From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753949AbaKZXJi (ORCPT ); Wed, 26 Nov 2014 18:09:38 -0500 Received: from terminus.zytor.com ([198.137.202.10]:58244 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752089AbaKZXJf (ORCPT ); Wed, 26 Nov 2014 18:09:35 -0500 Date: Wed, 26 Nov 2014 15:08:31 -0800 From: tip-bot for Jiang Liu Message-ID: Cc: gregkh@linuxfoundation.org, tglx@linutronix.de, jiang.liu@linux.intel.com, rjw@rjwysocki.net, rdunlap@infradead.org, konrad.wilk@oracle.com, joro@8bytes.org, bhelgaas@google.com, linux-kernel@vger.kernel.org, benh@kernel.crashing.org, jroedel@suse.de, tony.luck@intel.com, hpa@zytor.com, yinghai@kernel.org, mingo@kernel.org, bp@alien8.de Reply-To: yinghai@kernel.org, hpa@zytor.com, mingo@kernel.org, bp@alien8.de, benh@kernel.crashing.org, jroedel@suse.de, tony.luck@intel.com, rdunlap@infradead.org, rjw@rjwysocki.net, linux-kernel@vger.kernel.org, bhelgaas@google.com, joro@8bytes.org, konrad.wilk@oracle.com, tglx@linutronix.de, gregkh@linuxfoundation.org, jiang.liu@linux.intel.com In-Reply-To: <1416894816-23245-12-git-send-email-jiang.liu@linux.intel.com> References: <1416894816-23245-12-git-send-email-jiang.liu@linux.intel.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:x86/apic] iommu/amd: Enhance AMD IR driver to suppport hierarchy irqdomain Git-Commit-ID: ecf87b38d902dd0369e8c7039749183dfc309707 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: ecf87b38d902dd0369e8c7039749183dfc309707 Gitweb: http://git.kernel.org/tip/ecf87b38d902dd0369e8c7039749183dfc309707 Author: Jiang Liu AuthorDate: Tue, 25 Nov 2014 13:53:20 +0800 Committer: Thomas Gleixner CommitDate: Wed, 26 Nov 2014 18:59:24 +0100 iommu/amd: Enhance AMD IR driver to suppport hierarchy irqdomain Enhance AMD interrupt remapping driver to support hierarchy irqdomain, it will simplify the code eventually. Signed-off-by: Jiang Liu Acked-by: Joerg Roedel Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Greg Kroah-Hartman Cc: iommu@lists.linux-foundation.org Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Rafael J. Wysocki Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Joerg Roedel Link: http://lkml.kernel.org/r/1416894816-23245-12-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- drivers/iommu/amd_iommu.c | 329 +++++++++++++++++++++++++++++++++++++++- drivers/iommu/amd_iommu_init.c | 4 + drivers/iommu/amd_iommu_proto.h | 9 ++ drivers/iommu/amd_iommu_types.h | 5 + 4 files changed, 341 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 6fda7cc..d027423 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -3854,6 +3855,16 @@ union irte { } fields; }; +struct amd_ir_data { + struct irq_2_irte irq_2_irte; + union irte irte_entry; + union { + struct msi_msg msi_entry; + }; +}; + +static struct irq_chip amd_ir_chip; + #define DTE_IRQ_PHYS_ADDR_MASK (((1ULL << 45)-1) << 6) #define DTE_IRQ_REMAP_INTCTL (2ULL << 60) #define DTE_IRQ_TABLE_LEN (8ULL << 1) @@ -3947,7 +3958,8 @@ out_unlock: return table; } -static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count) +static int alloc_irq_index(struct irq_cfg *cfg, struct irq_2_irte *irte_info, + u16 devid, int count) { struct irq_remap_table *table; unsigned long flags; @@ -3969,15 +3981,12 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count) c = 0; if (c == count) { - struct irq_2_irte *irte_info; - for (; c != 0; --c) table->table[index - c + 1] = IRTE_ALLOCATED; index -= count - 1; cfg->remapped = 1; - irte_info = &cfg->irq_2_irte; irte_info->devid = devid; irte_info->index = index; @@ -4222,7 +4231,7 @@ static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec) return -EINVAL; devid = get_device_id(&pdev->dev); - index = alloc_irq_index(cfg, devid, nvec); + index = alloc_irq_index(cfg, &cfg->irq_2_irte, devid, nvec); return index < 0 ? MAX_IRQS_PER_TABLE : index; } @@ -4269,7 +4278,7 @@ static int alloc_hpet_msi(unsigned int irq, unsigned int id) if (devid < 0) return devid; - index = alloc_irq_index(cfg, devid, 1); + index = alloc_irq_index(cfg, &cfg->irq_2_irte, devid, 1); if (index < 0) return index; @@ -4280,6 +4289,72 @@ static int alloc_hpet_msi(unsigned int irq, unsigned int id) return 0; } +static int get_devid(struct irq_alloc_info *info) +{ + int devid = -1; + + switch (info->type) { + case X86_IRQ_ALLOC_TYPE_IOAPIC: + devid = get_ioapic_devid(info->ioapic_id); + break; + case