Re: [PATCH V3 2/3] HYPERV/IOMMU: Add Hyper-V stub IOMMU driver

[Vitaly Kuznetsov <vkuznets@redhat.com>]

lantianyu1986@gmail.com writes:

> From: Lan Tianyu <Tianyu.Lan@microsoft.com>
>
> On the bare metal, enabling X2APIC mode requires interrupt remapping
> function which helps to deliver irq to cpu with 32-bit APIC ID.
> Hyper-V doesn't provide interrupt remapping function so far and Hyper-V
> MSI protocol already supports to deliver interrupt to the CPU whose
> virtual processor index is more than 255. IO-APIC interrupt still has
> 8-bit APIC ID limitation.
>
> This patch is to add Hyper-V stub IOMMU driver in order to enable
> X2APIC mode successfully in Hyper-V Linux guest. The driver returns X2APIC
> interrupt remapping capability when X2APIC mode is available. Otherwise,
> it creates a Hyper-V irq domain to limit IO-APIC interrupts' affinity
> and make sure cpus assigned with IO-APIC interrupt have 8-bit APIC ID.
>
> Define 24 IO-APIC remapping entries because Hyper-V only expose one
> single IO-APIC and one IO-APIC has 24 pins according IO-APIC spec(
> https://pdos.csail.mit.edu/6.828/2016/readings/ia32/ioapic.pdf).
>
> Signed-off-by: Lan Tianyu <Tianyu.Lan@microsoft.com>
> ---
> Change since v2:
>        - Improve comment about why save IO-APIC entry in the irq chip data.
>        - Some code improvement.
>        - Improve statement in the IOMMU Kconfig.
>
> Change since v1:
>       - Remove unused pr_fmt
>       - Make ioapic_ir_domain as static variable
>       - Remove unused variables cfg and entry in the hyperv_irq_remapping_alloc()
>       - Fix comments
> ---
>  drivers/iommu/Kconfig         |   8 ++
>  drivers/iommu/Makefile        |   1 +
>  drivers/iommu/hyperv-iommu.c  | 194 ++++++++++++++++++++++++++++++++++++++++++
>  drivers/iommu/irq_remapping.c |   3 +
>  drivers/iommu/irq_remapping.h |   1 +
>  5 files changed, 207 insertions(+)
>  create mode 100644 drivers/iommu/hyperv-iommu.c
>
> diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
> index 45d7021..6090935 100644
> --- a/drivers/iommu/Kconfig
> +++ b/drivers/iommu/Kconfig
> @@ -437,4 +437,12 @@ config QCOM_IOMMU
>  	help
>  	  Support for IOMMU on certain Qualcomm SoCs.
>  
> +config HYPERV_IOMMU
> +	bool "Hyper-V x2APIC IRQ Handling"
> +	depends on HYPERV
> +	select IOMMU_API
> +	help
> +	  Stub IOMMU driver to handle IRQs as to allow Hyper-V Linux
> +	  guests to run with x2APIC mode enabled.
> +
>  endif # IOMMU_SUPPORT
> diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
> index a158a68..8c71a15 100644
> --- a/drivers/iommu/Makefile
> +++ b/drivers/iommu/Makefile
> @@ -32,3 +32,4 @@ obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o
>  obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
>  obj-$(CONFIG_S390_IOMMU) += s390-iommu.o
>  obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o
> +obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
> diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
> new file mode 100644
> index 0000000..d8572c5
> --- /dev/null
> +++ b/drivers/iommu/hyperv-iommu.c
> @@ -0,0 +1,194 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +/*
> + * Hyper-V stub IOMMU driver.
> + *
> + * Copyright (C) 2019, Microsoft, Inc.
> + *
> + * Author : Lan Tianyu <Tianyu.Lan@microsoft.com>
> + */
> +
> +#include <linux/types.h>
> +#include <linux/interrupt.h>
> +#include <linux/irq.h>
> +#include <linux/iommu.h>
> +#include <linux/module.h>
> +
> +#include <asm/hw_irq.h>
> +#include <asm/io_apic.h>
> +#include <asm/irq_remapping.h>
> +#include <asm/hypervisor.h>
> +
> +#include "irq_remapping.h"
> +
> +#ifdef CONFIG_IRQ_REMAP
> +
> +/*
> + * According 82093AA IO-APIC spec , IO APIC has a 24-entry Interrupt
> + * Redirection Table. Hyper-V exposes one single IO-APIC and so define
> + * 24 IO APIC remmapping entries.
> + */
> +#define IOAPIC_REMAPPING_ENTRY 24
> +
> +static cpumask_t ioapic_max_cpumask = { CPU_BITS_NONE };
> +static struct irq_domain *ioapic_ir_domain;
> +
> +static int hyperv_ir_set_affinity(struct irq_data *data,
> +		const struct cpumask *mask, bool force)
> +{
> +	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. */
> +	if (!cpumask_subset(mask, &ioapic_max_cpumask))
> +		return -EINVAL;
> +
> +	ret = parent->chip->irq_set_affinity(parent, mask, force);
> +	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
> +		return ret;
> +
> +	entry = data->chip_data;
> +	entry->dest = cfg->dest_apicid;
> +	entry->vector = cfg->vector;
> +	send_cleanup_vector(cfg);
> +
> +	return 0;
> +}
> +
> +static struct irq_chip hyperv_ir_chip = {
> +	.name			= "HYPERV-IR",
> +	.irq_ack		= apic_ack_irq,
> +	.irq_set_affinity	= hyperv_ir_set_affinity,
> +};
> +
> +static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
> +				     unsigned int virq, unsigned int nr_irqs,
> +				     void *arg)
> +{
> +	struct irq_alloc_info *info = arg;
> +	struct irq_data *irq_data;
> +	struct irq_desc *desc;
> +	int ret = 0;
> +
> +	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
> +		return -EINVAL;
> +
> +	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
> +	if (ret < 0)
> +		return ret;
> +
> +	irq_data = irq_domain_get_irq_data(domain, virq);
> +	if (!irq_data) {
> +		irq_domain_free_irqs_common(domain, virq, nr_irqs);
> +		return -EINVAL;
> +	}
> +
> +	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.
> +	 */
> +	desc = irq_data_to_desc(irq_data);
> +	cpumask_copy(desc->irq_common_data.affinity, &ioapic_max_cpumask);
> +
> +	return 0;
> +}
> +
> +static void hyperv_irq_remapping_free(struct irq_domain *domain,
> +				 unsigned int virq, unsigned int nr_irqs)
> +{
> +	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->dest = cfg->dest_apicid;
> +	entry->vector = cfg->vector;
> +
> +	return 0;
> +}
> +
> +static 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)
> +{
> +	struct fwnode_handle *fn;
> +	int i;
> +
> +	if (!hypervisor_is_type(x86_hyper_type) ||

