From: Thomas Gleixner <tglx@linutronix.de> mainline inclusion from mainline-v5.11-rc1 commit 2e730cb56b2cd1626fecaf23ef1537fb24721ef2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/2e730cb56b2cd1626fecaf23ef1537fb247... -------------------------------- The ioapic interrupt type table is wrong as it assumes that polarity in IO/APIC context means active high when set. But the IO/APIC polarity is working the other way round. This works because the ordering of the entries is consistent with the device tree and the type information is not used by the IO/APIC interrupt chip. The whole trigger and polarity business of IO/APIC is misleading and the corresponding constants which are defined as 0/1 are not used consistently and are going to be removed. Rename the type table members to 'is_level' and 'active_low' and adjust the type information for consistency sake. No functional change. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-5-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawe.com> --- arch/x86/kernel/devicetree.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index ddffd80f5c52..6a4cb71c2498 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -184,31 +184,31 @@ static unsigned int ioapic_id; struct of_ioapic_type { u32 out_type; - u32 trigger; - u32 polarity; + u32 is_level; + u32 active_low; }; static struct of_ioapic_type of_ioapic_type[] = { { - .out_type = IRQ_TYPE_EDGE_RISING, - .trigger = IOAPIC_EDGE, - .polarity = 1, + .out_type = IRQ_TYPE_EDGE_FALLING, + .is_level = 0, + .active_low = 1, }, { - .out_type = IRQ_TYPE_LEVEL_LOW, - .trigger = IOAPIC_LEVEL, - .polarity = 0, + .out_type = IRQ_TYPE_LEVEL_HIGH, + .is_level = 1, + .active_low = 0, }, { - .out_type = IRQ_TYPE_LEVEL_HIGH, - .trigger = IOAPIC_LEVEL, - .polarity = 1, + .out_type = IRQ_TYPE_LEVEL_LOW, + .is_level = 1, + .active_low = 1, }, { - .out_type = IRQ_TYPE_EDGE_FALLING, - .trigger = IOAPIC_EDGE, - .polarity = 0, + .out_type = IRQ_TYPE_EDGE_RISING, + .is_level = 0, + .active_low = 0, }, }; @@ -228,7 +228,7 @@ static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, return -EINVAL; it = &of_ioapic_type[type_index]; - ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); + ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->is_level, it->active_low); tmp.devid = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); tmp.ioapic.pin = fwspec->param[0]; -- 2.33.0

From: Thomas Gleixner <tglx@linutronix.de> mainline inclusion from mainline-v5.11-rc1 commit e16c8058a10ba8e38d0d1ad0b64e444b245ffdbd category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/e16c8058a10ba8e38d0d1ad0b64e444b245... -------------------------------- Use the x86 shadow structs in msi_msg instead of the macros. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-16-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- drivers/pci/controller/vmd.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index f375c21ceeb1..6f8795454e5a 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -18,7 +18,6 @@ #include <asm/irqdomain.h> #include <asm/device.h> #include <asm/msi.h> -#include <asm/msidef.h> #define VMD_CFGBAR 0 #define VMD_MEMBAR1 2 @@ -131,10 +130,10 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct vmd_irq_list *irq = vmdirq->irq; struct vmd_dev *vmd = irq_data_get_irq_handler_data(data); - msg->address_hi = MSI_ADDR_BASE_HI; - msg->address_lo = MSI_ADDR_BASE_LO | - MSI_ADDR_DEST_ID(index_from_irqs(vmd, irq)); - msg->data = 0; + memset(msg, 0, sizeof(*msg)); + msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH; + msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW; + msg->arch_addr_lo.destid_0_7 = index_from_irqs(vmd, irq); } /* -- 2.33.0

From: Thomas Gleixner <tglx@linutronix.de> mainline inclusion from mainline-v5.11-rc1 commit 41bb2115beec5e318095a89f5ad4a9c343cb21ad category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/41bb2115beec5e318095a89f5ad4a9c343c... -------------------------------- Use the msi_msg shadow structs and compose the message with named bitfields instead of the unreadable macro maze. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-18-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/pci/xen.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 326d6d173733..d7f4bedb101e 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -152,7 +152,6 @@ static int acpi_register_gsi_xen(struct device *dev, u32 gsi, #if defined(CONFIG_PCI_MSI) #include <linux/msi.h> -#include <asm/msidef.h> struct xen_pci_frontend_ops *xen_pci_frontend; EXPORT_SYMBOL_GPL(xen_pci_frontend); @@ -210,23 +209,20 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return ret; } -#define XEN_PIRQ_MSI_DATA (MSI_DATA_TRIGGER_EDGE | \ - MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0)) - static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq, struct msi_msg *msg) { - /* We set vector == 0 to tell the hypervisor we don't care about it, - * but we want a pirq setup instead. - * We use the dest_id field to pass the pirq that we want. */ - msg->address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(pirq); - msg->address_lo = - MSI_ADDR_BASE_LO | - MSI_ADDR_DEST_MODE_PHYSICAL | - MSI_ADDR_REDIRECTION_CPU | - MSI_ADDR_DEST_ID(pirq); - - msg->data = XEN_PIRQ_MSI_DATA; + /* + * We set vector == 0 to tell the hypervisor we don't care about + * it, but we want a pirq setup instead. We use the dest_id fields + * to pass the pirq that we want. + */ + memset(msg, 0, sizeof(*msg)); + msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH; + msg->arch_addr_hi.destid_8_31 = pirq >> 8; + msg->arch_addr_lo.destid_0_7 = pirq & 0xFF; + msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW; + msg->arch_data.delivery_mode = APIC_DELIVERY_MODE_EXTINT; } static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -- 2.33.0

