diff options
Diffstat (limited to 'drivers/pci')
38 files changed, 1468 insertions, 296 deletions
diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 544922f097c0..0914ddeae17f 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -204,17 +204,13 @@ EXPORT_SYMBOL(pci_bus_set_ops); static DECLARE_WAIT_QUEUE_HEAD(pci_cfg_wait); static noinline void pci_wait_cfg(struct pci_dev *dev) + __must_hold(&pci_lock) { - DECLARE_WAITQUEUE(wait, current); - - __add_wait_queue(&pci_cfg_wait, &wait); do { - set_current_state(TASK_UNINTERRUPTIBLE); raw_spin_unlock_irq(&pci_lock); - schedule(); + wait_event(pci_cfg_wait, !dev->block_cfg_access); raw_spin_lock_irq(&pci_lock); } while (dev->block_cfg_access); - __remove_wait_queue(&pci_cfg_wait, &wait); } /* Returns 0 on success, negative values indicate error. */ @@ -336,15 +332,6 @@ static inline int pcie_cap_version(const struct pci_dev *dev) return pcie_caps_reg(dev) & PCI_EXP_FLAGS_VERS; } -static bool pcie_downstream_port(const struct pci_dev *dev) -{ - int type = pci_pcie_type(dev); - - return type == PCI_EXP_TYPE_ROOT_PORT || - type == PCI_EXP_TYPE_DOWNSTREAM || - type == PCI_EXP_TYPE_PCIE_BRIDGE; -} - bool pcie_cap_has_lnkctl(const struct pci_dev *dev) { int type = pci_pcie_type(dev); diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 495059d923f7..ff1170dd172d 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -322,12 +322,8 @@ void pci_bus_add_device(struct pci_dev *dev) dev->match_driver = true; retval = device_attach(&dev->dev); - if (retval < 0 && retval != -EPROBE_DEFER) { + if (retval < 0 && retval != -EPROBE_DEFER) pci_warn(dev, "device attach failed (%d)\n", retval); - pci_proc_detach_device(dev); - pci_remove_sysfs_dev_files(dev); - return; - } pci_dev_assign_added(dev, true); } diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 011c57cae4b0..6979e895ba1b 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -196,6 +196,14 @@ config PCI_HOST_THUNDER_PEM help Say Y here if you want PCIe support for CN88XX Cavium Thunder SoCs. +config PCI_HOST_OCTEONTX2_PEM + bool "Marvell OcteonTX2 PCIe controller to off-chip devices" + depends on ARM64 + depends on OF + select PCI_HOST_COMMON + help + Say Y here if you want PCIe support for CN9XXX Marvell OcteonTX2 SoCs. + config PCI_HOST_THUNDER_ECAM bool "Cavium Thunder ECAM controller to on-chip devices on pass-1.x silicon" depends on ARM64 || COMPILE_TEST diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile index d56a507495c5..bb635ceb14b8 100644 --- a/drivers/pci/controller/Makefile +++ b/drivers/pci/controller/Makefile @@ -46,5 +46,6 @@ obj-y += dwc/ ifdef CONFIG_PCI obj-$(CONFIG_ARM64) += pci-thunder-ecam.o obj-$(CONFIG_ARM64) += pci-thunder-pem.o +obj-$(CONFIG_ARM64) += pci-octeontx2-pem.o obj-$(CONFIG_ARM64) += pci-xgene.o endif diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index af677254a072..c8c702c494a2 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -422,7 +422,7 @@ static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie) lower_32_bits(start) | OB_ENABLEN); ks_pcie_app_writel(ks_pcie, OB_OFFSET_HI(i), upper_32_bits(start)); - start += OB_WIN_SIZE; + start += OB_WIN_SIZE * SZ_1M; } val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); @@ -510,7 +510,7 @@ static void ks_pcie_stop_link(struct dw_pcie *pci) /* Disable Link training */ val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); val &= ~LTSSM_EN_VAL; - ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val); + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); } static int ks_pcie_start_link(struct dw_pcie *pci) @@ -1354,7 +1354,7 @@ static int __init ks_pcie_probe(struct platform_device *pdev) ret = of_property_read_u32(np, "num-viewport", &num_viewport); if (ret < 0) { dev_err(dev, "unable to read *num-viewport* property\n"); - return ret; + goto err_get_sync; } /* diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c index e35e9eaa50ee..8c9f88704874 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -250,15 +250,15 @@ static int meson_pcie_probe_clocks(struct meson_pcie *mp) if (IS_ERR(res->port_clk)) return PTR_ERR(res->port_clk); - res->mipi_gate = meson_pcie_probe_clock(dev, "pcie_mipi_en", 0); + res->mipi_gate = meson_pcie_probe_clock(dev, "mipi", 0); if (IS_ERR(res->mipi_gate)) return PTR_ERR(res->mipi_gate); - res->general_clk = meson_pcie_probe_clock(dev, "pcie_general", 0); + res->general_clk = meson_pcie_probe_clock(dev, "general", 0); if (IS_ERR(res->general_clk)) return PTR_ERR(res->general_clk); - res->clk = meson_pcie_probe_clock(dev, "pcie", 0); + res->clk = meson_pcie_probe_clock(dev, "pclk", 0); if (IS_ERR(res->clk)) return PTR_ERR(res->clk); @@ -301,11 +301,11 @@ static void meson_pcie_init_dw(struct meson_pcie *mp) meson_cfg_writel(mp, val, PCIE_CFG0); val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF); - val &= ~LINK_CAPABLE_MASK; + val &= ~(LINK_CAPABLE_MASK | FAST_LINK_MODE); meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF); val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF); - val |= LINK_CAPABLE_X1 | FAST_LINK_MODE; + val |= LINK_CAPABLE_X1; meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF); val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 77db32529319..c8b93aae77ed 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -78,7 +78,8 @@ static struct msi_domain_info dw_pcie_msi_domain_info = { irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) { int i, pos, irq; - u32 val, num_ctrls; + unsigned long val; + u32 status, num_ctrls; irqreturn_t ret = IRQ_NONE; num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; @@ -86,14 +87,14 @@ irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) for (i = 0; i < num_ctrls; i++) { dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_STATUS + (i * MSI_REG_CTRL_BLOCK_SIZE), - 4, &val); - if (!val) + 4, &status); + if (!status) continue; ret = IRQ_HANDLED; + val = status; pos = 0; - while ((pos = find_next_bit((unsigned long *) &val, - MAX_MSI_IRQS_PER_CTRL, + while ((pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, pos)) != MAX_MSI_IRQS_PER_CTRL) { irq = irq_find_mapping(pp->irq_domain, (i * MAX_MSI_IRQS_PER_CTRL) + @@ -262,6 +263,8 @@ int dw_pcie_allocate_domains(struct pcie_port *pp) return -ENOMEM; } + irq_domain_update_bus_token(pp->irq_domain, DOMAIN_BUS_NEXUS); + pp->msi_domain = pci_msi_create_irq_domain(fwnode, &dw_pcie_msi_domain_info, pp->irq_domain); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 5d1713069d14..a16994e59776 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -45,7 +45,13 @@ #define PCIE_CAP_CPL_TIMEOUT_DISABLE 0x10 #define PCIE20_PARF_PHY_CTRL 0x40 +#define PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK GENMASK(20, 16) +#define PHY_CTRL_PHY_TX0_TERM_OFFSET(x) ((x) << 16) + #define PCIE20_PARF_PHY_REFCLK 0x4C +#define PHY_REFCLK_SSP_EN BIT(16) +#define PHY_REFCLK_USE_PAD BIT(12) + #define PCIE20_PARF_DBI_BASE_ADDR 0x168 #define PCIE20_PARF_SLV_ADDR_SPACE_SIZE 0x16C #define PCIE20_PARF_MHI_CLOCK_RESET_CTRL 0x174 @@ -76,6 +82,18 @@ #define DBI_RO_WR_EN 1 #define PERST_DELAY_US 1000 +/* PARF registers */ +#define PCIE20_PARF_PCS_DEEMPH 0x34 +#define PCS_DEEMPH_TX_DEEMPH_GEN1(x) ((x) << 16) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(x) ((x) << 8) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(x) ((x) << 0) + +#define PCIE20_PARF_PCS_SWING 0x38 +#define PCS_SWING_TX_SWING_FULL(x) ((x) << 8) +#define PCS_SWING_TX_SWING_LOW(x) ((x) << 0) + +#define PCIE20_PARF_CONFIG_BITS 0x50 +#define PHY_RX0_EQ(x) ((x) << 24) #define PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE 0x358 #define SLV_ADDR_SPACE_SZ 0x10000000 @@ -275,6 +293,7 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie) struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; + struct device_node *node = dev->of_node; u32 val; int ret; @@ -319,9 +338,29 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie) val &= ~BIT(0); writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); + if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) { + writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(34), + pcie->parf + PCIE20_PARF_PCS_DEEMPH); + writel(PCS_SWING_TX_SWING_FULL(120) | + PCS_SWING_TX_SWING_LOW(120), + pcie->parf + PCIE20_PARF_PCS_SWING); + writel(PHY_RX0_EQ(4), pcie->parf + PCIE20_PARF_CONFIG_BITS); + } + + if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) { + /* set TX termination offset */ + val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL); + val &= ~PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK; + val |= PHY_CTRL_PHY_TX0_TERM_OFFSET(7); + writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); + } + /* enable external reference clock */ val = readl(pcie->parf + PCIE20_PARF_PHY_REFCLK); - val |= BIT(16); + val &= ~PHY_REFCLK_USE_PAD; + val |= PHY_REFCLK_SSP_EN; writel(val, pcie->parf + PCIE20_PARF_PHY_REFCLK); ret = reset_control_deassert(res->phy_reset); @@ -1298,7 +1337,13 @@ static void qcom_fixup_class(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_PCI << 8; } -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, PCI_ANY_ID, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0101, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0104, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0106, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0107, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0302, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1000, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1001, qcom_fixup_class); static struct platform_driver qcom_pcie_driver = { .probe = qcom_pcie_probe, diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 134e0306ff00..a2006cc1de8c 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -180,6 +180,8 @@ #define LINK_WAIT_MAX_RETRIES 10 #define LINK_WAIT_USLEEP_MIN 90000 #define LINK_WAIT_USLEEP_MAX 100000 +#define RETRAIN_WAIT_MAX_RETRIES 10 +#define RETRAIN_WAIT_USLEEP_US 2000 #define MSI_IRQ_NUM 32 @@ -239,6 +241,17 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie) return -ETIMEDOUT; } +static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie) +{ + size_t retries; + + for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) { + if (!advk_pcie_link_up(pcie)) + break; + udelay(RETRAIN_WAIT_USLEEP_US); + } +} + static void advk_pcie_setup_hw(struct advk_pcie *pcie) { u32 reg; @@ -331,10 +344,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) advk_pcie_wait_for_link(pcie); - reg = PCIE_CORE_LINK_L0S_ENTRY | - (1 << PCIE_CORE_LINK_WIDTH_SHIFT); - advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); - reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); reg |= PCIE_CORE_CMD_MEM_ACCESS_EN | PCIE_CORE_CMD_IO_ACCESS_EN | @@ -415,7 +424,7 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, case PCI_EXP_RTCTL: { u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG); - *value = (val & PCIE_MSG_PM_PME_MASK) ? PCI_EXP_RTCTL_PMEIE : 0; + *value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE; return PCI_BRIDGE_EMUL_HANDLED; } @@ -426,11 +435,20 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, return PCI_BRIDGE_EMUL_HANDLED; } + case PCI_EXP_LNKCTL: { + /* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */ + u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) & + ~(PCI_EXP_LNKSTA_LT << 16); + if (!advk_pcie_link_up(pcie)) + val |= (PCI_EXP_LNKSTA_LT << 16); + *value = val; + return PCI_BRIDGE_EMUL_HANDLED; + } + case PCI_CAP_LIST_ID: case PCI_EXP_DEVCAP: case PCI_EXP_DEVCTL: case PCI_EXP_LNKCAP: - case PCI_EXP_LNKCTL: *value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); return PCI_BRIDGE_EMUL_HANDLED; default: @@ -447,14 +465,24 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, switch (reg) { case PCI_EXP_DEVCTL: + advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); + break; + case PCI_EXP_LNKCTL: advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); + if (new & PCI_EXP_LNKCTL_RL) + advk_pcie_wait_for_retrain(pcie); break; - case PCI_EXP_RTCTL: - new = (new & PCI_EXP_RTCTL_PMEIE) << 3; - advk_writel(pcie, new, PCIE_ISR0_MASK_REG); + case PCI_EXP_RTCTL: { + /* Only mask/unmask PME interrupt */ + u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG) & + ~PCIE_MSG_PM_PME_MASK; + if ((new & PCI_EXP_RTCTL_PMEIE) == 0) + val |= PCIE_MSG_PM_PME_MASK; + advk_writel(pcie, val, PCIE_ISR0_MASK_REG); break; + } case PCI_EXP_RTSTA: new = (new & PCI_EXP_RTSTA_PME) >> 9; diff --git a/drivers/pci/controller/pci-octeontx2-pem.c b/drivers/pci/controller/pci-octeontx2-pem.c new file mode 100644 index 000000000000..1e14dc065322 --- /dev/null +++ b/drivers/pci/controller/pci-octeontx2-pem.