From bd6fcefc66f6d038406e38edf96a95d9842f819d Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 23 Aug 2016 13:52:37 -0500 Subject: iommu/amd: Adding GALOG interrupt handler This patch adds AMD IOMMU guest virtual APIC log (GALOG) handler. When IOMMU hardware receives an interrupt targeting a blocking vcpu, it creates an entry in the GALOG, and generates an interrupt to notify the AMD IOMMU driver. At this point, the driver processes the log entry, and notify the SVM driver via the registered iommu_ga_log_notifier function. Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- include/linux/amd-iommu.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 2b08e79f5100..465d096a5f4b 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -168,11 +168,25 @@ typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, int pasid); extern int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev, amd_iommu_invalidate_ctx cb); - -#else +#else /* CONFIG_AMD_IOMMU */ static inline int amd_iommu_detect(void) { return -ENODEV; } -#endif +#endif /* CONFIG_AMD_IOMMU */ + +#if defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) + +/* IOMMU AVIC Function */ +extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32)); + +#else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */ + +static inline int +amd_iommu_register_ga_log_notifier(int (*notifier)(u32)) +{ + return 0; +} + +#endif /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */ #endif /* _ASM_X86_AMD_IOMMU_H */ -- cgit v1.2.3 From 8dbea3fd7becd4af8ca882c3132be4b1a857e301 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 23 Aug 2016 13:52:38 -0500 Subject: iommu/amd: Introduce amd_iommu_update_ga() Introduces a new IOMMU API, amd_iommu_update_ga(), which allows KVM (SVM) to update existing posted interrupt IOMMU IRTE when load/unload vcpu. Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 39 +++++++++++++++++++++++++++++++++++++++ drivers/iommu/amd_iommu_types.h | 1 + include/linux/amd-iommu.h | 9 +++++++++ 3 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index eec37b2f54df..089e1ed4deec 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -4269,4 +4269,43 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu) return 0; } + +int amd_iommu_update_ga(int cpu, bool is_run, void *data) +{ + unsigned long flags; + struct amd_iommu *iommu; + struct irq_remap_table *irt; + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + int devid = ir_data->irq_2_irte.devid; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + struct irte_ga *ref = (struct irte_ga *) ir_data->ref; + + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || + !ref || !entry || !entry->lo.fields_vapic.guest_mode) + return 0; + + iommu = amd_iommu_rlookup_table[devid]; + if (!iommu) + return -ENODEV; + + irt = get_irq_table(devid, false); + if (!irt) + return -ENODEV; + + spin_lock_irqsave(&irt->lock, flags); + + if (ref->lo.fields_vapic.guest_mode) { + if (cpu >= 0) + ref->lo.fields_vapic.destination = cpu; + ref->lo.fields_vapic.is_run = is_run; + barrier(); + } + + spin_unlock_irqrestore(&irt->lock, flags); + + iommu_flush_irt(iommu, devid); + iommu_completion_wait(iommu); + return 0; +} +EXPORT_SYMBOL(amd_iommu_update_ga); #endif diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 8a7a93d40063..60018a8fb655 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -810,6 +810,7 @@ struct amd_ir_data { struct irq_2_irte irq_2_irte; struct msi_msg msi_entry; void *entry; /* Pointer to union irte or struct irte_ga */ + void *ref; /* Pointer to the actual irte */ }; struct amd_irte_ops { diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 465d096a5f4b..d8d48aca0eb7 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -179,6 +179,9 @@ static inline int amd_iommu_detect(void) { return -ENODEV; } /* IOMMU AVIC Function */ extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32)); +extern int +amd_iommu_update_ga(int cpu, bool is_run, void *data); + #else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */ static inline int @@ -187,6 +190,12 @@ amd_iommu_register_ga_log_notifier(int (*notifier)(u32)) return 0; } +static inline int +amd_iommu_update_ga(int cpu, bool is_run, void *data) +{ + return 0; +} + #endif /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */ #endif /* _ASM_X86_AMD_IOMMU_H */ -- cgit v1.2.3 From b9fc6b56f478b487dc8fc400da73d89ac9137201 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 23 Aug 2016 13:52:39 -0500 Subject: iommu/amd: Implements irq_set_vcpu_affinity() hook to setup vapic mode for pass-through devices This patch implements irq_set_vcpu_affinity() function to set up interrupt remapping table entry with vapic mode for pass-through devices. In case requirements for vapic mode are not met, it falls back to set up the IRTE in legacy mode. Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 68 ++++++++++++++++++++++++++++++++++++++--- drivers/iommu/amd_iommu_types.h | 1 + include/linux/amd-iommu.h | 14 +++++++++ 3 files changed, 79 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 089e1ed4deec..69fc57e0b975 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3718,7 +3718,8 @@ out: return index; } -static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte) +static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte, + struct amd_ir_data *data) { struct irq_remap_table *table; struct amd_iommu *iommu; @@ -3741,6 +3742,8 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte) entry->hi.val = irte->hi.val; entry->lo.val = irte->lo.val; entry->lo.fields_remap.valid = 1; + if (data) + data->ref = entry; spin_unlock_irqrestore(&table->lock, flags); @@ -3839,7 +3842,7 @@ static void irte_ga_activate(void *entry, u16 devid, u16 index) struct irte_ga *irte = (struct irte_ga *) entry; irte->lo.fields_remap.valid = 1; - modify_irte_ga(devid, index, irte); + modify_irte_ga(devid, index, irte, NULL); } static void irte_deactivate(void *entry, u16 devid, u16 index) @@ -3855,7 +3858,7 @@ static void irte_ga_deactivate(void *entry, u16 devid, u16 index) struct irte_ga *irte = (struct irte_ga *) entry; irte->lo.fields_remap.valid = 0; - modify_irte_ga(devid, index, irte); + modify_irte_ga(devid, index, irte, NULL); } static void irte_set_affinity(void *entry, u16 devid, u16 index, @@ -3876,7 +3879,7 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index, irte->hi.fields.vector = vector; irte->lo.fields_remap.destination = dest_apicid; irte->lo.fields_remap.guest_mode = 0; - modify_irte_ga(devid, index, irte); + modify_irte_ga(devid, index, irte, NULL); } #define IRTE_ALLOCATED (~1U) @@ -4211,6 +4214,62 @@ static struct irq_domain_ops amd_ir_domain_ops = { .deactivate = irq_remapping_deactivate, }; +static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) +{ + struct amd_iommu *iommu; + struct amd_iommu_pi_data *pi_data = vcpu_info; + struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data; + struct amd_ir_data *ir_data = data->chip_data; + struct irte_ga *irte = (struct irte_ga *) ir_data->entry; + struct irq_2_irte *irte_info = &ir_data->irq_2_irte; + + pi_data->ir_data = ir_data; + + /* Note: + * SVM tries to set up for VAPIC mode, but we are in + * legacy mode. So, we force legacy mode instead. + */ + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) { + pr_debug("AMD-Vi: %s: Fall back to using intr legacy remap\n", + __func__); + pi_data->is_guest_mode = false; + } + + iommu = amd_iommu_rlookup_table[irte_info->devid]; + if (iommu == NULL) + return -EINVAL; + + pi_data->prev_ga_tag = ir_data->cached_ga_tag; + if (pi_data->is_guest_mode) { + /* Setting */ + irte->hi.fields.ga_root_ptr = (pi_data->base >> 12); + irte->hi.fields.vector = vcpu_pi_info->vector; + irte->lo.fields_vapic.guest_mode = 1; + irte->lo.fields_vapic.ga_tag = pi_data->ga_tag; + + ir_data->cached_ga_tag = pi_data->ga_tag; + } else { + /* Un-Setting */ + struct irq_cfg *cfg = irqd_cfg(data); + + irte->hi.val = 0; + irte->lo.val = 0; + irte->hi.fields.vector = cfg->vector; + irte->lo.fields_remap.guest_mode = 0; + irte->lo.fields_remap.destination = cfg->dest_apicid; + irte->lo.fields_remap.int_type = apic->irq_delivery_mode; + irte->lo.fields_remap.dm = apic->irq_dest_mode; + + /* + * This communicates the ga_tag back to the caller + * so that it can do all the necessary clean up. + */ + ir_data->cached_ga_tag = 0; + } + + return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data); +} + static int amd_ir_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -4255,6 +4314,7 @@ static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) static struct irq_chip amd_ir_chip = { .irq_ack = ir_ack_apic_edge, .irq_set_affinity = amd_ir_set_affinity, + .irq_set_vcpu_affinity = amd_ir_set_vcpu_affinity, .irq_compose_msi_msg = ir_compose_msi_msg, }; diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 60018a8fb655..79e91e68ee76 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -807,6 +807,7 @@ struct irq_2_irte { }; struct amd_ir_data { + u32 cached_ga_tag; struct irq_2_irte irq_2_irte; struct msi_msg msi_entry; void *entry; /* Pointer to union irte or struct irte_ga */ diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index d8d48aca0eb7..09751d349963 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -22,6 +22,20 @@ #include +/* + * This is mainly used to communicate information back-and-forth + * between SVM and IOMMU for setting up and tearing down posted + * interrupt + */ +struct amd_iommu_pi_data { + u32 ga_tag; + u32 prev_ga_tag; + u64 base; + bool is_guest_mode; + struct vcpu_data *vcpu_data; + void *ir_data; +}; + #ifdef CONFIG_AMD_IOMMU struct task_struct; -- cgit v1.2.3 From 235539b48a2357da28f52d66d04bec04f3dcb9dd Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Wed, 7 Sep 2016 14:47:23 -0400 Subject: kvm: add stubs for arch specific debugfs support Two stubs are added: o kvm_arch_has_vcpu_debugfs(): must return true if the arch supports creating debugfs entries in the vcpu debugfs dir (which will be implemented by the next commit) o kvm_arch_create_vcpu_debugfs(): code that creates debugfs entries in the vcpu debugfs dir For x86, this commit introduces a new file to avoid growing arch/x86/kvm/x86.c even more. Signed-off-by: Luiz Capitulino