diff options
Diffstat (limited to 'drivers/iommu/intel/irq_remapping.c')
-rw-r--r-- | drivers/iommu/intel/irq_remapping.c | 129 |
1 files changed, 117 insertions, 12 deletions
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 0f64fa72ac4f..e4a70886678c 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -19,9 +19,11 @@ #include <asm/cpu.h> #include <asm/irq_remapping.h> #include <asm/pci-direct.h> +#include <asm/posted_intr.h> #include "iommu.h" #include "../irq_remapping.h" +#include "../iommu-pages.h" #include "cap_audit.h" enum irq_mode { @@ -49,6 +51,7 @@ struct irq_2_iommu { u16 sub_handle; u8 irte_mask; enum irq_mode mode; + bool posted_msi; }; struct intel_ir_data { @@ -527,7 +530,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) struct ir_table *ir_table; struct fwnode_handle *fn; unsigned long *bitmap; - struct page *pages; + void *ir_table_base; if (iommu->ir_table) return 0; @@ -536,9 +539,9 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) if (!ir_table) return -ENOMEM; - pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, - INTR_REMAP_PAGE_ORDER); - if (!pages) { + ir_table_base = iommu_alloc_pages_node(iommu->node, GFP_KERNEL, + INTR_REMAP_PAGE_ORDER); + if (!ir_table_base) { pr_err("IR%d: failed to allocate pages of order %d\n", iommu->seq_id, INTR_REMAP_PAGE_ORDER); goto out_free_table; @@ -569,7 +572,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) IRQ_DOMAIN_FLAG_ISOLATED_MSI; iommu->ir_domain->msi_parent_ops = &dmar_msi_parent_ops; - ir_table->base = page_address(pages); + ir_table->base = ir_table_base; ir_table->bitmap = bitmap; iommu->ir_table = ir_table; @@ -618,7 +621,7 @@ out_free_fwnode: out_free_bitmap: bitmap_free(bitmap); out_free_pages: - __free_pages(pages, INTR_REMAP_PAGE_ORDER); + iommu_free_pages(ir_table_base, INTR_REMAP_PAGE_ORDER); out_free_table: kfree(ir_table); @@ -639,8 +642,7 @@ static void intel_teardown_irq_remapping(struct intel_iommu *iommu) irq_domain_free_fwnode(fn); iommu->ir_domain = NULL; } - free_pages((unsigned long)iommu->ir_table->base, - INTR_REMAP_PAGE_ORDER); + iommu_free_pages(iommu->ir_table->base, INTR_REMAP_PAGE_ORDER); bitmap_free(iommu->ir_table->bitmap); kfree(iommu->ir_table); iommu->ir_table = NULL; @@ -1114,6 +1116,14 @@ static void prepare_irte(struct irte *irte, int vector, unsigned int dest) irte->redir_hint = 1; } +static void prepare_irte_posted(struct irte *irte) +{ + memset(irte, 0, sizeof(*irte)); + + irte->present = 1; + irte->p_pst = 1; +} + struct irq_remap_ops intel_irq_remap_ops = { .prepare = intel_prepare_irq_remapping, .enable = intel_enable_irq_remapping, @@ -1122,6 +1132,47 @@ struct irq_remap_ops intel_irq_remap_ops = { .enable_faulting = enable_drhd_fault_handling, }; +#ifdef CONFIG_X86_POSTED_MSI + +static phys_addr_t get_pi_desc_addr(struct irq_data *irqd) +{ + int cpu = cpumask_first(irq_data_get_effective_affinity_mask(irqd)); + + if (WARN_ON(cpu >= nr_cpu_ids)) + return 0; + + return __pa(per_cpu_ptr(&posted_msi_pi_desc, cpu)); +} + +static void intel_ir_reconfigure_irte_posted(struct irq_data *irqd) +{ + struct intel_ir_data *ir_data = irqd->chip_data; + struct irte *irte = &ir_data->irte_entry; + struct irte irte_pi; + u64 pid_addr; + + pid_addr = get_pi_desc_addr(irqd); + + if (!pid_addr) { + pr_warn("Failed to setup IRQ %d for posted mode", irqd->irq); + return; + } + + memset(&irte_pi, 0, sizeof(irte_pi)); + + /* The shared IRTE already be set up as posted during alloc_irte */ + dmar_copy_shared_irte(&irte_pi, irte); + + irte_pi.pda_l = (pid_addr >> (32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT); + irte_pi.pda_h = (pid_addr >> 32) & ~(-1UL << PDA_HIGH_BIT); + + modify_irte(&ir_data->irq_2_iommu, &irte_pi); +} + +#else +static inline void intel_ir_reconfigure_irte_posted(struct irq_data *irqd) {} +#endif + static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force) { struct intel_ir_data *ir_data = irqd->chip_data; @@ -1135,8 +1186,9 @@ static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force) irte->vector = cfg->vector; irte->dest_id = IRTE_DEST(cfg->dest_apicid); - /* Update the hardware only if the interrupt is in remapped mode. */ - if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING) + if (ir_data->irq_2_iommu.posted_msi) + intel_ir_reconfigure_irte_posted(irqd); + else if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING) modify_irte(&ir_data->irq_2_iommu, irte); } @@ -1190,7 +1242,7 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info) struct intel_ir_data *ir_data = data->chip_data; struct vcpu_data *vcpu_pi_info = info; - /* stop posting interrupts, back to remapping mode */ + /* stop posting interrupts, back to the default mode */ if (!vcpu_pi_info) { modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry); } else { @@ -1229,6 +1281,49 @@ static struct irq_chip intel_ir_chip = { .irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity, }; +/* + * With posted MSIs, all vectors are multiplexed into a single notification + * vector. Devices MSIs are then dispatched in a demux loop where + * EOIs can be coalesced as well. + * + * "INTEL-IR-POST" IRQ chip does not do EOI on ACK, thus the dummy irq_ack() + * function. Instead EOI is performed by the posted interrupt notification + * handler. + * + * For the example below, 3 MSIs are coalesced into one CPU notification. Only + * one apic_eoi() is needed. + * + * __sysvec_posted_msi_notification() + * irq_enter(); + * handle_edge_irq() + * irq_chip_ack_parent() + * dummy(); // No EOI + * handle_irq_event() + * driver_handler() + * handle_edge_irq() + * irq_chip_ack_parent() + * dummy(); // No EOI + * handle_irq_event() + * driver_handler() + * handle_edge_irq() + * irq_chip_ack_parent() + * dummy(); // No EOI + * handle_irq_event() + * driver_handler() + * apic_eoi() + * irq_exit() + */ + +static void dummy_ack(struct irq_data *d) { } + +static struct irq_chip intel_ir_chip_post_msi = { + .name = "INTEL-IR-POST", + .irq_ack = dummy_ack, + .irq_set_affinity = intel_ir_set_affinity, + .irq_compose_msi_msg = intel_ir_compose_msi_msg, + .irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity, +}; + static void fill_msi_msg(struct msi_msg *msg, u32 index, u32 subhandle) { memset(msg, 0, sizeof(*msg)); @@ -1270,6 +1365,11 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data, break; case X86_IRQ_ALLOC_TYPE_PCI_MSI: case X86_IRQ_ALLOC_TYPE_PCI_MSIX: + if (posted_msi_supported()) { + prepare_irte_posted(irte); + data->irq_2_iommu.posted_msi = 1; + } + set_msi_sid(irte, pci_real_dma_dev(msi_desc_to_pci_dev(info->desc))); break; @@ -1357,7 +1457,12 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain, irq_data->hwirq = (index << 16) + i; irq_data->chip_data = ird; - irq_data->chip = &intel_ir_chip; + if (posted_msi_supported() && + ((info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) || + (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSIX))) + irq_data->chip = &intel_ir_chip_post_msi; + else + irq_data->chip = &intel_ir_chip; intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i); irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT); } |