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell OcteonTx2 PCIe host controller + * + * Copyright (C) 2019 Marvell International Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/bitfield.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> +#include "../pci.h" + +#if defined(CONFIG_PCI_HOST_OCTEONTX2_PEM) + +/* Bridge config space reads/writes done using + * these registers. + */ +#define PEM_CFG_WR 0x018 +#define PEM_CFG_RD 0x020 +#define PEM_IB_MERGE_TIMER_CTL 0x1C0 + +#define PCIERC_RAS_EINJ_EN 0x348 +#define PCIERC_RAS_EINJ_CTL6CMPP0 0x364 +#define PCIERC_RAS_EINJ_CTL6CMPV0 0x374 +#define PCIERC_RAS_EINJ_CTL6CHGP1 0x388 +#define PCIERC_RAS_EINJ_CTL6CHGV1 0x398 +#define PCIERC_RAS_EINJ_CTL6PE 0x3A4 +#define PCIERC_RASDP_EP_CTL 0x420 +#define PCIERC_RASDP_DE_ME 0x440 + +struct octeontx2_pem_pci { + u32 ea_entry[3]; + void __iomem *pem_reg_base; +}; + +static int octeontx2_pem_bridge_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct pci_config_window *cfg = bus->sysdata; + struct octeontx2_pem_pci *pem_pci; + u64 read_val; + + if (devfn != 0 || where >= 2048) { + *val = ~0; + return PCIBIOS_DEVICE_NOT_FOUND; + } + + pem_pci = (struct octeontx2_pem_pci *)cfg->priv; + + /* + * 32-bit accesses only. Write the address to the low order + * bits of PEM_CFG_RD, then trigger the read by reading back. + * The config data lands in the upper 32-bits of PEM_CFG_RD. + */ + read_val = where & ~3ull; + writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD); + read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD); + read_val >>= 32; + + /* HW reset value at few config space locations are + * garbage, fix them. + */ + switch (where & ~3) { + case 0x00: /* DevID & VenID */ + read_val = 0xA02D177D; + break; + case 0x04: + read_val = 0x00100006; + break; + case 0x08: + read_val = 0x06040100; + break; + case 0x0c: + read_val = 0x00010000; + break; + case 0x18: + read_val = 0x00010100; + break; + case 0x40: + read_val &= 0xffff00ff; + read_val |= 0x00005000; /* In RC mode, point to EA capability */ + break; + case 0x5c: /* EA_ENTRY2 */ + read_val = pem_pci->ea_entry[0]; + break; + case 0x60: /* EA_ENTRY3 */ + read_val = pem_pci->ea_entry[1]; + break; + case 0x64: /* EA_ENTRY4 */ + read_val = pem_pci->ea_entry[2]; + break; + case 0x70: /* Express Cap */ + /* HW reset value is '0', set PME interrupt vector to 1 */ + if (!(read_val & (0x1f << 25))) + read_val |= (1u << 25); + break; + default: + break; + } + read_val >>= (8 * (where & 3)); + switch (size) { + case 1: + read_val &= 0xff; + break; + case 2: + read_val &= 0xffff; + break; + default: + break; + } + *val = read_val; + return PCIBIOS_SUCCESSFUL; +} + +static int octeontx2_pem_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct pci_config_window *cfg = bus->sysdata; + + if (bus->number < cfg->busr.start || + bus->number > cfg->busr.end) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* + * The first device on the bus is the PEM PCIe bridge. + * Special case its config access. + */ + if (bus->number == cfg->busr.start) + return octeontx2_pem_bridge_read(bus, devfn, where, size, val); + + return pci_generic_config_read(bus, devfn, where, size, val); +} + +/* + * Some of the w1c_bits below also include read-only or non-writable + * reserved bits, this makes the code simpler and is OK as the bits + * are not affected by writing zeros to them. + */ +static u32 octeontx2_pem_bridge_w1c_bits(u64 where_aligned) +{ + u32 w1c_bits = 0; + + switch (where_aligned) { + case 0x04: /* Command/Status */ + case 0x1c: /* Base and I/O Limit/Secondary Status */ + w1c_bits = 0xff000000; + break; + case 0x44: /* Power Management Control and Status */ + w1c_bits = 0xfffffe00; + break; + case 0x78: /* Device Control/Device Status */ + case 0x80: /* Link Control/Link Status */ + case 0x88: /* Slot Control/Slot Status */ + case 0x90: /* Root Status */ + case 0xa0: /* Link Control 2 Registers/Link Status 2 */ + w1c_bits = 0xffff0000; + break; + case 0x104: /* Uncorrectable Error Status */ + case 0x110: /* Correctable Error Status */ + case 0x130: /* Error Status */ + case 0x180: /* Lane error status */ + w1c_bits = 0xffffffff; + break; + default: + break; + } + return w1c_bits; +} + +/* Some bits must be written to one so they appear to be read-only. */ +static u32 octeontx2_pem_bridge_w1_bits(u64 where_aligned) +{ + u32 w1_bits; + + switch (where_aligned) { + case 0x1c: /* I/O Base / I/O Limit, Secondary Status */ + /* Force 32-bit I/O addressing. */ + w1_bits = 0x0101; + break; + case 0x24: /* Prefetchable Memory Base / Prefetchable Memory Limit */ + /* Force 64-bit addressing */ + w1_bits = 0x00010001; + break; + default: + w1_bits = 0; + break; + } + return w1_bits; +} + +static int octeontx2_pem_bridge_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct pci_config_window *cfg = bus->sysdata; + struct octeontx2_pem_pci *pem_pci; + u64 where_aligned = where & ~3ull; + u64 write_val, read_val; + u32 mask = 0; + + + if (devfn != 0 || where >= 2048) + return PCIBIOS_DEVICE_NOT_FOUND; + + pem_pci = (struct octeontx2_pem_pci *)cfg->priv; + + /* + * 32-bit accesses only. If the write is for a size smaller + * than 32-bits, we must first read the 32-bit value and merge + * in the desired bits and then write the whole 32-bits back + * out. + */ + switch (size) { + case 1: + writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD); + read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD); + read_val >>= 32; + mask = ~(0xff << (8 * (where & 3))); + read_val &= mask; + val = (val & 0xff) << (8 * (where & 3)); + val |= (u32)read_val; + break; + case 2: + writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD); + read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD); + read_val >>= 32; + mask = ~(0xffff << (8 * (where & 3))); + read_val &= mask; + val = (val & 0xffff) << (8 * (where & 3)); + val |= (u32)read_val; + break; + default: + break; + } + + /* + * By expanding the write width to 32 bits, we may + * inadvertently hit some W1C bits that were not intended to + * be written. Calculate the mask that must be applied to the + * data to be written to avoid these cases. + */ + if (mask) { + u32 w1c_bits = octeontx2_pem_bridge_w1c_bits(where); + + if (w1c_bits) { + mask &= w1c_bits; + val &= ~mask; + } + } + + /* + * Some bits must be read-only with value of one. Since the + * access method allows these to be cleared if a zero is + * written, force them to one before writing. + */ + val |= octeontx2_pem_bridge_w1_bits(where_aligned); + + /* + * Low order bits are the config address, the high order 32 + * bits are the data to be written. + */ + write_val = (((u64)val) << 32) | where_aligned; + writeq(write_val, pem_pci->pem_reg_base + PEM_CFG_WR); + return PCIBIOS_SUCCESSFUL; +} + +static void octeontx2_be_workaround_init(struct pci_bus *bus) +{ + u32 val; + + /* Ensure that PCIERC_RASDP_DE_ME.ERR_MODE is set to 0 */ + octeontx2_pem_bridge_read(bus, 0x00, + PCIERC_RASDP_DE_ME, 4, &val); + octeontx2_pem_bridge_write(bus, 0x00, + PCIERC_RASDP_DE_ME, 4, val & ~BIT(0)); + + /* Disable parity error correction */ + octeontx2_pem_bridge_read(bus, 0x00, + PCIERC_RASDP_EP_CTL, 4, &val); + octeontx2_pem_bridge_write(bus, 0x00, + PCIERC_RASDP_EP_CTL, 4, val | BIT(0)); + + /* Enable RAS to change header + * PCIERC_RAS_EINJ_EN.EINJ0_EN.set(0); + * PCIERC_RAS_EINJ_EN.EINJ1_EN.set(0); + * PCIERC_RAS_EINJ_EN.EINJ2_EN.set(0); + * PCIERC_RAS_EINJ_EN.EINJ3_EN.set(0); + * PCIERC_RAS_EINJ_EN.EINJ4_EN.set(0); + * PCIERC_RAS_EINJ_EN.EINJ5_EN.set(0); + * PCIERC_RAS_EINJ_EN.EINJ6_EN.set(1); + */ + octeontx2_pem_bridge_write(bus, 0x00, + PCIERC_RAS_EINJ_EN, 4, BIT(6)); + + /* Set up error injection count to 1 and + * set type to TLP and INV_CNTRL must be 0. + */ + octeontx2_pem_bridge_write(bus, 0x00, + PCIERC_RAS_EINJ_CTL6PE, 4, 1); + + /* Set up compare point to compare Fmt/Type field in TLP Header word 0 + * Where bits[31:0] = tlp_dw[7:0], tlp_dw[15:18], + * tlp_dw[23:16], tlp_dw[31:24]. + * + * PCIERC_RAS_EINJ_CTL6CMPP0.EINJ6_COM_PT_H0.set(32'hfe00_0000); + */ + octeontx2_pem_bridge_write(bus, 0x00, + PCIERC_RAS_EINJ_CTL6CMPP0, 4, 0xFE000000); + + /* Set up the value to compare against, + * look for Fmt/Type to indicate CfgRd/CfWr - both type 0 or 1. + * Where bits[31:0] = tlp_dw[7:0], tlp_dw[15:18], + * tlp_dw[23:16], tlp_dw[31:24] + */ + octeontx2_pem_bridge_write(bus, 0x00, + PCIERC_RAS_EINJ_CTL6CMPV0, 4, 0x44000000); + + /* Set up the bit position in TLP Header word 1 to replace + * (LBE is bits 7:4, FBE is bits 3:0). + * + * Where bits[31:0] = tlp_dw[7:0], tlp_dw[15:18], + * tlp_dw[23:16], tlp_dw[31:24]. + */ + octeontx2_pem_bridge_write(bus, 0x00, + PCIERC_RAS_EINJ_CTL6CHGP1, 4, 0xFF); +} + +static void octeontx2_be_workaround(struct pci_bus *bus, int where, + int size, u32 val) +{ + struct pci_host_bridge *rc; + u32 reg, be = 0; + + rc = pci_find_host_bridge(bus); + + /* Setup RAS to inject one error */ + octeontx2_be_workaround_init(rc->bus); + + /* Get byte-enable to inject into TLP */ + where &= 0x03; + switch (size) { + case 1: + be = 1 << where; + break; + case 2: + be = 3 << where; + break; + case 4: + be = 0xF; + } + + /* Set up the value you'd like to use for FBE (Cfg ops must have LBE==0) + * Where bits[31:0] = tlp_dw[7:0], tlp_dw[15:18], + * tlp_dw[23:16], tlp_dw[31:24]. + */ + octeontx2_pem_bridge_write(rc->bus, 0x00, + PCIERC_RAS_EINJ_CTL6CHGV1, 4, be); + + /* To be absolutely sure that the ECAM access does not get to + * the MAC prior to the PCIERC register updates that are setting + * up for that ECAM access, SW should read back one of the + * registers it wrote before launching the ECAM access. + */ + octeontx2_pem_bridge_read(rc->bus, 0x00, + PCIERC_RAS_EINJ_CTL6CHGV1, 4, ®); +} + +static int octeontx2_pem_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct pci_config_window *cfg = bus->sysdata; + + if (bus->number < cfg->busr.start || + bus->number > cfg->busr.end) + return PCIBIOS_DEVICE_NOT_FOUND; + /* + * The first device on the bus is the PEM PCIe bridge. + * Special case its config access. + */ + if (bus->number == cfg->busr.start) + return octeontx2_pem_bridge_write(bus, devfn, where, size, val); + + octeontx2_be_workaround(bus, where, size, val); + + return pci_generic_config_write(bus, devfn, where, size, val); +} + +static int octeontx2_pem_init(struct device *dev, struct pci_config_window *cfg, + struct resource *res_pem) +{ + struct octeontx2_pem_pci *pem_pci; + resource_size_t bar4_start; + u64 val; + + pem_pci = devm_kzalloc(dev, sizeof(*pem_pci), GFP_KERNEL); + if (!pem_pci) + return -ENOMEM; + + pem_pci->pem_reg_base = devm_ioremap(dev, res_pem->start, 0x10000); + if (!pem_pci->pem_reg_base) + return -ENOMEM; + + /* As per HW Errata 34726, an issue exists whereby inbound write + * merging may cause undefined operation. Hence disabling it. + * + * Need to revisit this for future silicon passes and versions. + */ + val = readq(pem_pci->pem_reg_base + PEM_IB_MERGE_TIMER_CTL); + val |= BIT_ULL(10); + writeq(val, pem_pci->pem_reg_base + PEM_IB_MERGE_TIMER_CTL); + + /* + * The MSI-X BAR for the PEM and AER interrupts is located at + * a fixed offset from the PEM register base. Generate a + * fragment of the synthesized Enhanced Allocation capability + * structure here for the BAR. + */ + bar4_start = res_pem->start + 0xf00000000; + pem_pci->ea_entry[0] = (u32)bar4_start | 2; + pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u; + pem_pci->ea_entry[2] = (u32)(bar4_start >> 32); + + cfg->priv = pem_pci; + return 0; +} + +static int octeontx2_pem_platform_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct platform_device *pdev; + struct resource *res_pem; + + if (!dev->of_node) + return -EINVAL; + + pdev = to_platform_device(dev); + + /* + * The second register range is the PEM bridge to the PCIe + * bus. It has a different config access method than those + * devices behind the bridge. + */ + res_pem = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res_pem) { + dev_err(dev, "missing \"reg[1]\"property\n"); + return -EINVAL; + } + + return octeontx2_pem_init(dev, cfg, res_pem); +} + +static struct pci_ecam_ops pci_octeontx2_pem_ops = { + .bus_shift = 20, + .init = octeontx2_pem_platform_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = octeontx2_pem_config_read, + .write = octeontx2_pem_config_write, + } +}; + +static const struct of_device_id octeontx2_pem_of_match[] = { + { .compatible = "marvell,pci-host-octeontx2-pem" }, + { }, +}; + +static int octeontx2_pem_probe(struct platform_device *pdev) +{ + return pci_host_common_probe(pdev, &pci_octeontx2_pem_ops); +} + +static struct platform_driver octeontx2_pem_driver = { + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = octeontx2_pem_of_match, + .suppress_bind_attrs = true, + }, + .probe = octeontx2_pem_probe, +}; +builtin_platform_driver(octeontx2_pem_driver); + +#endif diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c index 03c42e8684f6..952f7cfebdf8 100644 --- a/drivers/pci/controller/pci-tegra.c +++ b/drivers/pci/controller/pci-tegra.c @@ -2414,7 +2414,7 @@ static int tegra_pcie_probe(struct platform_device *pdev) pm_runtime_enable(pcie->dev); err = pm_runtime_get_sync(pcie->dev); - if (err) { + if (err < 0) { dev_err(dev, "fail to enable pcie controller: %d\n", err); goto teardown_msi; } diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c index d219404bad92..9a86bb7448ac 100644 --- a/drivers/pci/controller/pci-v3-semi.c +++ b/drivers/pci/controller/pci-v3-semi.c @@ -743,7 +743,7 @@ static int v3_pci_probe(struct platform_device *pdev) int ret; LIST_HEAD(res); - host = pci_alloc_host_bridge(sizeof(*v3)); + host = devm_pci_alloc_host_bridge(dev, sizeof(*v3)); if (!host) return -ENOMEM; diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c index 97e251090b4f..0dfc778f40a7 100644 --- a/drivers/pci/controller/pcie-cadence-host.c +++ b/drivers/pci/controller/pcie-cadence-host.c @@ -102,6 +102,7 @@ static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) { struct cdns_pcie *pcie = &rc->pcie; u32 value, ctrl; + u32 id; /* * Set the root complex BAR configuration register: @@ -121,8 +122,12 @@ static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); /* Set root port configuration space */ - if (rc->vendor_id != 0xffff) - cdns_pcie_rp_writew(pcie, PCI_VENDOR_ID, rc->vendor_id); + if (rc->vendor_id != 0xffff) { + id = CDNS_PCIE_LM_ID_VENDOR(rc->vendor_id) | + CDNS_PCIE_LM_ID_SUBSYS(rc->vendor_id); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id); + } + if (rc->device_id != 0xffff) cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id); diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c index e3ca46497470..0795c46b2bbb 100644 --- a/drivers/pci/controller/pcie-iproc.c +++ b/drivers/pci/controller/pcie-iproc.c @@ -1608,6 +1608,30 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_disable_msi_parsing); +static void quirk_paxc_bridge(struct pci_dev *pdev) +{ + /* + * The PCI config space is shared with the PAXC root port and the first + * Ethernet device. So, we need to workaround this by telling the PCI + * code that the bridge is not an Ethernet device. + */ + if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + pdev->class = PCI_CLASS_BRIDGE_PCI << 8; + + /* + * MPSS is not being set properly (as it is currently 0). This is + * because that area of the PCI config space is hard coded to zero, and + * is not modifiable by firmware. Set this to 2 (e.g., 512 byte MPS) + * so that the MPS can be set to the real max value. + */ + pdev->pcie_mpss = 2; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge); + MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>"); MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index 8e7e714e33fd..8be0e8d880e4 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -94,8 +94,11 @@ #define LINK_SPEED_2_5GTS (1 << 16) #define LINK_SPEED_5_0GTS (2 << 16) #define MACCTLR 0x011058 +#define MACCTLR_NFTS_MASK GENMASK(23, 16) /* The name is from SH7786 */ #define SPEED_CHANGE BIT(24) #define SCRAMBLE_DISABLE BIT(27) +#define LTSMDIS BIT(31) +#define MACCTLR_INIT_VAL (LTSMDIS | MACCTLR_NFTS_MASK) #define PMSR 0x01105c #define MACS2R 0x011078 #define MACCGSPSETR 0x011084 @@ -335,11 +338,12 @@ static struct pci_ops rcar_pcie_ops = { }; static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie, - struct resource *res) + struct resource_entry *window) { /* Setup PCIe address space mappings for each resource */ resource_size_t size; resource_size_t res_start; + struct resource *res = window->res; u32 mask; rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win)); @@ -353,9 +357,9 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie, rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win)); if (res->flags & IORESOURCE_IO) - res_start = pci_pio_to_address(res->start); + res_start = pci_pio_to_address(res->start) - window->offset; else - res_start = res->start; + res_start = res->start - window->offset; rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPAUR(win)); rcar_pci_write_reg(pcie, lower_32_bits(res_start) & ~0x7F, @@ -384,7 +388,7 @@ static int rcar_pcie_setup(struct list_head *resource, struct rcar_pcie *pci) switch (resource_type(res)) { case IORESOURCE_IO: case IORESOURCE_MEM: - rcar_pcie_setup_window(i, pci, res); + rcar_pcie_setup_window(i, pci, win); i++; break; case IORESOURCE_BUS: @@ -618,6 +622,8 @@ static int rcar_pcie_hw_init(struct rcar_pcie *pcie) if (IS_ENABLED(CONFIG_PCI_MSI)) rcar_pci_write_reg(pcie, 0x801f0000, PCIEMSITXR); + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); + /* Finish initialization - establish a PCI Express link */ rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); @@ -1301,6 +1307,7 @@ static int rcar_pcie_resume_noirq(struct device *dev) return 0; /* Re-establish the PCIe link */ + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); return rcar_pcie_wait_for_dl(pcie); } diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 21ee1833a247..583abbb7a7a2 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -593,9 +593,11 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) if (!membar2) return -ENOMEM; offset[0] = vmd->dev->resource[VMD_MEMBAR1].start - - readq(membar2 + MB2_SHADOW_OFFSET); + (readq(membar2 + MB2_SHADOW_OFFSET) & + PCI_BASE_ADDRESS_MEM_MASK); offset[1] = vmd->dev->resource[VMD_MEMBAR2].start - - readq(membar2 + MB2_SHADOW_OFFSET + 8); + (readq(membar2 + MB2_SHADOW_OFFSET + 8) & + PCI_BASE_ADDRESS_MEM_MASK); pci_iounmap(vmd->dev, membar2); } } @@ -854,6 +856,8 @@ static const struct pci_device_id vmd_ids[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW | VMD_FEAT_HAS_BUS_RESTRICTIONS,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B), + .driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,}, {0,} }; MODULE_DEVICE_TABLE(pci, vmd_ids); diff --git a/drivers/pci/endpoint/pci-epc-mem.c b/drivers/pci/endpoint/pci-epc-mem.c index 2bf8bd1f0563..abfac1109a13 100644 --- a/drivers/pci/endpoint/pci-epc-mem.c +++ b/drivers/pci/endpoint/pci-epc-mem.c @@ -79,6 +79,7 @@ int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_base, size_t size, mem->page_size = page_size; mem->pages = pages; mem->size = size; + mutex_init(&mem->lock); epc->mem = mem; @@ -122,7 +123,7 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, phys_addr_t *phys_addr, size_t size) { int pageno; - void __iomem *virt_addr; + void __iomem *virt_addr = NULL; struct pci_epc_mem *mem = epc->mem; unsigned int page_shift = ilog2(mem->page_size); int order; @@ -130,15 +131,18 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, size = ALIGN(size, mem->page_size); order = pci_epc_mem_get_order(mem, size); + mutex_lock(&mem->lock); pageno = bitmap_find_free_region(mem->bitmap, mem->pages, order); if (pageno < 0) - return NULL; + goto ret; - *phys_addr = mem->phys_base + (pageno << page_shift); + *phys_addr = mem->phys_base + ((phys_addr_t)pageno << page_shift); virt_addr = ioremap(*phys_addr, size); if (!virt_addr) bitmap_release_region(mem->bitmap, pageno, order); +ret: + mutex_unlock(&mem->lock); return virt_addr; } EXPORT_SYMBOL_GPL(pci_epc_mem_alloc_addr); @@ -164,7 +168,9 @@ void pci_epc_mem_free_addr(struct pci_epc *epc, phys_addr_t phys_addr, pageno = (phys_addr - mem->phys_base) >> page_shift; size = ALIGN(size, mem->page_size); order = pci_epc_mem_get_order(mem, size); + mutex_lock(&mem->lock); bitmap_release_region(mem->bitmap, pageno, order); + mutex_unlock(&mem->lock); } EXPORT_SYMBOL_GPL(pci_epc_mem_free_addr); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index e4c46637f32f..6e60b4b1bf53 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -122,13 +122,21 @@ static struct acpiphp_context *acpiphp_grab_context(struct acpi_device *adev) struct acpiphp_context *context; acpi_lock_hp_context(); + context = acpiphp_get_context(adev); - if (!context || context->func.parent->is_going_away) { - acpi_unlock_hp_context(); - return NULL; + if (!context) + goto unlock; + + if (context->func.parent->is_going_away) { + acpiphp_put_context(context); + context = NULL; + goto unlock; } + get_bridge(context->func.parent); acpiphp_put_context(context); + +unlock: acpi_unlock_hp_context(); return context; } @@ -449,8 +457,15 @@ static void acpiphp_native_scan_bridge(struct pci_dev *bridge) /* Scan non-hotplug bridges that need to be reconfigured */ for_each_pci_bridge(dev, bus) { - if (!hotplug_is_native(dev)) - max = pci_scan_bridge(bus, dev, max, 1); + if (hotplug_is_native(dev)) + continue; + + max = pci_scan_bridge(bus, dev, max, 1); + if (dev->subordinate) { + pcibios_resource_survey_bus(dev->subordinate); + pci_bus_size_bridges(dev->subordinate); + pci_bus_assign_resources(dev->subordinate); + } } } @@ -480,7 +495,6 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (PCI_SLOT(dev->devfn) == slot->device) acpiphp_native_scan_bridge(dev); } - pci_assign_unassigned_bridge_resources(bus->self); } else { LIST_HEAD(add_list); int max, pass; diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index 8c51a04b8083..e28b4fffd84d 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -72,6 +72,7 @@ extern int pciehp_poll_time; * @reset_lock: prevents access to the Data Link Layer Link Active bit in the * Link Status register and to the Presence Detect State bit in the Slot * Status register during a slot reset which may cause them to flap + * @ist_running: flag to keep user request waiting while IRQ thread is running * @request_result: result of last user request submitted to the IRQ thread * @requester: wait queue to wake up on completion of user request, * used for synchronous slot enable/disable request via sysfs @@ -101,6 +102,7 @@ struct controller { struct hotplug_slot hotplug_slot; /* hotplug core interface */ struct rw_semaphore reset_lock; + unsigned int ist_running; int request_result; wait_queue_head_t requester; }; @@ -173,10 +175,10 @@ int pciehp_query_power_fault(struct controller *ctrl); void pciehp_green_led_on(struct controller *ctrl); void pciehp_green_led_off(struct controller *ctrl); void pciehp_green_led_blink(struct controller *ctrl); -bool pciehp_card_present(struct controller *ctrl); -bool pciehp_card_present_or_link_active(struct controller *ctrl); +int pciehp_card_present(struct controller *ctrl); +int pciehp_card_present_or_link_active(struct controller *ctrl); int pciehp_check_link_status(struct controller *ctrl); -bool pciehp_check_link_active(struct controller *ctrl); +int pciehp_check_link_active(struct controller *ctrl); void pciehp_release_ctrl(struct controller *ctrl); int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot); diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index 6ad0d86762cb..4c032d75c874 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -134,10 +134,15 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl->pcie->port; + int ret; pci_config_pm_runtime_get(pdev); - *value = pciehp_card_present_or_link_active(ctrl); + ret = pciehp_card_present_or_link_active(ctrl); pci_config_pm_runtime_put(pdev); + if (ret < 0) + return ret; + + *value = ret; return 0; } @@ -153,13 +158,13 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) */ static void pciehp_check_presence(struct controller *ctrl) { - bool occupied; + int occupied; down_read(&ctrl->reset_lock); mutex_lock(&ctrl->state_lock); occupied = pciehp_card_present_or_link_active(ctrl); - if ((occupied && (ctrl->state == OFF_STATE || + if ((occupied > 0 && (ctrl->state == OFF_STATE || ctrl->state == BLINKINGON_STATE)) || (!occupied && (ctrl->state == ON_STATE || ctrl->state == BLINKINGOFF_STATE))) @@ -248,7 +253,7 @@ static bool pme_is_native(struct pcie_device *dev) return pcie_ports_native || host->native_pme; } -static int pciehp_suspend(struct pcie_device *dev) +static void pciehp_disable_interrupt(struct pcie_device *dev) { /* * Disable hotplug interrupt so that it does not trigger @@ -256,7 +261,19 @@ static int pciehp_suspend(struct pcie_device *dev) */ if (pme_is_native(dev)) pcie_disable_interrupt(get_service_data(dev)); +} + +#ifdef CONFIG_PM_SLEEP +static int pciehp_suspend(struct pcie_device *dev) +{ + /* + * If the port is already runtime suspended we can keep it that + * way. + */ + if (dev_pm_smart_suspend_and_suspended(&dev->port->dev)) + return 0; + pciehp_disable_interrupt(dev); return 0; } @@ -274,6 +291,7 @@ static int pciehp_resume_noirq(struct pcie_device *dev) return 0; } +#endif static int pciehp_resume(struct pcie_device *dev) { @@ -287,6 +305,12 @@ static int pciehp_resume(struct pcie_device *dev) return 0; } +static int pciehp_runtime_suspend(struct pcie_device *dev) +{ + pciehp_disable_interrupt(dev); + return 0; +} + static int pciehp_runtime_resume(struct pcie_device *dev) { struct controller *ctrl = get_service_data(dev); @@ -313,10 +337,12 @@ static struct pcie_port_service_driver hpdriver_portdrv = { .remove = pciehp_remove, #ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .suspend = pciehp_suspend, .resume_noirq = pciehp_resume_noirq, .resume = pciehp_resume, - .runtime_suspend = pciehp_suspend, +#endif + .runtime_suspend = pciehp_runtime_suspend, .runtime_resume = pciehp_runtime_resume, #endif /* PM */ }; diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 631ced0ab28a..abb460c93554 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -221,7 +221,7 @@ void pciehp_handle_disable_request(struct controller *ctrl) void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) { - bool present, link_active; + int present, link_active; /* * If the slot is on and presence or link has changed, turn it off. @@ -252,7 +252,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) mutex_lock(&ctrl->state_lock); present = pciehp_card_present(ctrl); link_active = pciehp_check_link_active(ctrl); - if (!present && !link_active) { + if (present <= 0 && link_active <= 0) { mutex_unlock(&ctrl->state_lock); return; } @@ -368,7 +368,8 @@ int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot) ctrl->request_result = -ENODEV; pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC); wait_event(ctrl->requester, - !atomic_read(&ctrl->pending_events)); + !atomic_read(&ctrl->pending_events) && + !ctrl->ist_running); return ctrl->request_result; case POWERON_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering on state\n", @@ -401,7 +402,8 @@ int pciehp_sysfs_disable_slot(struct hotplug_slot *hotplug_slot) mutex_unlock(&ctrl->state_lock); pciehp_request(ctrl, DISABLE_SLOT); wait_event(ctrl->requester, - !atomic_read(&ctrl->pending_events)); + !atomic_read(&ctrl->pending_events) && + !ctrl->ist_running); return ctrl->request_result; case POWEROFF_STATE: ctrl_info(ctrl, "Slot(%s): Already in powering off state\n", diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index bd990e3371e3..bbb1f23fb510 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -201,17 +201,29 @@ static void pcie_write_cmd_nowait(struct controller *ctrl, u16 cmd, u16 mask) pcie_do_write_cmd(ctrl, cmd, mask, false); } -bool pciehp_check_link_active(struct controller *ctrl) +/** + * pciehp_check_link_active() - Is the link active + * @ctrl: PCIe hotplug controller + * + * Check whether the downstream link is currently active. Note it is + * possible that the card is removed immediately after this so the + * caller may need to take it into account. + * + * If the hotplug controller itself is not available anymore returns + * %-ENODEV. + */ +int pciehp_check_link_active(struct controller *ctrl) { struct pci_dev *pdev = ctrl_dev(ctrl); u16 lnk_status; - bool ret; + int ret; - pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); - ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || lnk_status == (u16)~0) + return -ENODEV; - if (ret) - ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); + ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status); return ret; } @@ -373,13 +385,29 @@ void pciehp_get_latch_status(struct controller *ctrl, u8 *status) *status = !!(slot_status & PCI_EXP_SLTSTA_MRLSS); } -bool pciehp_card_present(struct controller *ctrl) +/** + * pciehp_card_present() - Is the card present + * @ctrl: PCIe hotplug controller + * + * Function checks whether the card is currently present in the slot and + * in that case returns true. Note it is possible that the card is + * removed immediately after the check so the caller may need to take + * this into account. + * + * It the hotplug controller itself is not available anymore returns + * %-ENODEV. + */ +int pciehp_card_present(struct controller *ctrl) { struct pci_dev *pdev = ctrl_dev(ctrl); u16 slot_status; + int ret; - pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); - return slot_status & PCI_EXP_SLTSTA_PDS; + ret = pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || slot_status == (u16)~0) + return -ENODEV; + + return !!(slot_status & PCI_EXP_SLTSTA_PDS); } /** @@ -390,10 +418,19 @@ bool pciehp_card_present(struct controller *ctrl) * Presence Detect State bit, this helper also returns true if the Link Active * bit is set. This is a concession to broken hotplug ports which hardwire * Presence Detect State to zero, such as Wilocity's [1ae9:0200]. + * + * Returns: %1 if the slot is occupied and %0 if it is not. If the hotplug + * port is not present anymore returns %-ENODEV. */ -bool pciehp_card_present_or_link_active(struct controller *ctrl) +int pciehp_card_present_or_link_active(struct controller *ctrl) { - return pciehp_card_present(ctrl) || pciehp_check_link_active(ctrl); + int ret; + + ret = pciehp_card_present(ctrl); + if (ret) + return ret; + + return pciehp_check_link_active(ctrl); } int pciehp_query_power_fault(struct controller *ctrl) @@ -608,23 +645,22 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) irqreturn_t ret; u32 events; + ctrl->ist_running = true; pci_config_pm_runtime_get(pdev); /* rerun pciehp_isr() if the port was inaccessible on interrupt */ if (atomic_fetch_and(~RERUN_ISR, &ctrl->pending_events) & RERUN_ISR) { ret = pciehp_isr(irq, dev_id); enable_irq(irq); - if (ret != IRQ_WAKE_THREAD) { - pci_config_pm_runtime_put(pdev); - return ret; - } + if (ret != IRQ_WAKE_THREAD) + goto out; } synchronize_hardirq(irq); events = atomic_xchg(&ctrl->pending_events, 0); if (!events) { - pci_config_pm_runtime_put(pdev); - return IRQ_NONE; + ret = IRQ_NONE; + goto out; } /* Check Attention Button Pressed */ @@ -653,9 +689,12 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) pciehp_handle_presence_or_link_change(ctrl, events); up_read(&ctrl->reset_lock); + ret = IRQ_HANDLED; +out: pci_config_pm_runtime_put(pdev); + ctrl->ist_running = false; wake_up(&ctrl->requester); - return IRQ_HANDLED; + return ret; } static int pciehp_poll(void *data) diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c index c3899ee1db99..3e9e7b121c27 100644 --- a/drivers/pci/hotplug/rpaphp_core.c +++ b/drivers/pci/hotplug/rpaphp_core.c @@ -154,11 +154,11 @@ static enum pci_bus_speed get_max_bus_speed(struct slot *slot) return speed; } -static int get_children_props(struct device_node *dn, const int **drc_indexes, - const int **drc_names, const int **drc_types, - const int **drc_power_domains) +static int get_children_props(struct device_node *dn, const __be32 **drc_indexes, + const __be32 **drc_names, const __be32 **drc_types, + const __be32 **drc_power_domains) { - const int *indexes, *names, *types, *domains; + const __be32 *indexes, *names, *types, *domains; indexes = of_get_property(dn, "ibm,drc-indexes", NULL); names = of_get_property(dn, "ibm,drc-names", NULL); @@ -194,8 +194,8 @@ static int rpaphp_check_drc_props_v1(struct device_node *dn, char *drc_name, char *drc_type, unsigned int my_index) { char *name_tmp, *type_tmp; - const int *indexes, *names; - const int *types, *domains; + const __be32 *indexes, *names; + const __be32 *types, *domains; int i, rc; rc = get_children_props(dn->parent, &indexes, &names, &types, &domains); @@ -208,7 +208,7 @@ static int rpaphp_check_drc_props_v1(struct device_node *dn, char *drc_name, /* Iterate through parent properties, looking for my-drc-index */ for (i = 0; i < be32_to_cpu(indexes[0]); i++) { - if ((unsigned int) indexes[i + 1] == my_index) + if (be32_to_cpu(indexes[i + 1]) == my_index) break; name_tmp += (strlen(name_tmp) + 1); @@ -239,6 +239,8 @@ static int rpaphp_check_drc_props_v2(struct device_node *dn, char *drc_name, value = of_prop_next_u32(info, NULL, &entries); if (!value) return -EINVAL; + else + value++; for (j = 0; j < entries; j++) { of_read_drc_info_cell(&info, &value, &drc); @@ -246,9 +248,10 @@ static int rpaphp_check_drc_props_v2(struct device_node *dn, char *drc_name, /* Should now know end of current entry */ /* Found it */ - if (my_index <= drc.last_drc_index) { + if (my_index >= drc.drc_index_start && my_index <= drc.last_drc_index) { + int index = my_index - drc.drc_index_start; sprintf(cell_drc_name, "%s%d", drc.drc_name_prefix, - my_index); + drc.drc_name_suffix_start + index); break; } } @@ -265,7 +268,7 @@ static int rpaphp_check_drc_props_v2(struct device_node *dn, char *drc_name, int rpaphp_check_drc_props(struct device_node *dn, char *drc_name, char *drc_type) { - const unsigned int *my_index; + const __be32 *my_index; my_index = of_get_property(dn, "ibm,my-drc-index", NULL); if (!my_index) { @@ -273,12 +276,12 @@ int rpaphp_check_drc_props(struct device_node *dn, char *drc_name, return -EINVAL; } - if (firmware_has_feature(FW_FEATURE_DRC_INFO)) + if (of_find_property(dn->parent, "ibm,drc-info", NULL)) return rpaphp_check_drc_props_v2(dn, drc_name, drc_type, - *my_index); + be32_to_cpu(*my_index)); else return rpaphp_check_drc_props_v1(dn, drc_name, drc_type, - *my_index); + be32_to_cpu(*my_index)); } EXPORT_SYMBOL_GPL(rpaphp_check_drc_props); @@ -309,10 +312,11 @@ static int is_php_type(char *drc_type) * for built-in pci slots (even when the built-in slots are * dlparable.) */ -static int is_php_dn(struct device_node *dn, const int **indexes, - const int **names, const int **types, const int **power_domains) +static int is_php_dn(struct device_node *dn, const __be32 **indexes, + const __be32 **names, const __be32 **types, + const __be32 **power_domains) { - const int *drc_types; + const __be32 *drc_types; int rc; rc = get_children_props(dn, indexes, names, &drc_types, power_domains); @@ -347,7 +351,7 @@ int rpaphp_add_slot(struct device_node *dn) struct slot *slot; int retval = 0; int i; - const int *indexes, *names, *types, *power_domains; + const __be32 *indexes, *names, *types, *power_domains; char *name, *type; if (!dn->name || strcmp(dn->name, "pci")) diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 3aa115ed3a65..1f35a6b0e71a 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -189,10 +189,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id) sprintf(buf, "virtfn%u", id); rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf); if (rc) - goto failed2; + goto failed1; rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn"); if (rc) - goto failed3; + goto failed2; kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE); @@ -200,11 +200,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id) return 0; -failed3: - sysfs_remove_link(&dev->dev.kobj, buf); failed2: - pci_stop_and_remove_bus_device(virtfn); + sysfs_remove_link(&dev->dev.kobj, buf); failed1: + pci_stop_and_remove_bus_device(virtfn); pci_dev_put(dev); failed0: virtfn_remove_bus(dev->bus, bus); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index e039b740fe74..27c2fb3d42fc 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -211,7 +211,7 @@ u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) return 0; mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; - if (flag) + if (flag & PCI_MSIX_ENTRY_CTRL_MASKBIT) mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT; writel(mask_bits, pci_msix_desc_addr(desc) + PCI_MSIX_ENTRY_VECTOR_CTRL); diff --git a/drivers/pci/pci-bridge-emul.c b/drivers/pci/pci-bridge-emul.c index 702966e4fcaa..84f1865b1ab6 100644 --- a/drivers/pci/pci-bridge-emul.c +++ b/drivers/pci/pci-bridge-emul.c @@ -195,8 +195,8 @@ static const struct pci_bridge_reg_behavior pcie_cap_regs_behavior[] = { * RO, the rest is reserved */ .w1c = GENMASK(19, 16), - .ro = GENMASK(20, 19), - .rsvd = GENMASK(31, 21), + .ro = GENMASK(21, 20), + .rsvd = GENMASK(31, 22), }, [PCI_EXP_LNKCAP / 4] = { @@ -236,7 +236,7 @@ static const struct pci_bridge_reg_behavior pcie_cap_regs_behavior[] = { PCI_EXP_SLTSTA_CC | PCI_EXP_SLTSTA_DLLSC) << 16, .ro = (PCI_EXP_SLTSTA_MRLSS | PCI_EXP_SLTSTA_PDS | PCI_EXP_SLTSTA_EIS) << 16, - .rsvd = GENMASK(15, 12) | (GENMASK(15, 9) << 16), + .rsvd = GENMASK(15, 13) | (GENMASK(15, 9) << 16), }, [PCI_EXP_RTCTL / 4] = { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 9c8d619d5979..346f4ce5a318 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -900,6 +900,8 @@ static int pci_pm_resume_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct device_driver *drv = dev->driver; + pci_power_t prev_state = pci_dev->current_state; + bool skip_bus_pm = pci_dev->skip_bus_pm; int error = 0; if (dev_pm_may_skip_resume(dev)) @@ -919,16 +921,18 @@ static int pci_pm_resume_noirq(struct device *dev) * configuration here and attempting to put them into D0 again is * pointless, so avoid doing that. */ - if (!