Signed-off-by: Paolo Bonzini --- arch/arm/kvm/arm.c | 10 ++++++++++ arch/mips/kvm/mips.c | 10 ++++++++++ arch/powerpc/kvm/powerpc.c | 10 ++++++++++ arch/s390/kvm/kvm-s390.c | 10 ++++++++++ arch/x86/kvm/Makefile | 2 +- arch/x86/kvm/debugfs.c | 20 ++++++++++++++++++++ include/linux/kvm_host.h | 3 +++ 7 files changed, 64 insertions(+), 1 deletion(-) create mode 100644 arch/x86/kvm/debugfs.c (limited to 'include/linux') diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 75f130ef6504..c638935baad6 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -144,6 +144,16 @@ out_fail_alloc: return ret; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index a6ea084b4d9d..49b25e74d0c7 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -140,6 +140,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + void kvm_mips_free_vcpus(struct kvm *kvm) { unsigned int i; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 0b7d66422650..70963c845e96 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -438,6 +438,16 @@ err_out: return -EINVAL; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + void kvm_arch_destroy_vm(struct kvm *kvm) { unsigned int i; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ac6c056df4b9..0a9ce9dd7825 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1489,6 +1489,16 @@ out_err: return rc; } +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 3, "%s", "free cpu"); diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 464fa477afbf..3bff20710471 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -13,7 +13,7 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o page_track.o + hyperv.o page_track.o debugfs.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c new file mode 100644 index 000000000000..bb5e9f635dde --- /dev/null +++ b/arch/x86/kvm/debugfs.c @@ -0,0 +1,20 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * Copyright 2016 Red Hat, Inc. and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#include + +bool kvm_arch_has_vcpu_debugfs(void) +{ + return false; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9c28b4d4c90b..5486ff9aa71e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -749,6 +749,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); +bool kvm_arch_has_vcpu_debugfs(void); +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu); + int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); int kvm_arch_hardware_setup(void); -- cgit v1.2.3 From 45b5939e50746b92fd4cb47c02524f79ba8fabe6 Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Fri, 16 Sep 2016 10:27:35 -0400 Subject: kvm: create per-vcpu dirs in debugfs This commit adds the ability for archs to export per-vcpu information via a new per-vcpu dir in the VM's debugfs directory. If kvm_arch_has_vcpu_debugfs() returns true, then KVM will create a vcpu dir for each vCPU in the VM's debugfs directory. Then kvm_arch_create_vcpu_debugfs() is responsible for populating each vcpu directory with arch specific entries. The per-vcpu path in debugfs will look like: /sys/kernel/debug/kvm/29162-10/vcpu0 /sys/kernel/debug/kvm/29162-10/vcpu1 This is all arch specific for now because the only user of this interface (x86) wants to export x86-specific per-vcpu information to user-space. Signed-off-by: Luiz Capitulino Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5486ff9aa71e..01c0b9cc3915 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -265,6 +265,7 @@ struct kvm_vcpu { #endif bool preempted; struct kvm_vcpu_arch arch; + struct dentry *debugfs_dentry; }; static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a6e864c67e35..81dfc73d3df3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2371,6 +2371,7 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp) { struct kvm_vcpu *vcpu = filp->private_data; + debugfs_remove_recursive(vcpu->debugfs_dentry); kvm_put_kvm(vcpu->kvm); return 0; } @@ -2393,6 +2394,32 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu) return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } +static int kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + char dir_name[ITOA_MAX_LEN * 2]; + int ret; + + if (!kvm_arch_has_vcpu_debugfs()) + return 0; + + if (!debugfs_initialized()) + return 0; + + snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id); + vcpu->debugfs_dentry = debugfs_create_dir(dir_name, + vcpu->kvm->debugfs_dentry); + if (!vcpu->debugfs_dentry) + return -ENOMEM; + + ret = kvm_arch_create_vcpu_debugfs(vcpu); + if (ret < 0) { + debugfs_remove_recursive(vcpu->debugfs_dentry); + return ret; + } + + return 0; +} + /* * Creates some virtual cpus. Good luck creating more than one. */ @@ -2425,6 +2452,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) if (r) goto vcpu_destroy; + r = kvm_create_vcpu_debugfs(vcpu); + if (r) + goto vcpu_destroy; + mutex_lock(&kvm->lock); if (kvm_get_vcpu_by_id(kvm, id)) { r = -EEXIST; @@ -2456,6 +2487,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) unlock_vcpu_destroy: mutex_unlock(&kvm->lock); + debugfs_remove_recursive(vcpu->debugfs_dentry); vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); vcpu_decrement: -- cgit v1.2.3