From: Thomas Gleixner <tglx@linutronix.de> mainline inclusion from mainline-v5.11-rc1 commit a27dca645d2c0f31abb7858aa0e10b2fa0f2f659 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/a27dca645d2c0f31abb7858aa0e10b2fa0f... Conflict:adapt mp_irqdomain_alloc context -------------------------------- 'trigger' and 'polarity' are used throughout the I/O-APIC code for handling the trigger type (edge/level) and the active low/high configuration. While there are defines for initializing these variables and struct members, they are not used consequently and the meaning of 'trigger' and 'polarity' is opaque and confusing at best. Rename them to 'is_level' and 'active_low' and make them boolean in various structs so it's entirely clear what the meaning is. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-20-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/include/asm/hw_irq.h | 6 +- arch/x86/kernel/apic/io_apic.c | 244 +++++++++++++--------------- arch/x86/pci/intel_mid_pci.c | 8 +- drivers/iommu/amd/iommu.c | 10 +- drivers/iommu/intel/irq_remapping.c | 9 +- 5 files changed, 130 insertions(+), 147 deletions(-) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 871cc174413f..8655cba926a3 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -48,9 +48,9 @@ enum irq_alloc_type { struct ioapic_alloc_info { int pin; int node; - u32 trigger : 1; - u32 polarity : 1; - u32 valid : 1; + u32 is_level : 1; + u32 active_low : 1; + u32 valid : 1; struct IO_APIC_route_entry *entry; }; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 086e1fbebb6e..640e685bf345 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -89,12 +89,12 @@ struct irq_pin_list { }; struct mp_chip_data { - struct list_head irq_2_pin; - struct IO_APIC_route_entry entry; - int trigger; - int polarity; + struct list_head irq_2_pin; + struct IO_APIC_route_entry entry; + bool is_level; + bool active_low; + bool isa_irq; u32 count; - bool isa_irq; }; struct mp_ioapic_gsi { @@ -737,44 +737,7 @@ static int __init find_isa_irq_apic(int irq, int type) return -1; } -#ifdef CONFIG_EISA -/* - * EISA Edge/Level control register, ELCR - */ -static int EISA_ELCR(unsigned int irq) -{ - if (irq < nr_legacy_irqs()) { - unsigned int port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; - } - apic_printk(APIC_VERBOSE, KERN_INFO - "Broken MPtable reports ISA irq %d\n", irq); - return 0; -} - -#endif - -/* ISA interrupts are always active high edge triggered, - * when listed as conforming in the MP table. */ - -#define default_ISA_trigger(idx) (IOAPIC_EDGE) -#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH) - -/* EISA interrupts are always polarity zero and can be edge or level - * trigger depending on the ELCR value. If an interrupt is listed as - * EISA conforming in the MP table, that means its trigger type must - * be read in from the ELCR */ - -#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq)) -#define default_EISA_polarity(idx) default_ISA_polarity(idx) - -/* PCI interrupts are always active low level triggered, - * when listed as conforming in the MP table. */ - -#define default_PCI_trigger(idx) (IOAPIC_LEVEL) -#define default_PCI_polarity(idx) (IOAPIC_POL_LOW) - -static int irq_polarity(int idx) +static bool irq_active_low(int idx) { int bus = mp_irqs[idx].srcbus; @@ -783,90 +746,139 @@ static int irq_polarity(int idx) */ switch (mp_irqs[idx].irqflag & MP_IRQPOL_MASK) { case MP_IRQPOL_DEFAULT: - /* conforms to spec, ie. bus-type dependent polarity */ - if (test_bit(bus, mp_bus_not_pci)) - return default_ISA_polarity(idx); - else - return default_PCI_polarity(idx); + /* + * Conforms to spec, ie. bus-type dependent polarity. PCI + * defaults to low active. [E]ISA defaults to high active. + */ + return !test_bit(bus, mp_bus_not_pci); case MP_IRQPOL_ACTIVE_HIGH: - return IOAPIC_POL_HIGH; + return false; case MP_IRQPOL_RESERVED: pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); fallthrough; case MP_IRQPOL_ACTIVE_LOW: default: /* Pointless default required due to do gcc stupidity */ - return IOAPIC_POL_LOW; + return true; } } #ifdef CONFIG_EISA -static int eisa_irq_trigger(int idx, int bus, int trigger) +/* + * EISA Edge/Level control register, ELCR + */ +static bool EISA_ELCR(unsigned int irq) +{ + if (irq < nr_legacy_irqs()) { + unsigned int port = 0x4d0 + (irq >> 3); + return (inb(port) >> (irq & 7)) & 1; + } + apic_printk(APIC_VERBOSE, KERN_INFO + "Broken MPtable reports ISA irq %d\n", irq); + return false; +} + +/* + * EISA interrupts are always active high and can be edge or level + * triggered depending on the ELCR value. If an interrupt is listed as + * EISA conforming in the MP table, that means its trigger type must be + * read in from the ELCR. + */ +static bool eisa_irq_is_level(int idx, int bus, bool level) { switch (mp_bus_id_to_type[bus]) { case MP_BUS_PCI: case MP_BUS_ISA: - return trigger; + return level; case MP_BUS_EISA: - return default_EISA_trigger(idx); + return EISA_ELCR(mp_irqs[idx].srcbusirq); } pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus); - return IOAPIC_LEVEL; + return true; } #else -static inline int eisa_irq_trigger(int idx, int bus, int trigger) +static inline int eisa_irq_is_level(int idx, int bus, bool level) { - return trigger; + return level; } #endif -static int irq_trigger(int idx) +static bool irq_is_level(int idx) { int bus = mp_irqs[idx].srcbus; - int trigger; + bool level; /* * Determine IRQ trigger mode (edge or level sensitive): */ switch (mp_irqs[idx].irqflag & MP_IRQTRIG_MASK) { case MP_IRQTRIG_DEFAULT: - /* conforms to spec, ie. bus-type dependent trigger mode */ - if (test_bit(bus, mp_bus_not_pci)) - trigger = default_ISA_trigger(idx); - else - trigger = default_PCI_trigger(idx); + /* + * Conforms to spec, ie. bus-type dependent trigger + * mode. PCI defaults to egde, ISA to level. + */ + level = test_bit(bus, mp_bus_not_pci); /* Take EISA into account */ - return eisa_irq_trigger(idx, bus, trigger); + return eisa_irq_is_level(idx, bus, level); case MP_IRQTRIG_EDGE: - return IOAPIC_EDGE; + return false; case MP_IRQTRIG_RESERVED: pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); fallthrough; case MP_IRQTRIG_LEVEL: default: /* Pointless default required due to do gcc stupidity */ - return IOAPIC_LEVEL; + return true; } } +static int __acpi_get_override_irq(u32 gsi, bool *trigger, bool *polarity) +{ + int ioapic, pin, idx; + + if (skip_ioapic_setup) + return -1; + + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return -1; + + pin = mp_find_ioapic_pin(ioapic, gsi); + if (pin < 0) + return -1; + + idx = find_irq_entry(ioapic, pin, mp_INT); + if (idx < 0) + return -1; + + *trigger = irq_is_level(idx); + *polarity = irq_active_low(idx); + return 0; +} + +#ifdef CONFIG_ACPI +int acpi_get_override_irq(u32 gsi, int *is_level, int *active_low) +{ + *is_level = *active_low = 0; + return __acpi_get_override_irq(gsi, (bool *)is_level, + (bool *)active_low); +} +#endif + void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node, int trigger, int polarity) { init_irq_alloc_info(info, NULL); info->type = X86_IRQ_ALLOC_TYPE_IOAPIC; info->ioapic.node = node; - info->ioapic.trigger = trigger; - info->ioapic.polarity = polarity; + info->ioapic.is_level = trigger; + info->ioapic.active_low = polarity; info->ioapic.valid = 1; } -#ifndef CONFIG_ACPI -int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); -#endif - static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, struct irq_alloc_info *src, u32 gsi, int ioapic_idx, int pin) { - int trigger, polarity; + bool level, pol_low; copy_irq_alloc_info(dst, src); dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC; @@ -875,20 +887,20 @@ static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, dst->ioapic.valid = 1; if (src && src->ioapic.valid) { dst->ioapic.node = src->ioapic.node; - dst->ioapic.trigger = src->ioapic.trigger; - dst->ioapic.polarity = src->ioapic.polarity; + dst->ioapic.is_level = src->ioapic.is_level; + dst->ioapic.active_low = src->ioapic.active_low; } else { dst->ioapic.node = NUMA_NO_NODE; - if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) { - dst->ioapic.trigger = trigger; - dst->ioapic.polarity = polarity; + if (__acpi_get_override_irq(gsi, &level, &pol_low) >= 0) { + dst->ioapic.is_level = level; + dst->ioapic.active_low = pol_low; } else { /* * PCI interrupts are always active low level * triggered. */ - dst->ioapic.trigger = IOAPIC_LEVEL; - dst->ioapic.polarity = IOAPIC_POL_LOW; + dst->ioapic.is_level = true; + dst->ioapic.active_low = true; } } } @@ -898,12 +910,12 @@ static int ioapic_alloc_attr_node(struct irq_alloc_info *info) return (info && info->ioapic.valid) ? info->ioapic.node : NUMA_NO_NODE; } -static void mp_register_handler(unsigned int irq, unsigned long trigger) +static void mp_register_handler(unsigned int irq, bool level) { irq_flow_handler_t hdl; bool fasteoi; - if (trigger) { + if (level) { irq_set_status_flags(irq, IRQ_LEVEL); fasteoi = true; } else { @@ -925,14 +937,14 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) * pin with real trigger and polarity attributes. */ if (irq < nr_legacy_irqs() && data->count == 1) { - if (info->ioapic.trigger != data->trigger) - mp_register_handler(irq, info->ioapic.trigger); - data->entry.trigger = data->trigger = info->ioapic.trigger; - data->entry.polarity = data->polarity = info->ioapic.polarity; + if (info->ioapic.is_level != data->is_level) + mp_register_handler(irq, info->ioapic.is_level); + data->entry.trigger = data->is_level = info->ioapic.is_level; + data->entry.polarity = data->active_low = info->ioapic.active_low; } - return data->trigger == info->ioapic.trigger && - data->polarity == info->ioapic.polarity; + return data->is_level == info->ioapic.is_level && + data->active_low == info->ioapic.active_low; } static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, @@ -2207,9 +2219,9 @@ static inline void __init check_timer(void) * so only need to unmask if it is level-trigger * do we really have level trigger timer? */ - int idx; - idx = find_irq_entry(apic1, pin1, mp_INT); - if (idx != -1 && irq_trigger(idx)) + int idx = find_irq_entry(apic1, pin1, mp_INT); + + if (idx != -1 && irq_is_level(idx)) unmask_ioapic_irq(irq_get_irq_data(0)); } irq_domain_deactivate_irq(irq_data); @@ -2620,30 +2632,6 @@ static int io_apic_get_version(int ioapic) return reg_01.bits.version; } -int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) -{ - int ioapic, pin, idx; - - if (skip_ioapic_setup) - return -1; - - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return -1; - - pin = mp_find_ioapic_pin(ioapic, gsi); - if (pin < 0) - return -1; - - idx = find_irq_entry(ioapic, pin, mp_INT); - if (idx < 0) - return -1; - - *trigger = irq_trigger(idx); - *polarity = irq_polarity(idx); - return 0; -} - /* * This function updates target affinity of IOAPIC interrupts to include * the CPUs which came online during SMP bringup. @@ -2967,13 +2955,13 @@ static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, struct irq_alloc_info *info) { if (info && info->ioapic.valid) { - data->trigger = info->ioapic.trigger; - data->polarity = info->ioapic.polarity; - } else if (acpi_get_override_irq(gsi, &data->trigger, - &data->polarity) < 0) { + data->is_level = info->ioapic.is_level; + data->active_low = info->ioapic.active_low; + } else if (__acpi_get_override_irq(gsi, &data->is_level, + &data->active_low) < 0) { /* PCI interrupts are always active low level triggered. */ - data->trigger = IOAPIC_LEVEL; - data->polarity = IOAPIC_POL_LOW; + data->is_level = true; + data->active_low = true; } } @@ -2985,16 +2973,13 @@ static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data, entry->dest_mode = apic->dest_mode_logical; entry->dest = cfg->dest_apicid; entry->vector = cfg->vector; - entry->trigger = data->trigger; - entry->polarity = data->polarity; + entry->trigger = data->is_level; + entry->polarity = data->active_low; /* * Mask level triggered irqs. Edge triggered irqs are masked * by the irq core code in case they fire. */ - if (data->trigger == IOAPIC_LEVEL) - entry->mask = IOAPIC_MASKED; - else - entry->mask = IOAPIC_UNMASKED; + entry->mask = data->is_level; } int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, @@ -3043,7 +3028,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, local_irq_save(flags); if (info->ioapic.entry) mp_setup_entry(cfg, data, info->ioapic.entry); - mp_register_handler(virq, data->trigger); + mp_register_handler(virq, data->is_level); if (virq < nr_legacy_irqs()) legacy_pic->mask(virq); local_irq_restore(flags); @@ -3051,7 +3036,8 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector, - virq, data->trigger, data->polarity, cfg->dest_apicid); + virq, data->is_level, data->active_low, + cfg->dest_apicid); return 0; diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 24ca4ee2802f..95e2e6bd8d8c 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, static int intel_mid_pci_irq_enable(struct pci_dev *dev) { struct irq_alloc_info info; - int polarity; + bool polarity_low; int ret; u8 gsi; @@ -230,7 +230,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) switch (intel_mid_identify_cpu()) { case INTEL_MID_CPU_CHIP_TANGIER: - polarity = IOAPIC_POL_HIGH; + polarity_low = false; /* Special treatment for IRQ0 */ if (gsi == 0) { @@ -252,11 +252,11 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) } break; default: - polarity = IOAPIC_POL_LOW; + polarity_low = true; break; } - ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity); + ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity_low); /* * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 932118b4dd54..ea36eeb0a179 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3696,13 +3696,11 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data, entry = info->ioapic.entry; info->ioapic.entry = NULL; memset(entry, 0, sizeof(*entry)); - entry->vector = index; - entry->mask = 0; - entry->trigger = info->ioapic.trigger; - entry->polarity = info->ioapic.polarity; + entry->vector = index; + entry->trigger = info->ioapic.is_level; + entry->polarity = info->ioapic.active_low; /* Mask level triggered irqs. */ - if (info->ioapic.trigger) - entry->mask = 1; + entry->mask = info->ioapic.is_level; break; case X86_IRQ_ALLOC_TYPE_HPET: diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 99d395b1e6c4..1e07522162ce 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1313,11 +1313,10 