(pci_dev->skip_bus_pm && pm_suspend_no_platform())) + if (!(skip_bus_pm && pm_suspend_no_platform())) pci_pm_default_resume_early(pci_dev); pci_fixup_device(pci_fixup_resume_early, pci_dev); + pcie_pme_root_status_cleanup(pci_dev); + + if (!skip_bus_pm && prev_state == PCI_D3cold) + pci_bridge_wait_for_secondary_bus(pci_dev); if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); - pcie_pme_root_status_cleanup(pci_dev); - if (drv && drv->pm && drv->pm->resume_noirq) error = drv->pm->resume_noirq(dev); @@ -1079,17 +1083,22 @@ static int pci_pm_thaw_noirq(struct device *dev) return error; } - if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); - /* - * pci_restore_state() requires the device to be in D0 (because of MSI - * restoration among other things), so force it into D0 in case the - * driver's "freeze" callbacks put it into a low-power state directly. + * Both the legacy ->resume_early() and the new pm->thaw_noirq() + * callbacks assume the device has been returned to D0 and its + * config state has been restored. + * + * In addition, pci_restore_state() restores MSI-X state in MMIO + * space, which requires the device to be in D0, so return it to D0 + * in case the driver's "freeze" callbacks put it into a low-power + * state. */ pci_set_power_state(pci_dev, PCI_D0); pci_restore_state(pci_dev); + if (pci_has_legacy_pm_support(pci_dev)) + return pci_legacy_resume_early(dev); + if (drv && drv->pm && drv->pm->thaw_noirq) error = drv->pm->thaw_noirq(dev); @@ -1334,6 +1343,7 @@ static int pci_pm_runtime_resume(struct device *dev) int rc = 0; struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + pci_power_t prev_state = pci_dev->current_state; /* * Restoring config space is necessary even if the device is not bound @@ -1349,6 +1359,9 @@ static int pci_pm_runtime_resume(struct device *dev) pci_enable_wake(pci_dev, PCI_D0, false); pci_fixup_device(pci_fixup_resume, pci_dev); + if (prev_state == PCI_D3cold) + pci_bridge_wait_for_secondary_bus(pci_dev); + if (pm && pm->runtime_resume) rc = pm->runtime_resume(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 42922dae29be..4edfa4f5f65e 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -796,7 +796,9 @@ static inline bool platform_pci_need_resume(struct pci_dev *dev) static inline bool platform_pci_bridge_d3(struct pci_dev *dev) { - return pci_platform_pm ? pci_platform_pm->bridge_d3(dev) : false; + if (pci_platform_pm && pci_platform_pm->bridge_d3) + return pci_platform_pm->bridge_d3(dev); + return false; } /** @@ -991,15 +993,11 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state) if (state == PCI_D0) { pci_platform_power_transition(dev, PCI_D0); /* - * Mandatory power management transition delays, see - * PCI Express Base Specification Revision 2.0 Section - * 6.6.1: Conventional Reset. Do not delay for - * devices powered on/off by corresponding bridge, - * because have already delayed for the bridge. + * Mandatory power management transition delays are handled in + * pci_pm_resume_noirq() and pci_pm_runtime_resume() of the + * corresponding bridge. */ if (dev->runtime_d3cold) { - if (dev->d3cold_delay && !dev->imm_ready) - msleep(dev->d3cold_delay); /* * When powering on a bridge from D3cold, the * whole hierarchy may be powered on into @@ -4573,14 +4571,17 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS); } + /** - * pcie_wait_for_link - Wait until link is active or inactive + * pcie_wait_for_link_delay - Wait until link is active or inactive * @pdev: Bridge device * @active: waiting for active or inactive? + * @delay: Delay to wait after link has become active (in ms) * * Use this to wait till link becomes active or inactive. */ -bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, + int delay) { int timeout = 1000; bool ret; @@ -4588,10 +4589,10 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active) /* * Some controllers might not implement link active reporting. In this - * case, we wait for 1000 + 100 ms. + * case, we wait for 1000 ms + any delay requested by the caller. */ if (!pdev->link_active_reporting) { - msleep(1100); + msleep(timeout + delay); return true; } @@ -4617,13 +4618,144 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active) timeout -= 10; } if (active && ret) - msleep(100); + msleep(delay); else if (ret != active) pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", active ? "set" : "cleared"); return ret == active; } +/** + * pcie_wait_for_link - Wait until link is active or inactive + * @pdev: Bridge device + * @active: waiting for active or inactive? + * + * Use this to wait till link becomes active or inactive. + */ +bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +{ + return pcie_wait_for_link_delay(pdev, active, 100); +} + +/* + * Find maximum D3cold delay required by all the devices on the bus. The + * spec says 100 ms, but firmware can lower it and we allow drivers to + * increase it as well. + * + * Called with @pci_bus_sem locked for reading. + */ +static int pci_bus_max_d3cold_delay(const struct pci_bus *bus) +{ + const struct pci_dev *pdev; + int min_delay = 100; + int max_delay = 0; + + list_for_each_entry(pdev, &bus->devices, bus_list) { + if (pdev->d3cold_delay < min_delay) + min_delay = pdev->d3cold_delay; + if (pdev->d3cold_delay > max_delay) + max_delay = pdev->d3cold_delay; + } + + return max(min_delay, max_delay); +} + +/** + * pci_bridge_wait_for_secondary_bus - Wait for secondary bus to be accessible + * @dev: PCI bridge + * + * Handle necessary delays before access to the devices on the secondary + * side of the bridge are permitted after D3cold to D0 transition. + * + * For PCIe this means the delays in PCIe 5.0 section 6.6.1. For + * conventional PCI it means Tpvrh + Trhfa specified in PCI 3.0 section + * 4.3.2. + */ +void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) +{ + struct pci_dev *child; + int delay; + + if (pci_dev_is_disconnected(dev)) + return; + + if (!pci_is_bridge(dev) || !dev->bridge_d3) + return; + + down_read(&pci_bus_sem); + + /* + * We only deal with devices that are present currently on the bus. + * For any hot-added devices the access delay is handled in pciehp + * board_added(). In case of ACPI hotplug the firmware is expected + * to configure the devices before OS is notified. + */ + if (!dev->subordinate || list_empty(&dev->subordinate->devices)) { + up_read(&pci_bus_sem); + return; + } + + /* Take d3cold_delay requirements into account */ + delay = pci_bus_max_d3cold_delay(dev->subordinate); + if (!delay) { + up_read(&pci_bus_sem); + return; + } + + child = list_first_entry(&dev->subordinate->devices, struct pci_dev, + bus_list); + up_read(&pci_bus_sem); + + /* + * Conventional PCI and PCI-X we need to wait Tpvrh + Trhfa before + * accessing the device after reset (that is 1000 ms + 100 ms). In + * practice this should not be needed because we don't do power + * management for them (see pci_bridge_d3_possible()). + */ + if (!pci_is_pcie(dev)) { + pci_dbg(dev, "waiting %d ms for secondary bus\n", 1000 + delay); + msleep(1000 + delay); + return; + } + + /* + * For PCIe downstream and root ports that do not support speeds + * greater than 5 GT/s need to wait minimum 100 ms. For higher + * speeds (gen3) we need to wait first for the data link layer to + * become active. + * + * However, 100 ms is the minimum and the PCIe spec says the + * software must allow at least 1s before it can determine that the + * device that did not respond is a broken device. There is + * evidence that 100 ms is not always enough, for example certain + * Titan Ridge xHCI controller does not always respond to + * configuration requests if we only wait for 100 ms (see + * https://bugzilla.kernel.org/show_bug.cgi?id=203885). + * + * Therefore we wait for 100 ms and check for the device presence. + * If it is still not present give it an additional 100 ms. + */ + if (!pcie_downstream_port(dev)) + return; + + if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) { + pci_dbg(dev, "waiting %d ms for downstream link\n", delay); + msleep(delay); + } else { + pci_dbg(dev, "waiting %d ms for downstream link, after activation\n", + delay); + if (!pcie_wait_for_link_delay(dev, true, delay)) { + /* Did not train, no need to wait any further */ + return; + } + } + + if (!pci_device_is_present(child)) { + pci_dbg(child, "waiting additional %d ms to become accessible\n", delay); + msleep(delay); + } +} + void pci_reset_secondary_bus(struct pci_dev *dev) { u16 ctrl; @@ -5820,10 +5952,29 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode, return 0; } +#ifdef CONFIG_ACPI +bool pci_pr3_present(struct pci_dev *pdev) +{ + struct acpi_device *adev; + + if (acpi_disabled) + return false; + + adev = ACPI_COMPANION(&pdev->dev); + if (!adev) + return false; + + return adev->power.flags.power_resources && + acpi_has_method(adev->handle, "_PR3"); +} +EXPORT_SYMBOL_GPL(pci_pr3_present); +#endif + /** * pci_add_dma_alias - Add a DMA devfn alias for a device * @dev: the PCI device for which alias is added - * @devfn: alias slot and function + * @devfn_from: alias slot and function + * @nr_devfns: number of subsequent devfns to alias * * This helper encodes an 8-bit devfn as a bit number in dma_alias_mask * which is used to program permissible bus-devfn source addresses for DMA @@ -5839,18 +5990,29 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode, * cannot be left as a userspace activity). DMA aliases should therefore * be configured via quirks, such as the PCI fixup header quirk. */ -void pci_add_dma_alias(struct pci_dev *dev, u8 devfn) +void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns) { + int devfn_to; + + nr_devfns = min(nr_devfns, (unsigned) MAX_NR_DEVFNS - devfn_from); + devfn_to = devfn_from + nr_devfns - 1; + if (!dev->dma_alias_mask) - dev->dma_alias_mask = bitmap_zalloc(U8_MAX, GFP_KERNEL); + dev->dma_alias_mask = bitmap_zalloc(MAX_NR_DEVFNS, GFP_KERNEL); if (!dev->dma_alias_mask) { pci_warn(dev, "Unable to allocate DMA alias mask\n"); return; } - set_bit(devfn, dev->dma_alias_mask); - pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n", - PCI_SLOT(devfn), PCI_FUNC(devfn)); + bitmap_set(dev->dma_alias_mask, devfn_from, nr_devfns); + + if (nr_devfns == 1) + pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n", + PCI_SLOT(devfn_from), PCI_FUNC(devfn_from)); + else if (nr_devfns > 1) + pci_info(dev, "Enabling fixed DMA alias for devfn range from %02x.%d to %02x.