I think this should be 

if (hypervisor_is_type(X86_HYPER_MS_HYPERV))

> +	    !x2apic_supported())
> +		return -ENODEV;
> +
> +	fn = irq_domain_alloc_named_id_fwnode("HYPERV-IR", 0);
> +	if (!fn)
> +		return -ENOMEM;
> +
> +	ioapic_ir_domain =
> +		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
> +				0, IOAPIC_REMAPPING_ENTRY, fn,
> +				&hyperv_ir_domain_ops, NULL);
> +
> +	irq_domain_free_fwnode(fn);
> +
> +	/*
> +	 * Hyper-V doesn't provide irq remapping function for
> +	 * IO-APIC and so IO-APIC only accepts 8-bit APIC ID.
> +	 * Cpu's APIC ID is read from ACPI MADT table and APIC IDs
> +	 * in the MADT table on Hyper-v are sorted monotonic increasingly.
> +	 * APIC ID reflects cpu topology. There maybe some APIC ID
> +	 * gaps when cpu number in a socket is not power of two. Prepare
> +	 * max cpu affinity for IOAPIC irqs. Scan cpu 0-255 and set cpu
> +	 * into ioapic_max_cpumask if its APIC ID is less than 256.
> +	 */
> +	for (i = 0; i < 256; i++)
> +		if (cpu_physical_id(i) < 256)
> +			cpumask_set_cpu(i, &ioapic_max_cpumask);
> +
> +	return 0;
> +}
> +
> +static int __init hyperv_enable_irq_remapping(void)
> +{
> +	return IRQ_REMAP_X2APIC_MODE;
> +}
> +
> +static struct irq_domain *hyperv_get_ir_irq_domain(struct irq_alloc_info *info)
> +{
> +	if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC)
> +		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_ir_irq_domain	= hyperv_get_ir_irq_domain,
> +};
> +
> +#endif
> diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
> index b94ebd4..81cf290 100644
> --- a/drivers/iommu/irq_remapping.c
> +++ b/drivers/iommu/irq_remapping.c
> @@ -103,6 +103,9 @@ int __init irq_remapping_prepare(void)
>  	else if (IS_ENABLED(CONFIG_AMD_IOMMU) &&
>  		 amd_iommu_irq_ops.prepare() == 0)
>  		remap_ops = &amd_iommu_irq_ops;
> +	else if (IS_ENABLED(CONFIG_HYPERV_IOMMU) &&
> +		 hyperv_irq_remap_ops.prepare() == 0)
> +		remap_ops = &hyperv_irq_remap_ops;
>  	else
>  		return -ENOSYS;
>  
> diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
> index 0afef6e..f8609e9 100644
> --- a/drivers/iommu/irq_remapping.h
> +++ b/drivers/iommu/irq_remapping.h
> @@ -64,6 +64,7 @@ struct irq_remap_ops {
>  
>  extern struct irq_remap_ops intel_irq_remap_ops;
>  extern struct irq_remap_ops amd_iommu_irq_ops;
> +extern struct irq_remap_ops hyperv_irq_remap_ops;
>  
>  #else  /* CONFIG_IRQ_REMAP */

-- 
Vitaly