X86_IRQ_ALLOC_TYPE_HPET: + devid = get_hpet_devid(info->hpet_id); + break; + case X86_IRQ_ALLOC_TYPE_MSI: + case X86_IRQ_ALLOC_TYPE_MSIX: + devid = get_device_id(&info->msi_dev->dev); + break; + default: + BUG_ON(1); + break; + } + + return devid; +} + +static struct irq_domain *get_ir_irq_domain(struct irq_alloc_info *info) +{ + int devid; + struct amd_iommu *iommu; + + if (!info) + return NULL; + + devid = get_devid(info); + if (devid >= 0) { + iommu = amd_iommu_rlookup_table[devid]; + if (iommu) + return iommu->ir_domain; + } + + return NULL; +} + +static struct irq_domain *get_irq_domain(struct irq_alloc_info *info) +{ + int devid; + struct amd_iommu *iommu; + + if (!info) + return NULL; + + switch (info->type) { + case X86_IRQ_ALLOC_TYPE_MSI: + case X86_IRQ_ALLOC_TYPE_MSIX: + devid = get_device_id(&info->msi_dev->dev); + if (devid >= 0) { + iommu = amd_iommu_rlookup_table[devid]; + if (iommu) + return iommu->msi_domain; + } + break; + default: + break; + } + + return NULL; +} + struct irq_remap_ops amd_iommu_irq_ops = { .supported = amd_iommu_supported, .prepare = amd_iommu_prepare, @@ -4294,5 +4369,247 @@ struct irq_remap_ops amd_iommu_irq_ops = { .msi_alloc_irq = msi_alloc_irq, .msi_setup_irq = msi_setup_irq, .alloc_hpet_msi = alloc_hpet_msi, + .get_ir_irq_domain = get_ir_irq_domain, + .get_irq_domain = get_irq_domain, +}; + +static void irq_remapping_prepare_irte(struct amd_ir_data *data, + struct irq_cfg *irq_cfg, + struct irq_alloc_info *info, + int devid, int index, int sub_handle) +{ + union irte *irte = &data->irte_entry; + struct irq_2_irte *irte_info = &data->irq_2_irte; + struct msi_msg *msg = &data->msi_entry; + struct IO_APIC_route_entry *entry; + + irq_cfg->remapped = 1; + data->irq_2_irte.devid = devid; + data->irq_2_irte.index = index + sub_handle; + + /* Setup IRTE for IOMMU */ + irte->val = 0; + irte->fields.vector = irq_cfg->vector; + irte->fields.int_type = apic->irq_delivery_mode; + irte->fields.destination = irq_cfg->dest_apicid; + irte->fields.dm = apic->irq_dest_mode; + irte->fields.valid = 1; + + 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->mask = 0; + entry->trigger = info->ioapic_trigger; + entry->polarity = info->ioapic_polarity; + /* Mask level triggered irqs. */ + if (info->ioapic_trigger) + entry->mask = 1; + break; + + case X86_IRQ_ALLOC_TYPE_HPET: + case X86_IRQ_ALLOC_TYPE_MSI: + case X86_IRQ_ALLOC_TYPE_MSIX: + msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_lo = MSI_ADDR_BASE_LO; + msg->data = irte_info->index; + break; + + default: + BUG_ON(1); + break; + } +} + +static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_alloc_info *info = arg; + struct amd_ir_data *data; + struct irq_data *irq_data; + struct irq_cfg *cfg; + int i, ret, devid; + int index = -1; + + if (!info) + return -EINVAL; + if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI && + info->type != X86_IRQ_ALLOC_TYPE_MSIX) + return -EINVAL; + + /* + * With IRQ remapping enabled, don't need contigious CPU vectors + * to support multiple MSI interrupts. + */ + if (info->type == X86_IRQ_ALLOC_TYPE_MSI) + info->flags &= ~X86_IRQ_ALLOC_CONTIGOUS_VECTORS; + + devid = get_devid(info); + if (devid < 0) + return -EINVAL; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret < 0) + return ret; + + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out_free_parent; + + if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) { + if (get_irq_table(devid, true)) + index = info->ioapic_pin; + else + ret = -ENOMEM; + } else { + cfg = irq_cfg(virq); + index = alloc_irq_index(cfg, &data->irq_2_irte, devid, nr_irqs); + } + if (index < 0) { + pr_warn("Failed to allocate IRTE\n"); + kfree(data); + goto out_free_parent; + } + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + cfg = irqd_cfg(irq_data); + if (!irq_data || !cfg) { + ret = -EINVAL; + goto out_free_data; + } + + if (i > 0) { + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out_free_data; + } + irq_data->hwirq = (devid << 16) + i; + irq_data->chip_data = data; + irq_data->chip = &amd_ir_chip; + irq_remapping_prepare_irte(data, cfg, info, devid, index, i); + irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT); + } + return 0; + +out_free_data: + for (i--; i >= 0; i--) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + if (irq_data) + kfree(irq_data->chip_data); + } + for (i = 0; i < nr_irqs; i++) + free_irte(devid, index + i); +out_free_parent: + irq_domain_free_irqs_common(domain, virq, nr_irqs); + return ret; +} + +static void irq_remapping_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *irq_data; + struct amd_ir_data *data; + struct irq_2_irte *irte_info; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + if (irq_data && irq_data->chip_data) { + data = irq_data->chip_data; + irte_info = &data->irq_2_irte; + free_irte(irte_info->devid, irte_info->index); + kfree(data); + } + } + irq_domain_free_irqs_common(domain, virq, nr_irqs); +} + +static void irq_remapping_activate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct amd_ir_data *data = irq_data->chip_data; + struct irq_2_irte *irte_info = &data->irq_2_irte; + + modify_irte(irte_info->devid, irte_info->index, data->irte_entry); +} + +static void irq_remapping_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct amd_ir_data *data = irq_data->chip_data; + struct irq_2_irte *irte_info = &data->irq_2_irte; + union irte entry; + + entry.val = 0; + modify_irte(irte_info->devid, irte_info->index, data->irte_entry); +} + +static struct irq_domain_ops amd_ir_domain_ops = { + .alloc = irq_remapping_alloc, + .free = irq_remapping_free, + .activate = irq_remapping_activate, + .deactivate = irq_remapping_deactivate, }; + +static int amd_ir_set_affinity(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct amd_ir_data *ir_data = data->chip_data; + struct irq_2_irte *irte_info = &ir_data->irq_2_irte; + struct irq_cfg *cfg = irqd_cfg(data); + struct irq_data *parent = data->parent_data; + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + + /* + * Atomically updates the IRTE with the new destination, vector + * and flushes the interrupt entry cache. + */ + ir_data->irte_entry.fields.vector = cfg->vector; + ir_data->irte_entry.fields.destination = cfg->dest_apicid; + modify_irte(irte_info->devid, irte_info->index, ir_data->irte_entry); + + /* + * After this point, all the interrupts will start arriving + * at the new destination. So, time to cleanup the previous + * vector allocation. + */ + if (cfg->move_in_progress) + send_cleanup_vector(cfg); + + return IRQ_SET_MASK_OK_DONE; +} + +static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) +{ + struct amd_ir_data *ir_data = irq_data->chip_data; + + *msg = ir_data->msi_entry; +} + +static struct irq_chip amd_ir_chip = { + .irq_ack = ir_ack_apic_edge, + .irq_set_affinity = amd_ir_set_affinity, + .irq_compose_msi_msg = ir_compose_msi_msg, +}; + +int amd_iommu_create_irq_domain(struct amd_iommu *iommu) +{ + iommu->ir_domain = irq_domain_add_tree(NULL, &amd_ir_domain_ops, iommu); + if (!iommu->ir_domain) + return -ENOMEM; + + iommu->ir_domain->parent = arch_get_ir_parent_domain(); + iommu->msi_domain = arch_create_msi_irq_domain(iommu->ir_domain); + + return 0; +} #endif diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index b0522f1..de3390a 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1124,6 +1124,10 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) if (ret) return ret; + ret = amd_iommu_create_irq_domain(iommu); + if (ret) + return ret; + /* * Make sure IOMMU is not considered to translate itself. The IVRS * table tells us so, but this is a lie! diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h index 95ed6de..612a221 100644 --- a/drivers/iommu/amd_iommu_proto.h +++ b/drivers/iommu/amd_iommu_proto.h @@ -63,6 +63,15 @@ extern u8 amd_iommu_pc_get_max_counters(u16 devid); extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, u64 *value, bool is_write); +#ifdef CONFIG_IRQ_REMAP +extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu); +#else +static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu) +{ + return 0; +} +#endif + #define PPR_SUCCESS 0x0 #define PPR_INVALID 0x1 #define PPR_FAILURE 0xf diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index cec51a8..ef12d74 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -392,6 +392,7 @@ struct amd_iommu_fault { struct iommu_domain; +struct irq_domain; /* * This structure contains generic data for IOMMU protection domains @@ -574,6 +575,10 @@ struct amd_iommu { /* The maximum PC banks and counters/bank (PCSup=1) */ u8 max_banks; u8 max_counters; +#ifdef CONFIG_IRQ_REMAP + struct irq_domain *ir_domain; + struct irq_domain *msi_domain; +#endif }; struct devid_map {