%d\n", + PCI_SLOT(devfn_from), PCI_FUNC(devfn_from), + PCI_SLOT(devfn_to), PCI_FUNC(devfn_to)); } bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2) diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9cb99380c61e..8e858d0a24ba 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -4,6 +4,9 @@ #include <linux/pci.h> +/* Number of possible devfns: 0.0 to 1f.7 inclusive */ +#define MAX_NR_DEVFNS 256 + #define PCI_FIND_CAP_TTL 48 #define PCI_VSEC_ID_INTEL_TBT 0x1234 /* Thunderbolt */ @@ -92,6 +95,7 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev); void pci_free_cap_save_buffers(struct pci_dev *dev); bool pci_bridge_d3_possible(struct pci_dev *dev); void pci_bridge_d3_update(struct pci_dev *dev); +void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev); static inline void pci_wakeup_event(struct pci_dev *dev) { @@ -113,6 +117,15 @@ static inline bool pci_power_manageable(struct pci_dev *pci_dev) return !pci_has_subordinate(pci_dev) || pci_dev->bridge_d3; } +static inline bool pcie_downstream_port(const struct pci_dev *dev) +{ + int type = pci_pcie_type(dev); + + return type == PCI_EXP_TYPE_ROOT_PORT || + type == PCI_EXP_TYPE_DOWNSTREAM || + type == PCI_EXP_TYPE_PCIE_BRIDGE; +} + int pci_vpd_init(struct pci_dev *dev); void pci_vpd_release(struct pci_dev *dev); void pcie_vpd_create_sysfs_dev_files(struct pci_dev *dev); diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index b45bc47d04fe..271aecfbc3bf 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -1387,6 +1387,7 @@ static int aer_probe(struct pcie_device *dev) return -ENOMEM; rpc->rpd = port; + INIT_KFIFO(rpc->aer_fifo); set_service_data(dev, rpc); status = devm_request_threaded_irq(device, dev->irq, aer_irq, aer_isr, diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index fd4cb75088f9..676863722695 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -65,6 +65,7 @@ struct pcie_link_state { u32 clkpm_capable:1; /* Clock PM capable? */ u32 clkpm_enabled:1; /* Current Clock PM state */ u32 clkpm_default:1; /* Default Clock PM state by BIOS */ + u32 clkpm_disable:1; /* Clock PM disabled */ /* Exit latencies */ struct aspm_latency latency_up; /* Upstream direction exit latency */ @@ -162,8 +163,11 @@ static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable) static void pcie_set_clkpm(struct pcie_link_state *link, int enable) { - /* Don't enable Clock PM if the link is not Clock PM capable */ - if (!link->clkpm_capable) + /* + * Don't enable Clock PM if the link is not Clock PM capable + * or Clock PM is disabled + */ + if (!link->clkpm_capable || link->clkpm_disable) enable = 0; /* Need nothing if the specified equals to current state */ if (link->clkpm_enabled == enable) @@ -193,7 +197,8 @@ static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist) } link->clkpm_enabled = enabled; link->clkpm_default = enabled; - link->clkpm_capable = (blacklist) ? 0 : capable; + link->clkpm_capable = capable; + link->clkpm_disable = blacklist ? 1 : 0; } static bool pcie_retrain_link(struct pcie_link_state *link) @@ -624,16 +629,6 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) /* Setup initial capable state. Will be updated later */ link->aspm_capable = link->aspm_support; - /* - * If the downstream component has pci bridge function, don't - * do ASPM for now. - */ - list_for_each_entry(child, &linkbus->devices, bus_list) { - if (pci_pcie_type(child) == PCI_EXP_TYPE_PCI_BRIDGE) { - link->aspm_disable = ASPM_STATE_ALL; - break; - } - } /* Get and check endpoint acceptable latencies */ list_for_each_entry(child, &linkbus->devices, bus_list) { @@ -743,9 +738,9 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) /* Enable what we need to enable */ pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1, - PCI_L1SS_CAP_L1_PM_SS, val); + PCI_L1SS_CTL1_L1SS_MASK, val); pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1, - PCI_L1SS_CAP_L1_PM_SS, val); + PCI_L1SS_CTL1_L1SS_MASK, val); } static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val) @@ -1098,10 +1093,9 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) link->aspm_disable |= ASPM_STATE_L1; pcie_config_aspm_link(link, policy_to_aspm_state(link)); - if (state & PCIE_LINK_STATE_CLKPM) { - link->clkpm_capable = 0; - pcie_set_clkpm(link, 0); - } + if (state & PCIE_LINK_STATE_CLKPM) + link->clkpm_disable = 1; + pcie_set_clkpm(link, policy_to_clkpm_state(link)); mutex_unlock(&aspm_lock); if (sem) up_read(&pci_bus_sem); @@ -1162,6 +1156,7 @@ static int pcie_aspm_get_policy(char *buffer, const struct kernel_param *kp) cnt += sprintf(buffer + cnt, "[%s] ", policy_str[i]); else cnt += sprintf(buffer + cnt, "%s ", policy_str[i]); + cnt += sprintf(buffer + cnt, "\n"); return cnt; } diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 98cfa30f3fae..357a454cafa0 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -21,7 +21,7 @@ static void pci_ptm_info(struct pci_dev *dev) snprintf(clock_desc, sizeof(clock_desc), ">254ns"); break; default: - snprintf(clock_desc, sizeof(clock_desc), "%udns", + snprintf(clock_desc, sizeof(clock_desc), "%uns", dev->ptm_granularity); break; } @@ -39,10 +39,6 @@ void pci_ptm_init(struct pci_dev *dev) if (!pci_is_pcie(dev)) return; - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM); - if (!pos) - return; - /* * Enable PTM only on interior devices (root ports, switch ports, * etc.) on the assumption that it causes no link traffic until an @@ -52,6 +48,23 @@ void pci_ptm_init(struct pci_dev *dev) pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END)) return; + /* + * Switch Downstream Ports are not permitted to have a PTM + * capability; their PTM behavior is controlled by the Upstream + * Port (PCIe r5.0, sec 7.9.16). + */ + ups = pci_upstream_bridge(dev); + if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM && + ups && ups->ptm_enabled) { + dev->ptm_granularity = ups->ptm_granularity; + dev->ptm_enabled = 1; + return; + } + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM); + if (!pos) + return; + pci_read_config_dword(dev, pos + PCI_PTM_CAP, &cap); local_clock = (cap & PCI_PTM_GRANULARITY_MASK) >> 8; @@ -61,7 +74,6 @@ void pci_ptm_init(struct pci_dev *dev) * the spec recommendation (PCIe r3.1, sec 7.32.3), select the * furthest upstream Time Source as the PTM Root. */ - ups = pci_upstream_bridge(dev); if (ups && ups->ptm_enabled) { ctrl = PCI_PTM_CTRL_ENABLE; if (ups->ptm_granularity == 0) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 0e8e2c186f50..37770fe6948e 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -577,6 +577,7 @@ static void devm_pci_release_host_bridge_dev(struct device *dev) bridge->release_fn(bridge); pci_free_resource_list(&bridge->windows); + pci_free_resource_list(&bridge->dma_ranges); } static void pci_release_host_bridge_dev(struct device *dev) @@ -871,9 +872,10 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) goto free; err = device_register(&bridge->dev); - if (err) + if (err) { put_device(&bridge->dev); - + goto free; + } bus->bridge = get_device(&bridge->dev); device_enable_async_suspend(bus->bridge); pci_set_bus_of_node(bus); @@ -1094,14 +1096,15 @@ static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, * @sec: updated with secondary bus number from EA * @sub: updated with subordinate bus number from EA * - * If @dev is a bridge with EA capability, update @sec and @sub with - * fixed bus numbers from the capability and return true. Otherwise, - * return false. + * If @dev is a bridge with EA capability that specifies valid secondary + * and subordinate bus numbers, return true with the bus numbers in @sec + * and @sub. Otherwise return false. */ static bool pci_ea_fixed_busnrs(struct pci_dev *dev, u8 *sec, u8 *sub) { int ea, offset; u32 dw; + u8 ea_sec, ea_sub; if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) return false; @@ -1113,8 +1116,13 @@ static bool pci_ea_fixed_busnrs(struct pci_dev *dev, u8 *sec, u8 *sub) offset = ea + PCI_EA_FIRST_ENT; pci_read_config_dword(dev, offset, &dw); - *sec = dw & PCI_EA_SEC_BUS_MASK; - *sub = (dw & PCI_EA_SUB_BUS_MASK) >> PCI_EA_SUB_BUS_SHIFT; + ea_sec = dw & PCI_EA_SEC_BUS_MASK; + ea_sub = (dw & PCI_EA_SUB_BUS_MASK) >> PCI_EA_SUB_BUS_SHIFT; + if (ea_sec == 0 || ea_sub < ea_sec) + return false; + + *sec = ea_sec; + *sub = ea_sub; return true; } @@ -1765,7 +1773,7 @@ int pci_setup_device(struct pci_dev *dev) /* Device class may be changed after fixup */ class = dev->class >> 8; - if (dev->non_compliant_bars) { + if (dev->non_compliant_bars && !dev->mmio_always_on) { pci_read_config_word(dev, PCI_COMMAND, &cmd); if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { pci_info(dev, "device has non-compliant BARs; disabling IO/MEM decoding\n"); @@ -1877,13 +1885,33 @@ static void pci_configure_mps(struct pci_dev *dev) struct pci_dev *bridge = pci_upstream_bridge(dev); int mps, mpss, p_mps, rc; - if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge)) + if (!pci_is_pcie(dev)) return; /* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */ if (dev->is_virtfn) return; + /* + * For Root Complex Integrated Endpoints, program the maximum + * supported value unless limited by the PCIE_BUS_PEER2PEER case. + */ + if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) { + if (pcie_bus_config == PCIE_BUS_PEER2PEER) + mps = 128; + else + mps = 128 << dev->pcie_mpss; + rc = pcie_set_mps(dev, mps); + if (rc) { + pci_warn(dev, "can't set Max Payload Size to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n", + mps); + } + return; + } + + if (!bridge || !pci_is_pcie(bridge)) + return; + mps = pcie_get_mps(dev); p_mps = pcie_get_mps(bridge); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 0f16acc323c6..0e23f47ef36d 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1872,19 +1872,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2609, quirk_intel_pcie_pm); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x260a, quirk_intel_pcie_pm); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x260b, quirk_intel_pcie_pm); +static void quirk_d3hot_delay(struct pci_dev *dev, unsigned int delay) +{ + if (dev->d3_delay >= delay) + return; + + dev->d3_delay = delay; + pci_info(dev, "extending delay after power-on from D3hot to %d msec\n", + dev->d3_delay); +} + static void quirk_radeon_pm(struct pci_dev *dev) { if (dev->subsystem_vendor == PCI_VENDOR_ID_APPLE && - dev->subsystem_device == 0x00e2) { - if (dev->d3_delay < 20) { - dev->d3_delay = 20; - pci_info(dev, "extending delay after power-on from D3 to %d msec\n", - dev->d3_delay); - } - } + dev->subsystem_device == 0x00e2) + quirk_d3hot_delay(dev, 20); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6741, quirk_radeon_pm); +/* + * Ryzen5/7 XHCI controllers fail upon resume from runtime suspend or s2idle. + * https://bugzilla.kernel.org/show_bug.cgi?id=205587 + * + * The kernel attempts to transition these devices to D3cold, but that seems + * to be ineffective on the platforms in question; the PCI device appears to + * remain on in D3hot state. The D3hot-to-D0 transition then requires an + * extended delay in order to succeed. + */ +static void quirk_ryzen_xhci_d3hot(struct pci_dev *dev) +{ + quirk_d3hot_delay(dev, 20); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15e0, quirk_ryzen_xhci_d3hot); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15e1, quirk_ryzen_xhci_d3hot); + #ifdef CONFIG_X86_IO_APIC static int dmi_disable_ioapicreroute(const struct dmi_system_id *d) { @@ -1950,26 +1971,92 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_80332_1, quirk /* * IO-APIC1 on 6300ESB generates boot interrupts, see Intel order no * 300641-004US, section 5.7.3. + * + * Core IO on Xeon E5 1600/2600/4600, see Intel order no 326509-003. + * Core IO on Xeon E5 v2, see Intel order no 329188-003. + * Core IO on Xeon E7 v2, see Intel order no 329595-002. + * Core IO on Xeon E5 v3, see Intel order no 330784-003. + * Core IO on Xeon E7 v3, see Intel order no 332315-001US. + * Core IO on Xeon E5 v4, see Intel order no 333810-002US. + * Core IO on Xeon E7 v4, see Intel order no 332315-001US. + * Core IO on Xeon D-1500, see Intel order no 332051-001. + * Core IO on Xeon Scalable, see Intel order no 610950. */ -#define INTEL_6300_IOAPIC_ABAR 0x40 +#define INTEL_6300_IOAPIC_ABAR 0x40 /* Bus 0, Dev 29, Func 5 */ #define INTEL_6300_DISABLE_BOOT_IRQ (1<<14) +#define INTEL_CIPINTRC_CFG_OFFSET 0x14C /* Bus 0, Dev 5, Func 0 */ +#define INTEL_CIPINTRC_DIS_INTX_ICH (1<<25) + static void quirk_disable_intel_boot_interrupt(struct pci_dev *dev) { u16 pci_config_word; + u32 pci_config_dword; if (noioapicquirk) return; - pci_read_config_word(dev, INTEL_6300_IOAPIC_ABAR, &pci_config_word); - pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ; - pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR, pci_config_word); - + switch (dev->device) { + case PCI_DEVICE_ID_INTEL_ESB_10: + pci_read_config_word(dev, INTEL_6300_IOAPIC_ABAR, + &pci_config_word); + pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ; + pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR, + pci_config_word); + break; + case 0x3c28: /* Xeon E5 1600/2600/4600 */ + case 0x0e28: /* Xeon E5/E7 V2 */ + case 0x2f28: /* Xeon E5/E7 V3,V4 */ + case 0x6f28: /* Xeon D-1500 */ + case 0x2034: /* Xeon Scalable Family */ + pci_read_config_dword(dev, INTEL_CIPINTRC_CFG_OFFSET, + &pci_config_dword); + pci_config_dword |= INTEL_CIPINTRC_DIS_INTX_ICH; + pci_write_config_dword(dev, INTEL_CIPINTRC_CFG_OFFSET, + pci_config_dword); + break; + default: + return; + } pci_info(dev, "disabled boot interrupts on device [%04x:%04x]\n", dev->vendor, dev->device); } -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt); -DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt); +/* + * Device 29 Func 5 Device IDs of IO-APIC + * containing ABAR—APIC1 Alternate Base Address Register + */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, + quirk_disable_intel_boot_interrupt); + +/* + * Device 5 Func 0 Device IDs of Core IO modules/hubs + * containing Coherent Interface Protocol Interrupt Control + * + * Device IDs obtained from volume 2 datasheets of commented + * families above. + */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x3c28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0e28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2f28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x6f28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2034, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x3c28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x0e28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x2f28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x6f28, + quirk_disable_intel_boot_interrupt); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x2034, + quirk_disable_intel_boot_interrupt); /* Disable boot interrupts on HT-1000 */ #define BC_HT1000_FEATURE_REG 0x64 @@ -2244,6 +2331,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); +static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) +{ + pci_info(dev, "Disabling ASPM L0s/L1\n"); + pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); +} + +/* + * ASM1083/1085 PCIe-PCI bridge devices cause AER timeout errors on the + * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected; + * disable both L0s and L1 for now to be safe. + */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); + /* * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain * Link bit cleared after starting the link retrain process to allow this @@ -2382,32 +2482,6 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5719, quirk_brcm_5719_limit_mrrs); -#ifdef CONFIG_PCIE_IPROC_PLATFORM -static void quirk_paxc_bridge(struct pci_dev *pdev) -{ - /* - * The PCI config space is shared with the PAXC root port and the first - * Ethernet device. So, we need to workaround this by telling the PCI - * code that the bridge is not an Ethernet device. - */ - if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) - pdev->class = PCI_CLASS_BRIDGE_PCI << 8; - - /* - * MPSS is not being set properly (as it is currently 0). This is - * because that area of the PCI config space is hard coded to zero, and - * is not modifiable by firmware. Set this to 2 (e.g., 512 byte MPS) - * so that the MPS can be set to the real max value. - */ - pdev->pcie_mpss = 2; -} -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge); -#endif - /* * Originally in EDAC sources for i82875P: Intel tells BIOS developers to * hide device 6 which configures the overflow device access containing the @@ -3862,7 +3936,7 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe) static void quirk_dma_func0_alias(struct pci_dev *dev) { if (PCI_FUNC(dev->devfn) != 0) - pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0)); + pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0), 1); } /* @@ -3876,7 +3950,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe476, quirk_dma_func0_alias); static void quirk_dma_func1_alias(struct pci_dev *dev) { if (PCI_FUNC(dev->devfn) != 1) - pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1)); + pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1), 1); } /* @@ -3961,7 +4035,7 @@ static void quirk_fixed_dma_alias(struct pci_dev *dev) id = pci_match_id(fixed_dma_alias_tbl, dev); if (id) - pci_add_dma_alias(dev, id->driver_data); + pci_add_dma_alias(dev, id->driver_data, 1); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ADAPTEC2, 0x0285, quirk_fixed_dma_alias); @@ -4003,14 +4077,43 @@ DECLARE_PCI_FIXUP_HEADER(0x8086, 0x244e, quirk_use_pcie_bridge_dma_alias); */ static void quirk_mic_x200_dma_alias(struct pci_dev *pdev) { - pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0)); - pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0)); - pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3)); + pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0), 1); + pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0), 1); + pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3), 1); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2260, quirk_mic_x200_dma_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2264, quirk_mic_x200_dma_alias); /* + * Intel Visual Compute Accelerator (VCA) is a family of PCIe add-in devices + * exposing computational units via Non Transparent Bridges (NTB, PEX 87xx). + * + * Similarly to MIC x200, we need to add DMA aliases to allow buffer access + * when IOMMU is enabled. These aliases allow computational unit access to + * host memory. These aliases mark the whole VCA device as one IOMMU + * group. + * + * All possible slot numbers (0x20) are used, since we are unable to tell + * what slot is used on other side. This quirk is intended for both host + * and computational unit sides. The VCA devices have up to five functions + * (four for DMA channels and one additional). + */ +static void quirk_pex_vca_alias(struct pci_dev *pdev) +{ + const unsigned int num_pci_slots = 0x20; + unsigned int slot; + + for (slot = 0; slot < num_pci_slots; slot++) + pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x0), 5); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2954, quirk_pex_vca_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2955, quirk_pex_vca_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2956, quirk_pex_vca_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2958, quirk_pex_vca_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2959, quirk_pex_vca_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x295A, quirk_pex_vca_alias); + +/* * The IOMMU and interrupt controller on Broadcom Vulcan/Cavium ThunderX2 are * associated not at the root bus, but at a bridge below. This quirk avoids * generating invalid DMA aliases. @@ -4193,6 +4296,24 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, quirk_chelsio_T5_disable_root_port_attributes); /* + * pci_acs_ctrl_enabled - compare desired ACS controls with those provided + * by a device + * @acs_ctrl_req: Bitmask of desired ACS controls + * @acs_ctrl_ena: Bitmask of ACS controls enabled or provided implicitly by + * the hardware design + * + * Return 1 if all ACS controls in the @acs_ctrl_req bitmask are included + * in @acs_ctrl_ena, i.e., the device provides all the access controls the + * caller desires. Return 0 otherwise. + */ +static int pci_acs_ctrl_enabled(u16 acs_ctrl_req, u16 acs_ctrl_ena) +{ + if ((acs_ctrl_req & acs_ctrl_ena) == acs_ctrl_req) + return 1; + return 0; +} + +/* * AMD has indicated that the devices below do not support peer-to-peer * in any system where they are found in the southbridge with an AMD * IOMMU in the system. Multifunction devices that do not support @@ -4232,10 +4353,12 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags) if (ACPI_FAILURE(status)) return -ENODEV; + acpi_put_table(header); + /* Filter out flags not applicable to multifunction */ acs_flags &= (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC | PCI_ACS_DT); - return acs_flags & ~(PCI_ACS_RR | PCI_ACS_CR) ? 0 : 1; + return pci_acs_ctrl_enabled(acs_flags, PCI_ACS_RR | PCI_ACS_CR); #else return -ENODEV; #endif @@ -4243,33 +4366,27 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags) static bool pci_quirk_cavium_acs_match(struct pci_dev *dev) { - /* - * Effectively selects all downstream ports for whole ThunderX 1 - * family by 0xf800 mask (which represents 8 SoCs), while the lower - * bits of device ID are used to indicate which subdevice is used - * within the SoC. - */ - return (pci_is_pcie(dev) && - (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) && - ((dev->device & 0xf800) == 0xa000)); + if (!pci_is_pcie(dev) || pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) + return false; + + return (pci_is_pcie(dev) && ((dev->device & 0xf800) == 0xa000)); } static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags) { + if (!pci_quirk_cavium_acs_match(dev)) + return -ENOTTY; + /* - * Cavium root ports don't advertise an ACS capability. However, + * Cavium Root Ports don't advertise an ACS capability. However, * the RTL internally implements similar protection as if ACS had - * Request Redirection, Completion Redirection, Source Validation, + * Source Validation, Request Redirection, Completion Redirection, * and Upstream Forwarding features enabled. Assert that the * hardware implements and enables equivalent ACS functionality for * these flags. */ - acs_flags &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_SV | PCI_ACS_UF); - - if (!pci_quirk_cavium_acs_match(dev)) - return -ENOTTY; - - return acs_flags ? 0 : 1; + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags) @@ -4279,13 +4396,35 @@ static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags) * transactions with others, allowing masking out these bits as if they * were unimplemented in the ACS capability. */ - acs_flags &= ~(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); +} + +/* + * Many Zhaoxin Root Ports and Switch Downstream Ports have no ACS capability. + * But the implementation could block peer-to-peer transactions between them + * and provide ACS-like functionality. + */ +static int pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags) +{ + if (!pci_is_pcie(dev) || + ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) && + (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM))) + return -ENOTTY; - return acs_flags ? 0 : 1; + switch (dev->device) { + case 0x0710 ... 0x071e: + case 0x0721: + case 0x0723 ... 0x0732: + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); + } + + return false; } /* - * Many Intel PCH root ports do provide ACS-like features to disable peer + * Many Intel PCH Root Ports do provide ACS-like features to disable peer * transactions and validate bus numbers in requests, but do not provide an * actual PCIe ACS capability. This is the list of device IDs known to fall * into that category as provided by Intel in Red Hat bugzilla 1037684. @@ -4333,37 +4472,32 @@ static bool pci_quirk_intel_pch_acs_match(struct pci_dev *dev) return false; } -#define INTEL_PCH_ACS_FLAGS (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_SV) - static int pci_quirk_intel_pch_acs(struct pci_dev *dev, u16 acs_flags) { - u16 flags = dev->dev_flags & PCI_DEV_FLAGS_ACS_ENABLED_QUIRK ? - INTEL_PCH_ACS_FLAGS : 0; - if (!pci_quirk_intel_pch_acs_match(dev)) return -ENOTTY; - return acs_flags & ~flags ? 0 : 1; + if (dev->dev_flags & PCI_DEV_FLAGS_ACS_ENABLED_QUIRK) + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); + + return pci_acs_ctrl_enabled(acs_flags, 0); } /* - * These QCOM root ports do provide ACS-like features to disable peer + * These QCOM Root Ports do provide ACS-like features to disable peer * transactions and validate bus numbers in requests, but do not provide an * actual PCIe ACS capability. Hardware supports source validation but it * will report the issue as Completer Abort instead of ACS Violation. - * Hardware doesn't support peer-to-peer and each root port is a root - * complex with unique segment numbers. It is not possible for one root - * port to pass traffic to another root port. All PCIe transactions are - * terminated inside the root port. + * Hardware doesn't support peer-to-peer and each Root Port is a Root + * Complex with unique segment numbers. It is not possible for one Root + * Port to pass traffic to another Root Port. All PCIe transactions are + * terminated inside the Root Port. */ static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags) { - u16 flags = (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_SV); - int ret = acs_flags & ~flags ? 