream component first and then downstream, and vice - * versa for disabling ASPM L1. Spec doesn't mention L0S. - */ - if (state & PCIE_LINK_STATE_L1) - pcie_config_aspm_dev(parent, upstream); + pcie_config_aspm_dev(parent, upstream); list_for_each_entry(child, &linkbus->devices, bus_list) pcie_config_aspm_dev(child, dwstream); - if (!(state & PCIE_LINK_STATE_L1)) - pcie_config_aspm_dev(parent, upstream); link->aspm_enabled = state; diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 2b6ef7efa3c1..cdc54315d879 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -260,40 +260,48 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev, void dpc_process_error(struct pci_dev *pdev) { u16 cap = pdev->dpc_cap, status, source, reason, ext_reason; - struct aer_err_info info; + struct aer_err_info info = {}; pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status); - pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source); - - pci_info(pdev, "containment event, status:%#06x source:%#06x\n", - status, source); reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN; - ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT; - pci_warn(pdev, "%s detected\n", - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR) ? - "unmasked uncorrectable error" : - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE) ? - "ERR_NONFATAL" : - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ? - "ERR_FATAL" : - (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ? - "RP PIO error" : - (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ? - "software trigger" : - "reserved error"); - - /* show RP PIO error detail information */ - if (pdev->dpc_rp_extensions && - reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT && - ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) - dpc_process_rp_pio_error(pdev); - else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR && - dpc_get_aer_uncorrect_severity(pdev, &info) && - aer_get_device_error_info(pdev, &info)) { - aer_print_error(pdev, &info); - pci_aer_clear_nonfatal_status(pdev); - pci_aer_clear_fatal_status(pdev); + + switch (reason) { + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR: + pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n", + status); + if (dpc_get_aer_uncorrect_severity(pdev, &info) && + aer_get_device_error_info(pdev, &info)) { + aer_print_error(pdev, &info); + pci_aer_clear_nonfatal_status(pdev); + pci_aer_clear_fatal_status(pdev); + } + break; + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE: + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE: + pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, + &source); + pci_warn(pdev, "containment event, status:%#06x, %s received from %04x:%02x:%02x.%d\n", + status, + (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ? + "ERR_FATAL" : "ERR_NONFATAL", + pci_domain_nr(pdev->bus), PCI_BUS_NUM(source), + PCI_SLOT(source), PCI_FUNC(source)); + break; + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT: + ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT; + pci_warn(pdev, "containment event, status:%#06x: %s detected\n", + status, + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ? + "RP PIO error" : + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ? + "software trigger" : + "reserved error"); + /* show RP PIO error detail information */ + if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO && + pdev->dpc_rp_extensions) + dpc_process_rp_pio_error(pdev); + break; } } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index cf7c7886b642..b358b93a0275 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1627,7 +1627,7 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev) pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, ®32); if (reg32 & PCI_EXP_SLTCAP_HPC) - pdev->is_hotplug_bridge = 1; + pdev->is_hotplug_bridge = pdev->is_pciehp = 1; } static void set_pcie_thunderbolt(struct pci_dev *dev) @@ -1972,6 +1972,9 @@ int pci_setup_device(struct pci_dev *dev) set_pcie_untrusted(dev); + if (pci_is_pcie(dev)) + dev->supported_speeds = pcie_get_supported_speeds(dev); + /* "Unknown power state" */ dev->current_state = PCI_UNKNOWN; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 064067d9c8b5..db609d26811b 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4995,6 +4995,18 @@ static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags) PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } +static int pci_quirk_loongson_acs(struct pci_dev *dev, u16 acs_flags) +{ + /* + * Loongson PCIe Root Ports don't advertise an ACS capability, but + * they do not allow peer-to-peer transactions between Root Ports. + * Allow each Root Port to be in a separate IOMMU group by masking + * SV/RR/CR/UF bits. + */ + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); +} + /* * Wangxun 40G/25G/10G/1G NICs have no ACS capability, but on * multi-function devices, the hardware isolates the functions by @@ -5128,6 +5140,17 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_BROADCOM, 0x1762, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_BROADCOM, 0x1763, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs }, + /* Loongson PCIe Root Ports */ + { PCI_VENDOR_ID_LOONGSON, 0x3C09, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x3C19, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x3C29, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A09, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A19, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A29, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A39, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A49, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A59, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A69, pci_quirk_loongson_acs }, /* Amazon Annapurna Labs */ { PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs }, /* Zhaoxin multi-function devices */ diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index f16c7ce3bf3f..1eceabef9e84 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -814,11 +814,9 @@ static resource_size_t calculate_iosize(resource_size_t size, size = (size & 0xff) + ((size & ~0xffUL) << 2); #endif size = size + size1; - if (size < old_size) - size = old_size; - size = ALIGN(max(size, add_size) + children_add_size, align); - return size; + size = max(size, add_size) + children_add_size; + return ALIGN(max(size, old_size), align); } static resource_size_t calculate_memsize(resource_size_t size, |