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data, * irq handler will do the explicit EOI to the io-apic. */ entry->vector = info->ioapic.pin; - entry->mask = 0; /* enable IRQ */ - entry->trigger = info->ioapic.trigger; - entry->polarity = info->ioapic.polarity; - if (info->ioapic.trigger) - entry->mask = 1; /* Mask level triggered irqs. */ + entry->trigger = info->ioapic.is_level; + entry->polarity = info->ioapic.active_low; + /* Mask level triggered irqs. */ + entry->mask = info->ioapic.is_level; break; case X86_IRQ_ALLOC_TYPE_HPET: -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit 5d5a97133887b2dfd8e2ad0347c3a02cc7aaa0cb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/5d5a97133887b2dfd8e2ad0347c3a02cc7a... Conflict: adapt mp_irqdomain_alloc context -------------------------------- The I/O-APIC generates an MSI cycle with address/data bits taken from its Redirection Table Entry in some combination which used to make sense, but now is just a bunch of bits which get passed through in some seemingly arbitrary order. Instead of making IRQ remapping drivers directly frob the I/OA-PIC RTE, let them just do their job and generate an MSI message. The bit swizzling to turn that MSI message into the I/O-APIC's RTE is the same in all cases, since it's a function of the I/O-APIC hardware. The IRQ remappers have no real need to get involved with that. The only slight caveat is that the I/OAPIC is interpreting some of those fields too, and it does want the 'vector' field to be unique to make EOI work. The AMD IOMMU happens to put its IRTE index in the bits that the I/O-APIC thinks are the vector field, and accommodates this requirement by reserving the first 32 indices for the I/O-APIC. The Intel IOMMU doesn't actually use the bits that the I/O-APIC thinks are the vector field, so it fills in the 'pin' value there instead. [ tglx: Replaced the unreadably macro maze with the cleaned up RTE/msi_msg bitfields and added commentry to explain the mapping magic ] Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-22-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/include/asm/hw_irq.h | 11 ++- arch/x86/kernel/apic/io_apic.c | 103 +++++++++++++++++++--------- drivers/iommu/amd/iommu.c | 12 ---- drivers/iommu/hyperv-iommu.c | 31 --------- drivers/iommu/intel/irq_remapping.c | 31 ++------- 5 files changed, 83 insertions(+), 105 deletions(-) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 8655cba926a3..517074323674 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -46,12 +46,11 @@ enum irq_alloc_type { }; struct ioapic_alloc_info { - int pin; - int node; - u32 is_level : 1; - u32 active_low : 1; - u32 valid : 1; - struct IO_APIC_route_entry *entry; + int pin; + int node; + u32 is_level : 1; + u32 active_low : 1; + u32 valid : 1; }; struct uv_alloc_info { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 20e480c173ae..1f0121b739e9 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -48,6 +48,7 @@ #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> #include <linux/memblock.h> +#include <linux/msi.h> #include <asm/irqdomain.h> #include <asm/io.h> @@ -63,7 +64,6 @@ #include <asm/setup.h> #include <asm/irq_remapping.h> #include <asm/hw_irq.h> - #include <asm/apic.h> #define for_each_ioapic(idx) \ @@ -1874,21 +1874,58 @@ static void ioapic_ir_ack_level(struct irq_data *irq_data) eoi_ioapic_pin(data->entry.vector, data); } +/* + * The I/OAPIC is just a device for generating MSI messages from legacy + * interrupt pins. Various fields of the RTE translate into bits of the + * resulting MSI which had a historical meaning. + * + * With interrupt remapping, many of those bits have different meanings + * in the underlying MSI, but the way that the I/OAPIC transforms them + * from its RTE to the MSI message is the same. This function allows + * the parent IRQ domain to compose the MSI message, then takes the + * relevant bits to put them in the appropriate places in the RTE in + * order to generate that message when the IRQ happens. + * + * The setup here relies on a preconfigured route entry (is_level, + * active_low, masked) because the parent domain is merely composing the + * generic message routing information which is used for the MSI. + */ +static void ioapic_setup_msg_from_msi(struct irq_data *irq_data, + struct IO_APIC_route_entry *entry) +{ + struct msi_msg msg; + + /* Let the parent domain compose the MSI message */ + irq_chip_compose_msi_msg(irq_data, &msg); + + /* + * - Real vector + * - DMAR/IR: 8bit subhandle (ioapic.pin) + * - AMD/IR: 8bit IRTE index + */ + entry->vector = msg.arch_data.vector; + /* Delivery mode (for DMAR/IR all 0) */ + entry->delivery_mode = msg.arch_data.delivery_mode; + /* Destination mode or DMAR/IR index bit 15 */ + entry->dest_mode_logical = msg.arch_addr_lo.dest_mode_logical; + /* DMAR/IR: 1, 0 for all other modes */ + entry->ir_format = msg.arch_addr_lo.dmar_format; + /* + * DMAR/IR: index bit 0-14. + * + * All other modes have bit 0-6 of dmar_index_0_14 cleared and the + * topmost 8 bits are destination id bit 0-7 (entry::destid_0_7). + */ + entry->ir_index_0_14 = msg.arch_addr_lo.dmar_index_0_14; +} + static void ioapic_configure_entry(struct irq_data *irqd) { struct mp_chip_data *mpd = irqd->chip_data; - struct irq_cfg *cfg = irqd_cfg(irqd); struct irq_pin_list *entry; - /* - * Only update when the parent is the vector domain, don't touch it - * if the parent is the remapping domain. Check the installed - * ioapic chip to verify that. - */ - if (irqd->chip == &ioapic_chip) { - mpd->entry.destid_0_7 = cfg->dest_apicid; - mpd->entry.vector = cfg->vector; - } + ioapic_setup_msg_from_msi(irqd, &mpd->entry); + for_each_irq_pin(entry, mpd->irq_2_pin) __ioapic_write_entry(entry->apic, entry->pin, mpd->entry); } @@ -2951,14 +2988,23 @@ static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, } } -static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data, - struct IO_APIC_route_entry *entry) +/* + * Configure the I/O-APIC specific fields in the routing entry. + * + * This is important to setup the I/O-APIC specific bits (is_level, + * active_low, masked) because the underlying parent domain will only + * provide the routing information and is oblivious of the I/O-APIC + * specific bits. + * + * The entry is just preconfigured at this point and not written into the + * RTE. This happens later during activation which will fill in the actual + * routing information. + */ +static void mp_preconfigure_entry(struct mp_chip_data *data) { + struct IO_APIC_route_entry *entry = &data->entry; + memset(entry, 0, sizeof(*entry)); - entry->delivery_mode = apic->delivery_mode; - entry->dest_mode_logical = apic->dest_mode_logical; - entry->destid_0_7 = cfg->dest_apicid; - entry->vector = cfg->vector; entry->is_level = data->is_level; entry->active_low = data->active_low; /* @@ -2971,11 +3017,10 @@ static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data, int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { - int ret, ioapic, pin; - struct irq_cfg *cfg; - struct irq_data *irq_data; - struct mp_chip_data *data; struct irq_alloc_info *info = arg; + struct mp_chip_data *data; + struct irq_data *irq_data; + int ret, ioapic, pin; unsigned long flags; if (!info || nr_irqs > 1) @@ -2993,7 +3038,6 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, if (!data) return -ENOMEM; - info->ioapic.entry = &data->entry; ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); if (ret < 0) goto free_data; @@ -3005,26 +3049,23 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); - cfg = irqd_cfg(irq_data); if (!add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin)) { ret = -ENOMEM; goto free_irqs; } - local_irq_save(flags); - if (info->ioapic.entry) - mp_setup_entry(cfg, data, info->ioapic.entry); + mp_preconfigure_entry(data); mp_register_handler(virq, data->is_level); + + local_irq_save(flags); if (virq < nr_legacy_irqs()) legacy_pic->mask(virq); local_irq_restore(flags); apic_printk(APIC_VERBOSE, KERN_DEBUG - "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", - ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector, - virq, data->is_level, data->active_low, - cfg->dest_apicid); - + "IOAPIC[%d]: Preconfigured routing entry (%d-%d -> IRQ %d Level:%i ActiveLow:%i)\n", + ioapic, mpc_ioapic_id(ioapic), pin, virq, + data->is_level, data->active_low); return 0; free_irqs: diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 9631882e8c65..4b33c83f75b0 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3678,7 +3678,6 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data, int devid, int index, int sub_handle) { struct irq_2_irte *irte_info = &data->irq_2_irte; - struct IO_APIC_route_entry *entry; struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; if (!iommu) @@ -3692,17 +3691,6 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data, switch (info->type) { case X86_IRQ_ALLOC_TYPE_IOAPIC: - /* Setup IOAPIC entry */ - entry = info->ioapic.entry; - info->ioapic.entry = NULL; - memset(entry, 0, sizeof(*entry)); - entry->vector = index; - entry->is_level = info->ioapic.is_level; - entry->active_low = info->ioapic.active_low; - /* Mask level triggered irqs. */ - entry->masked = info->ioapic.is_level; - break; - case X86_IRQ_ALLOC_TYPE_HPET: case X86_IRQ_ALLOC_TYPE_PCI_MSI: case X86_IRQ_ALLOC_TYPE_PCI_MSIX: diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 1ab7eb918a5c..37dd485a5640 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -40,7 +40,6 @@ static int hyperv_ir_set_affinity(struct irq_data *data, { struct irq_data *parent = data->parent_data; struct irq_cfg *cfg = irqd_cfg(data); - struct IO_APIC_route_entry *entry; int ret; /* Return error If new irq affinity is out of ioapic_max_cpumask. */ @@ -51,9 +50,6 @@ static int hyperv_ir_set_affinity(struct irq_data *data, if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) return ret; - entry = data->chip_data; - entry->destid_0_7 = cfg->dest_apicid; - entry->vector = cfg->vector; send_cleanup_vector(cfg); return 0; @@ -89,20 +85,6 @@ static int hyperv_irq_remapping_alloc(struct irq_domain *domain, irq_data->chip = &hyperv_ir_chip; - /* - * If there is interrupt remapping function of IOMMU, setting irq - * affinity only needs to change IRTE of IOMMU. But Hyper-V doesn't - * support interrupt remapping function, setting irq affinity of IO-APIC - * interrupts still needs to change IO-APIC registers. But ioapic_ - * configure_entry() will ignore value of cfg->vector and cfg-> - * dest_apicid when IO-APIC's parent irq domain is not the vector - * domain.(See ioapic_configure_entry()) In order to setting vector - * and dest_apicid to IO-APIC register, IO-APIC entry pointer is saved - * in the chip_data and hyperv_irq_remapping_activate()/hyperv_ir_set_ - * affinity() set vector and dest_apicid directly into IO-APIC entry. - */ - irq_data->chip_data = info->ioapic.entry; - /* * Hypver-V IO APIC irq affinity should be in the scope of * ioapic_max_cpumask because no irq remapping support. @@ -119,22 +101,9 @@ static void hyperv_irq_remapping_free(struct irq_domain *domain, irq_domain_free_irqs_common(domain, virq, nr_irqs); } -static int hyperv_irq_remapping_activate(struct irq_domain *domain, - struct irq_data *irq_data, bool reserve) -{ - struct irq_cfg *cfg = irqd_cfg(irq_data); - struct IO_APIC_route_entry *entry = irq_data->chip_data; - - entry->destid_0_7 = cfg->dest_apicid; - entry->vector = cfg->vector; - - return 0; -} - static const struct irq_domain_ops hyperv_ir_domain_ops = { .alloc = hyperv_irq_remapping_alloc, .free = hyperv_irq_remapping_free, - .activate = hyperv_irq_remapping_activate, }; static int __init hyperv_prepare_irq_remapping(void) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index e26aee553181..af2cd833fb22 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1287,9 +1287,9 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data, int index, int sub_handle) { struct irte *irte = &data->irte_entry; - struct IO_APIC_route_entry *entry; prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid); + switch (info->type) { case X86_IRQ_ALLOC_TYPE_IOAPIC: /* Set source-id of interrupt request */ @@ -1300,39 +1300,20 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data, irte->trigger_mode, irte->dlvry_mode, irte->avail, irte->vector, irte->dest_id, irte->sid, irte->sq, irte->svt); - - entry = info->ioapic.entry; - info->ioapic.entry = NULL; - memset(entry, 0, sizeof(*entry)); - entry->ir_index_15 = !!(index & 0x8000); - entry->ir_format = true; - entry->ir_index_0_14 = index & 0x7fff; - /* - * IO-APIC RTE will be configured with virtual vector. - * irq handler will do the explicit EOI to the io-apic. - */ - entry->vector = info->ioapic.pin; - entry->is_level = info->ioapic.is_level; - entry->active_low = info->ioapic.active_low; - /* Mask level triggered irqs. */ - entry->masked = info->ioapic.is_level; + sub_handle = info->ioapic.pin; break; - case X86_IRQ_ALLOC_TYPE_HPET: + set_hpet_sid(irte, info->devid); + break; case X86_IRQ_ALLOC_TYPE_PCI_MSI: case X86_IRQ_ALLOC_TYPE_PCI_MSIX: - if (info->type == X86_IRQ_ALLOC_TYPE_HPET) - set_hpet_sid(irte, info->devid); - else - set_msi_sid(irte, msi_desc_to_pci_dev(info->desc)); - - fill_msi_msg(&data->msi_entry, index, sub_handle); + set_msi_sid(irte, msi_desc_to_pci_dev(info->desc)); break; - default: BUG_ON(1); break; } + fill_msi_msg(&data->msi_entry, index, sub_handle); } static void intel_free_irq_resources(struct irq_domain *domain, -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit 6452ea2a323b80868ce5e6d3030e4ccbeab9dc30 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/6452ea2a323b80868ce5e6d3030e4ccbeab... -------------------------------- This will be used to select the irqdomain for I/O-APIC and HPET. Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-24-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/include/asm/irqdomain.h | 3 +++ arch/x86/kernel/apic/vector.c | 43 ++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+) diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index cd684d45cb5f..125c23b7bad3 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -12,6 +12,9 @@ enum { X86_IRQ_ALLOC_LEGACY = 0x2, }; +extern int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec); +extern int x86_fwspec_is_hpet(struct irq_fwspec *fwspec); + extern struct irq_domain *x86_vector_domain; extern void init_irq_alloc_info(struct irq_alloc_info *info, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 5331e3faf03c..4d9e850f8efb 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -640,7 +640,50 @@ static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d, } #endif +int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec) +{ + if (fwspec->param_count != 1) + return 0; + + if (is_fwnode_irqchip(fwspec->fwnode)) { + const char *fwname = fwnode_get_name(fwspec->fwnode); + return fwname && !strncmp(fwname, "IO-APIC-", 8) && + simple_strtol(fwname+8, NULL, 10) == fwspec->param[0]; + } + return to_of_node(fwspec->fwnode) && + of_device_is_compatible(to_of_node(fwspec->fwnode), + "intel,ce4100-ioapic"); +} + +int x86_fwspec_is_hpet(struct irq_fwspec *fwspec) +{ + if (fwspec->param_count != 1) + return 0; + + if (is_fwnode_irqchip(fwspec->fwnode)) { + const char *fwname = fwnode_get_name(fwspec->fwnode); + return fwname && !strncmp(fwname, "HPET-MSI-", 9) && + simple_strtol(fwname+9, NULL, 10) == fwspec->param[0]; + } + return 0; +} + +static int x86_vector_select(struct irq_domain *d, struct irq_fwspec *fwspec, + enum irq_domain_bus_token bus_token) +{ + /* + * HPET and I/OAPIC cannot be parented in the vector domain + * if IRQ remapping is enabled. APIC IDs above 15 bits are + * only permitted if IRQ remapping is enabled, so check that. + */ + if (apic->apic_id_valid(32768)) + return 0; + + return x86_fwspec_is_ioapic(fwspec) || x86_fwspec_is_hpet(fwspec); +} + static const struct irq_domain_ops x86_vector_domain_ops = { + .select = x86_vector_select, .alloc = x86_vector_alloc_irqs, .free = x86_vector_free_irqs, .activate = x86_vector_activate, -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit a87fb465ffe8eacd0d69032da33455e4f6fd8b41 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/a87fb465ffe8eacd0d69032da33455e4f6f... -------------------------------- Preparatory for removing irq_remapping_get_irq_domain() Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-26-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- drivers/iommu/intel/irq_remapping.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index af2cd833fb22..666a570c8ba8 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1440,7 +1440,20 @@ static void intel_irq_remapping_deactivate(struct irq_domain *domain, modify_irte(&data->irq_2_iommu, &entry); } +static int intel_irq_remapping_select(struct irq_domain *d, + struct irq_fwspec *fwspec, + enum irq_domain_bus_token bus_token) +{ + if (x86_fwspec_is_ioapic(fwspec)) + return d == map_ioapic_to_ir(fwspec->param[0]); + else if (x86_fwspec_is_hpet(fwspec)) + return d == map_hpet_to_ir(fwspec->param[0]); + + return 0; +} + static const struct irq_domain_ops intel_ir_domain_ops = { + .select = intel_irq_remapping_select, .alloc = intel_irq_remapping_alloc, .free = intel_irq_remapping_free, .activate = intel_irq_remapping_activate, -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit c2a5881c28e5bb4cb901029423a1c7068c0afa2d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/c2a5881c28e5bb4cb901029423a1c7068c0... -------------------------------- All possible parent domains have a select method now. Make use of it. Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-28-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/kernel/hpet.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 0553f22de90e..71f336425e58 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -544,8 +544,8 @@ static struct irq_domain *hpet_create_irq_domain(int hpet_id) { struct msi_domain_info *domain_info; struct irq_domain *parent, *d; - struct irq_alloc_info info; struct fwnode_handle *fn; + struct irq_fwspec fwspec; if (x86_vector_domain == NULL) return NULL; @@ -557,15 +557,6 @@ static struct irq_domain *hpet_create_irq_domain(int hpet_id) *domain_info = hpet_msi_domain_info; domain_info->data = (void *)(long)hpet_id; - init_irq_alloc_info(&info, NULL); - info.type = X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT; - info.devid = hpet_id; - parent = irq_remapping_get_irq_domain(&info); - if (parent == NULL) - parent = x86_vector_domain; - else - hpet_msi_controller.name = "IR-HPET-MSI"; - fn = irq_domain_alloc_named_id_fwnode(hpet_msi_controller.name, hpet_id); if (!fn) { @@ -573,6 +564,19 @@ static struct irq_domain *hpet_create_irq_domain(int hpet_id) return NULL; } + fwspec.fwnode = fn; + fwspec.param_count = 1; + fwspec.param[0] = hpet_id; + + parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); + if (!parent) { + irq_domain_free_fwnode(fn); + kfree(domain_info); + return NULL; + } + if (parent != x86_vector_domain) + hpet_msi_controller.name = "IR-HPET-MSI"; + d = msi_create_irq_domain(fn, domain_info, parent); if (!d) { irq_domain_free_fwnode(fn); -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit ed381fca47122f0787ee53b97e5f9d562eec7237 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/ed381fca47122f0787ee53b97e5f9d562ee... Conflict: adapt irq_alloc_type context because merge c73e909ebb14802494441a93cc6c31ad8db43e65 in advance. -------------------------------- All users are converted to use the fwspec based parent domain lookup. Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-30-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/include/asm/hw_irq.h | 2 -- arch/x86/include/asm/irq_remapping.h | 9 -------- drivers/iommu/amd/iommu.c | 34 ---------------------------- drivers/iommu/hyperv-iommu.c | 9 -------- drivers/iommu/intel/irq_remapping.c | 17 -------------- drivers/iommu/irq_remapping.c | 14 ------------ drivers/iommu/irq_remapping.h | 3 --- 7 files changed, 88 deletions(-) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 517074323674..d465ece58151 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -41,8 +41,6 @@ enum irq_alloc_type { X86_IRQ_ALLOC_TYPE_DMAR, X86_IRQ_ALLOC_TYPE_AMDVI, X86_IRQ_ALLOC_TYPE_UV, - X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT, - X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT, }; struct ioapic_alloc_info { diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index af4a151d70b3..7cc49432187f 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -44,9 +44,6 @@ extern int irq_remapping_reenable(int); extern int irq_remap_enable_fault_handling(void); extern void panic_if_irq_remap(const char *msg); -extern struct irq_domain * -irq_remapping_get_irq_domain(struct irq_alloc_info *info); - /* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */ extern struct irq_domain * arch_create_remap_msi_irq_domain(struct irq_domain *par, const char *n, int id); @@ -71,11 +68,5 @@ static inline void panic_if_irq_remap(const char *msg) { } -static inline struct irq_domain * -irq_remapping_get_irq_domain(struct irq_alloc_info *info) -{ - return NULL; -} - #endif /* CONFIG_IRQ_REMAP */ #endif /* __X86_IRQ_REMAPPING_H */ diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 73833f3bcaa4..9f6cabc00ced 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3610,10 +3610,8 @@ static int get_devid(struct irq_alloc_info *info) { switch (info->type) { case X86_IRQ_ALLOC_TYPE_IOAPIC: - case X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT: return get_ioapic_devid(info->devid); case X86_IRQ_ALLOC_TYPE_HPET: - case X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT: return get_hpet_devid(info->devid); case X86_IRQ_ALLOC_TYPE_PCI_MSI: case X86_IRQ_ALLOC_TYPE_PCI_MSIX: @@ -3624,44 +3622,12 @@ static int get_devid(struct irq_alloc_info *info) } } -static struct irq_domain *get_irq_domain_for_devid(struct irq_alloc_info *info, - int devid) -{ - struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; - - if (!iommu) - return NULL; - - switch (info->type) { - case X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT: - case X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT: - return iommu->ir_domain; - default: - WARN_ON_ONCE(1); - return NULL; - } -} - -static struct irq_domain *get_irq_domain(struct irq_alloc_info *info) -{ - int devid; - - if (!info) - return NULL; - - devid = get_devid(info); - if (devid < 0) - return NULL; - return get_irq_domain_for_devid(info, devid); -} - struct irq_remap_ops amd_iommu_irq_ops = { .prepare = amd_iommu_prepare, .enable = amd_iommu_enable, .disable = amd_iommu_disable, .reenable = amd_iommu_reenable, .enable_faulting = amd_iommu_enable_faulting, - .get_irq_domain = get_irq_domain, }; static void fill_msi_msg(struct msi_msg *msg, u32 index) diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 78a264ad9405..a629a6be65c7 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -160,18 +160,9 @@ static int __init hyperv_enable_irq_remapping(void) return IRQ_REMAP_X2APIC_MODE; } -static struct irq_domain *hyperv_get_irq_domain(struct irq_alloc_info *info) -{ - if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT) - return ioapic_ir_domain; - else - return NULL; -} - struct irq_remap_ops hyperv_irq_remap_ops = { .prepare = hyperv_prepare_irq_remapping, .enable = hyperv_enable_irq_remapping, - .get_irq_domain = hyperv_get_irq_domain, }; #endif diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 666a570c8ba8..3595627596ea 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1134,29 +1134,12 @@ static void prepare_irte(struct irte *irte, int vector, unsigned int dest) irte->redir_hint = 1; } -static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info) -{ - if (!info) - return NULL; - - switch (info->type) { - case X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT: - return map_ioapic_to_ir(info->devid); - case X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT: - return map_hpet_to_ir(info->devid); - default: - WARN_ON_ONCE(1); - return NULL; - } -} - struct irq_remap_ops intel_irq_remap_ops = { .prepare = intel_prepare_irq_remapping, .enable = intel_enable_irq_remapping, .disable = disable_irq_remapping, .reenable = reenable_irq_remapping, .enable_faulting = enable_drhd_fault_handling, - .get_irq_domain = intel_get_irq_domain, }; static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force) diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 2d84b1ed205e..83314b9d8f38 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -158,17 +158,3 @@ void panic_if_irq_remap(const char *msg) if (irq_remapping_enabled) panic(msg); } - -/** - * irq_remapping_get_irq_domain - Get the irqdomain serving the request @info - * @info: interrupt allocation information, used to identify the IOMMU device - * - * Returns pointer to IRQ domain, or NULL on failure. - */ -struct irq_domain *irq_remapping_get_irq_domain(struct irq_alloc_info *info) -{ - if (!remap_ops || !remap_ops->get_irq_domain) - return NULL; - - return remap_ops->get_irq_domain(info); -} diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h index 1661b3d75920..8c89cb947cdb 100644 --- a/drivers/iommu/irq_remapping.h +++ b/drivers/iommu/irq_remapping.h @@ -42,9 +42,6 @@ struct irq_remap_ops { /* Enable fault handling */ int (*enable_faulting)(void); - - /* Get the irqdomain associated to IOMMU device */ - struct irq_domain *(*get_irq_domain)(struct irq_alloc_info *); }; extern struct irq_remap_ops intel_irq_remap_ops; -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit 51130d21881d435fad5fa7f25bea77aa0ffc9a4e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/51130d21881d435fad5fa7f25bea77aa0ff... -------------------------------- Bits 63-48 of the I/OAPIC Redirection Table Entry map directly to bits 19-4 of the address used in the resulting MSI cycle. Historically, the x86 MSI format only used the top 8 of those 16 bits as the destination APIC ID, and the "Extended Destination ID" in the lower 8 bits was unused. With interrupt remapping, the lowest bit of the Extended Destination ID (bit 48 of RTE, bit 4 of MSI address) is now used to indicate a remappable format MSI. A hypervisor can use the other 7 bits of the Extended Destination ID to permit guests to address up to 15 bits of APIC IDs, thus allowing 32768 vCPUs before having to expose a vIOMMU and interrupt remapping to the guest. No behavioural change in this patch, since nothing yet permits APIC IDs above 255 to be used with the non-IR I/OAPIC domain. [ tglx: Converted it to the cleaned up entry/msi_msg format and added commentry ] Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-32-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/include/asm/io_apic.h | 3 ++- arch/x86/kernel/apic/io_apic.c | 20 +++++++++++++++----- 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 4b614ee06d0f..072ce70d44ee 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -67,7 +67,8 @@ struct IO_APIC_route_entry { is_level : 1, masked : 1, reserved_0 : 15, - reserved_1 : 24, + reserved_1 : 17, + virt_destid_8_14 : 7, destid_0_7 : 8; }; struct { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f4f822522ee5..288e8fd7c776 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1264,9 +1264,10 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) (entry.ir_index_15 << 15) | entry.ir_index_0_14, entry.ir_zero); } else { - printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", buf, + printk(KERN_DEBUG "%s, %s, D(%02X%02X), M(%1d)\n", buf, entry.dest_mode_logical ? "logical " : "physical", - entry.destid_0_7, entry.delivery_mode); + entry.virt_destid_8_14, entry.destid_0_7, + entry.delivery_mode); } } } @@ -1435,6 +1436,7 @@ void native_restore_boot_irq_mode(void) */ if (ioapic_i8259.pin != -1) { struct IO_APIC_route_entry entry; + u32 apic_id = read_apic_id(); memset(&entry, 0, sizeof(entry)); entry.masked = false; @@ -1442,7 +1444,8 @@ void native_restore_boot_irq_mode(void) entry.active_low = false; entry.dest_mode_logical = false; entry.delivery_mode = APIC_DELIVERY_MODE_EXTINT; - entry.destid_0_7 = read_apic_id(); + entry.destid_0_7 = apic_id & 0xFF; + entry.virt_destid_8_14 = apic_id >> 8; /* * Add it to the IO-APIC irq-routing table: @@ -1911,7 +1914,11 @@ static void ioapic_setup_msg_from_msi(struct irq_data *irq_data, /* DMAR/IR: 1, 0 for all other modes */ entry->ir_format = msg.arch_addr_lo.dmar_format; /* - * DMAR/IR: index bit 0-14. + * - DMAR/IR: index bit 0-14. + * + * - Virt: If the host supports x2apic without a virtualized IR + * unit then bit 0-6 of dmar_index_0_14 are providing bit + * 8-14 of the destination id. * * All other modes have bit 0-6 of dmar_index_0_14 cleared and the * topmost 8 bits are destination id bit 0-7 (entry::destid_0_7). @@ -2091,6 +2098,7 @@ static inline void __init unlock_ExtINT_logic(void) int apic, pin, i; struct IO_APIC_route_entry entry0, entry1; unsigned char save_control, save_freq_select; + u32 apic_id; pin = find_isa_irq_pin(8, mp_INT); if (pin == -1) { @@ -2106,11 +2114,13 @@ static inline void __init unlock_ExtINT_logic(void) entry0 = ioapic_read_entry(apic, pin); clear_IO_APIC_pin(apic, pin); + apic_id = hard_smp_processor_id(); memset(&entry1, 0, sizeof(entry1)); entry1.dest_mode_logical = true; entry1.masked = false; - entry1.destid_0_7 = hard_smp_processor_id(); + entry1.destid_0_7 = apic_id & 0xFF; + entry1.virt_destid_8_14 = apic_id >> 8; entry1.delivery_mode = APIC_DELIVERY_MODE_EXTINT; entry1.active_low = entry0.active_low; entry1.is_level = false; -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit bf27ef8a77d8da38c9f35f8f6aab013a2dcf175f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/bf27ef8a77d8da38c9f35f8f6aab013a2dc... -------------------------------- If the 15-bit APIC ID support is present in emulated MSI then there's no need for the pseudo-remapping support. Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20201024213535.443185-34-dwmw2@infradead.org Signed-off-by: Liu Chao <liuchao173@huawei.com> --- drivers/iommu/hyperv-iommu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index a629a6be65c7..9438daa24fdb 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -121,6 +121,7 @@ static int __init hyperv_prepare_irq_remapping(void) int i; if (!hypervisor_is_type(X86_HYPER_MS_HYPERV) || + x86_init.hyper.msi_ext_dest_id() || !x2apic_supported()) return -ENODEV; -- 2.33.0

From: David Woodhouse <dwmw@amazon.co.uk> mainline inclusion from mainline-v5.11-rc1 commit f36a74b9345aebaf5d325380df87a54720229d18 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/f36a74b9345aebaf5d325380df87a547202... -------------------------------- In commit b643128b917 ("x86/ioapic: Use irq_find_matching_fwspec() to find remapping irqdomain") the I/O-APIC code was changed to find its parent irqdomain using irq_find_matching_fwspec(), but the key used for the lookup was wrong. It shouldn't use 'ioapic' which is the index into its own ioapics[] array. It should use the actual arbitration ID of the I/O-APIC in question, which is mpc_ioapic_id(ioapic). Fixes: b643128b917 ("x86/ioapic: Use irq_find_matching_fwspec() to find remapping irqdomain") Reported-by: lkp <oliver.sang@intel.com> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/57adf2c305cd0c5e9d860b2f3007a7e676fd0f9f.camel@inf... Signed-off-by: Liu Chao <liuchao173@huawei.com> --- arch/x86/kernel/apic/io_apic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 288e8fd7c776..58b417cad51c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2373,14 +2373,14 @@ static int mp_irqdomain_create(int ioapic) if (cfg->dev) { fn = of_node_to_fwnode(cfg->dev); } else { - fn = irq_domain_alloc_named_id_fwnode("IO-APIC", ioapic); + fn = irq_domain_alloc_named_id_fwnode("IO-APIC", mpc_ioapic_id(ioapic)); if (!fn) return -ENOMEM; } fwspec.fwnode = fn; fwspec.param_count = 1; - fwspec.param[0] = ioapic; + fwspec.param[0] = mpc_ioapic_id(ioapic); parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); if (!parent) { -- 2.33.0

From: Dexuan Cui <decui@microsoft.com> mainline inclusion from mainline-v5.11-rc1 commit 26ab12bb9d96133b7880141d68b5e01a8783de9d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC9GHN Reference: https://github.com/torvalds/linux/commit/26ab12bb9d96133b7880141d68b5e01a878... -------------------------------- commit a491bb19f728 ("iommu/hyper-v: Implement select() method on remapping irqdomain") restricted the irq_domain_ops::select() callback to match on I/O-APIC index 0, which was correct until the parameter was changed to carry the I/O APIC ID in commit f36a74b9345a. If the ID is not 0 then the match fails. Therefore I/O-APIC init fails to retrieve the parent irqdomain for the I/O-APIC resulting in a boot panic: kernel BUG at arch/x86/kernel/apic/io_apic.c:2408! Fix it by matching the I/O-APIC independent of the ID as there is only one I/O APIC emulated by Hyper-V. [ tglx: Amended changelog ] Fixes: f36a74b9345a ("x86/ioapic: Use I/O-APIC ID for finding irqdomain, not index") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: David Woodhouse <dwmw@amazon.co.uk> Link: https://lore.kernel.org/r/20201202004510.1818-1-decui@microsoft.com Signed-off-by: Liu Chao <liuchao173@huawei.com> --- drivers/iommu/hyperv-iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 9438daa24fdb..1d21a0b5f724 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -105,8 +105,8 @@ static int hyperv_irq_remapping_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token) { - /* Claim only the first (and only) I/OAPIC */ - return x86_fwspec_is_ioapic(fwspec) && fwspec->param[0] == 0; + /* Claim the only I/O APIC emulated by Hyper-V */ + return x86_fwspec_is_ioapic(fwspec); } static const struct irq_domain_ops hyperv_ir_domain_ops = { -- 2.33.0