0 : 1; - - pci_info(dev, "Using QCOM ACS Quirk (%d)\n", ret); - - return ret; + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } /* @@ -4446,7 +4580,7 @@ static int pci_quirk_intel_spt_pch_acs(struct pci_dev *dev, u16 acs_flags) pci_read_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, &ctrl); - return acs_flags & ~ctrl ? 0 : 1; + return pci_acs_ctrl_enabled(acs_flags, ctrl); } static int pci_quirk_mf_endpoint_acs(struct pci_dev *dev, u16 acs_flags) @@ -4460,10 +4594,35 @@ static int pci_quirk_mf_endpoint_acs(struct pci_dev *dev, u16 acs_flags) * perform peer-to-peer with other functions, allowing us to mask out * these bits as if they were unimplemented in the ACS capability. */ - acs_flags &= ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR | - PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT); + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR | + PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT); +} + +static int pci_quirk_rciep_acs(struct pci_dev *dev, u16 acs_flags) +{ + /* + * Intel RCiEP's are required to allow p2p only on translated + * addresses. Refer to Intel VT-d specification, r3.1, sec 3.16, + * "Root-Complex Peer to Peer Considerations". + */ + if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_END) + return -ENOTTY; + + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); +} - return acs_flags ? 0 : 1; +static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags) +{ + /* + * iProc PAXB 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); } static const struct pci_dev_acs_enabled { @@ -4536,6 +4695,7 @@ static const struct pci_dev_acs_enabled { /* I219 */ { PCI_VENDOR_ID_INTEL, 0x15b7, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_INTEL, 0x15b8, pci_quirk_mf_endpoint_acs }, + { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_rciep_acs }, /* QCOM QDF2xxx root ports */ { PCI_VENDOR_ID_QCOM, 0x0400, pci_quirk_qcom_rp_acs }, { PCI_VENDOR_ID_QCOM, 0x0401, pci_quirk_qcom_rp_acs }, @@ -4559,9 +4719,27 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs }, { PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs }, + { PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs }, + /* Zhaoxin multi-function devices */ + { PCI_VENDOR_ID_ZHAOXIN, 0x3038, pci_quirk_mf_endpoint_acs }, + { PCI_VENDOR_ID_ZHAOXIN, 0x3104, pci_quirk_mf_endpoint_acs }, + { PCI_VENDOR_ID_ZHAOXIN, 0x9083, pci_quirk_mf_endpoint_acs }, + /* Zhaoxin Root/Downstream Ports */ + { PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs }, { 0 } }; +/* + * pci_dev_specific_acs_enabled - check whether device provides ACS controls + * @dev: PCI device + * @acs_flags: Bitmask of desired ACS controls + * + * Returns: + * -ENOTTY: No quirk applies to this device; we can't tell whether the + * device provides the desired controls + * 0: Device does not provide all the desired controls + * >0: Device provides all the controls in @acs_flags + */ int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags) { const struct pci_dev_acs_enabled *i; @@ -4602,7 +4780,7 @@ int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags) #define INTEL_BSPR_REG_BPPD (1 << 9) /* Upstream Peer Decode Configuration Register */ -#define INTEL_UPDCR_REG 0x1114 +#define INTEL_UPDCR_REG 0x1014 /* 5:0 Peer Decode Enable bits */ #define INTEL_UPDCR_REG_MASK 0x3f @@ -4881,13 +5059,25 @@ static void quirk_intel_qat_vf_cap(struct pci_dev *pdev) } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443, quirk_intel_qat_vf_cap); -/* FLR may cause some 82579 devices to hang */ -static void quirk_intel_no_flr(struct pci_dev *dev) +/* + * FLR may cause the following to devices to hang: + * + * AMD Starship/Matisse HD Audio Controller 0x1487 + * AMD Starship USB 3.0 Host Controller 0x148c + * AMD Matisse USB 3.0 Host Controller 0x149c + * Intel 82579LM Gigabit Ethernet Controller 0x1502 + * Intel 82579V Gigabit Ethernet Controller 0x1503 + * + */ +static void quirk_no_flr(struct pci_dev *dev) { dev->dev_flags |= PCI_DEV_FLAGS_NO_FLR_RESET; } -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_intel_no_flr); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_intel_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1487, quirk_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x148c, quirk_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x149c, quirk_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr); static void quirk_no_ext_tags(struct pci_dev *pdev) { @@ -4911,18 +5101,28 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); #ifdef CONFIG_PCI_ATS /* - * Some devices have a broken ATS implementation causing IOMMU stalls. - * Don't use ATS for those devices. + * Some devices require additional driver setup to enable ATS. Don't use + * ATS for those devices as ATS will be enabled before the driver has had a + * chance to load and configure the device. */ -static void quirk_no_ats(struct pci_dev *pdev) +static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { - pci_info(pdev, "disabling ATS (broken on this device)\n"); + if ((pdev->device == 0x7312 && pdev->revision != 0x00) || + (pdev->device == 0x7340 && pdev->revision != 0xc5)) + return; + + pci_info(pdev, "disabling ATS\n"); pdev->ats_cap = 0; } /* AMD Stoney platform GPU */ -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_no_ats); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats); +/* AMD Iceland dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); +/* AMD Navi10 dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats); +/* AMD Navi14 dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ /* Freescale PCIe doesn't support MSI in RC mode */ @@ -5099,7 +5299,7 @@ static void quirk_switchtec_ntb_dma_alias(struct pci_dev *pdev) pci_dbg(pdev, "Aliasing Partition %d Proxy ID %02x.%d\n", pp, PCI_SLOT(devfn), PCI_FUNC(devfn)); - pci_add_dma_alias(pdev, devfn); + pci_add_dma_alias(pdev, devfn, 1); } } @@ -5142,6 +5342,21 @@ SWITCHTEC_QUIRK(0x8575); /* PFXI 80XG3 */ SWITCHTEC_QUIRK(0x8576); /* PFXI 96XG3 */ /* + * The PLX NTB uses devfn proxy IDs to move TLPs between NT endpoints. + * These IDs are used to forward responses to the originator on the other + * side of the NTB. Alias all possible IDs to the NTB to permit access when + * the IOMMU is turned on. + */ +static void quirk_plx_ntb_dma_alias(struct pci_dev *pdev) +{ + pci_info(pdev, "Setting PLX NTB proxy ID aliases\n"); + /* PLX NTB may use all 256 devfns */ + pci_add_dma_alias(pdev, 0, 256); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PLX, 0x87b0, quirk_plx_ntb_dma_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PLX, 0x87b1, quirk_plx_ntb_dma_alias); + +/* * On Lenovo Thinkpad P50 SKUs with a Nvidia Quadro M1000M, the BIOS does * not always reset the secondary Nvidia GPU between reboots if the system * is configured to use Hybrid Graphics mode. This results in the GPU @@ -5186,7 +5401,7 @@ static void quirk_reset_lenovo_thinkpad_p50_nvgpu(struct pci_dev *pdev) */ if (ioread32(map + 0x2240c) & 0x2) { pci_info(pdev, FW_BUG "GPU left initialized by EFI, resetting\n"); - ret = pci_reset_function(pdev); + ret = pci_reset_bus(pdev); if (ret < 0) pci_err(pdev, "Failed to reset GPU: %d\n", ret); } @@ -5198,3 +5413,34 @@ out_disable: DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, 0x13b1, PCI_CLASS_DISPLAY_VGA, 8, quirk_reset_lenovo_thinkpad_p50_nvgpu); + +/* + * Device [1b21:2142] + * When in D0, PME# doesn't get asserted when plugging USB 3.0 device. + */ +static void pci_fixup_no_d0_pme(struct pci_dev *dev) +{ + pci_info(dev, "PME# does not work under D0, disabling it\n"); + dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x2142, pci_fixup_no_d0_pme); + +static void apex_pci_fixup_class(struct pci_dev *pdev) +{ + pdev->class = (PCI_CLASS_SYSTEM_OTHER << 8) | pdev->class; +} +DECLARE_PCI_FIXUP_CLASS_HEADER(0x1ac1, 0x089a, + PCI_CLASS_NOT_DEFINED, 8, apex_pci_fixup_class); + +/* + * Device [12d8:0x400e] and [12d8:0x400f] + * These devices advertise PME# support in all power states but don't + * reliably assert it. + */ +static void pci_fixup_no_pme(struct pci_dev *dev) +{ + pci_info(dev, "PME# is unreliable, disabling it\n"); + dev->pme_support = 0; +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_PERICOM, 0x400e, pci_fixup_no_pme); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_PERICOM, 0x400f, pci_fixup_no_pme); diff --git a/drivers/pci/search.c b/drivers/pci/search.c index 5c7922612733..68326e5849da 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -42,9 +42,9 @@ int pci_for_each_dma_alias(struct pci_dev *pdev, * DMA, iterate over that too. */ if (unlikely(pdev->dma_alias_mask)) { - u8 devfn; + unsigned int devfn; - for_each_set_bit(devfn, pdev->dma_alias_mask, U8_MAX) { + for_each_set_bit(devfn, pdev->dma_alias_mask, MAX_NR_DEVFNS) { ret = fn(pdev, PCI_DEVID(pdev->bus->number, devfn), data); if (ret) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 0cdd5ff389de..6bbfcc825199 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1780,12 +1780,18 @@ again: /* Restore size and flags */ list_for_each_entry(fail_res, &fail_head, list) { struct resource *res = fail_res->res; + int idx; res->start = fail_res->start; res->end = fail_res->end; res->flags = fail_res->flags; - if (fail_res->dev->subordinate) - res->flags = 0; + + if (pci_is_bridge(fail_res->dev)) { + idx = res - &fail_res->dev->resource[0]; + if (idx >= PCI_BRIDGE_RESOURCES && + idx <= PCI_BRIDGE_RESOURCE_END) + res->flags = 0; + } } free_list(&fail_head); @@ -2031,12 +2037,18 @@ again: /* Restore size and flags */ list_for_each_entry(fail_res, &fail_head, list) { struct resource *res = fail_res->res; + int idx; res->start = fail_res->start; res->end = fail_res->end; res->flags = fail_res->flags; - if (fail_res->dev->subordinate) - res->flags = 0; + + if (pci_is_bridge(fail_res->dev)) { + idx = res - &fail_res->dev->resource[0]; + if (idx >= PCI_BRIDGE_RESOURCES && + idx <= PCI_BRIDGE_RESOURCE_END) + res->flags = 0; + } } free_list(&fail_head); diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index d8ca40a97693..d21fa04fa44d 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -439,10 +439,11 @@ int pci_resize_resource(struct pci_dev *dev, int resno, int size) res->end = res->start + pci_rebar_size_to_bytes(size) - 1; /* Check if the new config works by trying to assign everything. */ - ret = pci_reassign_bridge_resources(dev->bus->self, res->flags); - if (ret) - goto error_resize; - + if (dev->bus->self) { + ret = pci_reassign_bridge_resources(dev->bus->self, res->flags); + if (ret) + goto error_resize; + } return 0; error_resize: diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index bebbde4ebec0..2ad1c30b9ef1 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -171,7 +171,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser) kref_get(&stuser->kref); stuser->read_len = sizeof(stuser->data); stuser_set_state(stuser, MRPC_QUEUED); - init_completion(&stuser->comp); + reinit_completion(&stuser->comp); list_add_tail(&stuser->list, &stdev->mrpc_queue); mrpc_cmd_submit(stdev); @@ -671,7 +671,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev, return -ENOMEM; s->global = ioread32(&stdev->mmio_sw_event->global_summary); - s->part_bitmap = ioread32(&stdev->mmio_sw_event->part_event_bitmap); + s->part_bitmap = ioread64(&stdev->mmio_sw_event->part_event_bitmap); s->local_part = ioread32(&stdev->mmio_part_cfg->part_event_summary); for (i = 0; i < stdev->partition_count; i++) { @@ -1268,7 +1268,7 @@ static int switchtec_init_isr(struct switchtec_dev *stdev) if (nvecs < 0) return nvecs; - event_irq = ioread32(&stdev->mmio_part_cfg->vep_vector_number); + event_irq = ioread16(&stdev->mmio_part_cfg->vep_vector_number); if (event_irq < 0 || event_irq >= nvecs) return -EFAULT; @@ -1341,7 +1341,7 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, if (rc) return rc; - rc = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (rc) return rc; |