Re: [PATCH v14 23/25] virt: gunyah: Add irqfd interface

[Alex Elder]

On 6/13/23 12:20 PM, Elliot Berman wrote:
> Enable support for creating irqfds which can raise an interrupt on a
> Gunyah virtual machine. irqfds are exposed to userspace as a Gunyah VM
> function with the name "irqfd". If the VM devicetree is not configured
> to create a doorbell with the corresponding label, userspace will still
> be able to assert the eventfd but no interrupt will be raised on the
> guest.
>
> Acked-by: Alex Elder <elder@xxxxxxxxxx>

I guess I don't mind upgrading this.  It looks good to me.

Reviewed-by: Alex Elder <elder@xxxxxxxxxx>

> Co-developed-by: Prakruthi Deepak Heragu <quic_pheragu@xxxxxxxxxxx>
> Signed-off-by: Prakruthi Deepak Heragu <quic_pheragu@xxxxxxxxxxx>
> Signed-off-by: Elliot Berman <quic_eberman@xxxxxxxxxxx>
> ---
>   Documentation/virt/gunyah/vm-manager.rst |   2 +-
>   drivers/virt/gunyah/Kconfig              |   9 ++
>   drivers/virt/gunyah/Makefile             |   1 +
>   drivers/virt/gunyah/gunyah_irqfd.c       | 180 +++++++++++++++++++++++
>   include/uapi/linux/gunyah.h              |  35 +++++
>   5 files changed, 226 insertions(+), 1 deletion(-)
>   create mode 100644 drivers/virt/gunyah/gunyah_irqfd.c
>
> diff --git a/Documentation/virt/gunyah/vm-manager.rst b/Documentation/virt/gunyah/vm-manager.rst
> index b0c3bde105ae9..57a254827be26 100644
> --- a/Documentation/virt/gunyah/vm-manager.rst
> +++ b/Documentation/virt/gunyah/vm-manager.rst
> @@ -116,7 +116,7 @@ the VM *before* the VM starts.
>   The argument types are documented below:
>   
>   .. kernel-doc:: include/uapi/linux/gunyah.h
> -   :identifiers: gh_fn_vcpu_arg
> +   :identifiers: gh_fn_vcpu_arg gh_fn_irqfd_arg gh_irqfd_flags
>   
>   Gunyah VCPU API Descriptions
>   ----------------------------
> diff --git a/drivers/virt/gunyah/Kconfig b/drivers/virt/gunyah/Kconfig
> index 0a58395f7d2c5..bc2c46d9df946 100644
> --- a/drivers/virt/gunyah/Kconfig
> +++ b/drivers/virt/gunyah/Kconfig
> @@ -39,3 +39,12 @@ config GUNYAH_VCPU
>   	  VMMs can also handle stage 2 faults of the vCPUs.
>   
>   	  Say Y/M here if unsure and you want to support Gunyah VMMs.
> +
> +config GUNYAH_IRQFD
> +	tristate "Gunyah irqfd interface"
> +	depends on GUNYAH
> +	help
> +	  Enable kernel support for creating irqfds which can raise an interrupt
> +	  on Gunyah virtual machine.
> +
> +	  Say Y/M here if unsure and you want to support Gunyah VMMs.
> diff --git a/drivers/virt/gunyah/Makefile b/drivers/virt/gunyah/Makefile
> index cc16b6c19db92..ad212a1cf9671 100644
> --- a/drivers/virt/gunyah/Makefile
> +++ b/drivers/virt/gunyah/Makefile
> @@ -7,3 +7,4 @@ gunyah-y += rsc_mgr.o rsc_mgr_rpc.o vm_mgr.o vm_mgr_mm.o
>   obj-$(CONFIG_GUNYAH) += gunyah.o
>   
>   obj-$(CONFIG_GUNYAH_VCPU) += gunyah_vcpu.o
> +obj-$(CONFIG_GUNYAH_IRQFD) += gunyah_irqfd.o
> diff --git a/drivers/virt/gunyah/gunyah_irqfd.c b/drivers/virt/gunyah/gunyah_irqfd.c
> new file mode 100644
> index 0000000000000..3e954ebd20297
> --- /dev/null
> +++ b/drivers/virt/gunyah/gunyah_irqfd.c
> @@ -0,0 +1,180 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
> + */
> +
> +#include <linux/eventfd.h>
> +#include <linux/file.h>
> +#include <linux/fs.h>
> +#include <linux/gunyah.h>
> +#include <linux/gunyah_vm_mgr.h>
> +#include <linux/module.h>
> +#include <linux/poll.h>
> +#include <linux/printk.h>
> +
> +#include <uapi/linux/gunyah.h>
> +
> +struct gh_irqfd {
> +	struct gh_resource *ghrsc;
> +	struct gh_vm_resource_ticket ticket;
> +	struct gh_vm_function_instance *f;
> +
> +	bool level;
> +
> +	struct eventfd_ctx *ctx;
> +	wait_queue_entry_t wait;
> +	poll_table pt;
> +};
> +
> +static int irqfd_wakeup(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key)
> +{
> +	struct gh_irqfd *irqfd = container_of(wait, struct gh_irqfd, wait);
> +	__poll_t flags = key_to_poll(key);
> +	int ret = 0;
> +
> +	if (flags & EPOLLIN) {
> +		if (irqfd->ghrsc) {
> +			ret = gh_hypercall_bell_send(irqfd->ghrsc->capid, 1, NULL);
> +			if (ret)
> +				pr_err_ratelimited("Failed to inject interrupt %d: %d\n",
> +						irqfd->ticket.label, ret);
> +		} else
> +			pr_err_ratelimited("Premature injection of interrupt\n");
> +	}
> +
> +	return 0;
> +}
> +
> +static void irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh, poll_table *pt)
> +{
> +	struct gh_irqfd *irq_ctx = container_of(pt, struct gh_irqfd, pt);
> +
> +	add_wait_queue(wqh, &irq_ctx->wait);
> +}
> +
> +static bool gh_irqfd_populate(struct gh_vm_resource_ticket *ticket, struct gh_resource *ghrsc)
> +{
> +	struct gh_irqfd *irqfd = container_of(ticket, struct gh_irqfd, ticket);
> +	int ret;
> +
> +	if (irqfd->ghrsc) {
> +		pr_warn("irqfd%d already got a Gunyah resource. Check if multiple resources with same label were configured.\n",
> +			irqfd->ticket.label);
> +		return false;
> +	}
> +
> +	irqfd->ghrsc = ghrsc;
> +	if (irqfd->level) {
> +		/* Configure the bell to trigger when bit 0 is asserted (see
> +		 * irq_wakeup) and for bell to automatically clear bit 0 once
> +		 * received by the VM (ack_mask).  need to make sure bit 0 is cleared right away,
> +		 * otherwise the line will never be deasserted. Emulating edge
> +		 * trigger interrupt does not need to set either mask
> +		 * because irq is listed only once per gh_hypercall_bell_send
> +		 */
> +		ret = gh_hypercall_bell_set_mask(irqfd->ghrsc->capid, 1, 1);
> +		if (ret)
> +			pr_warn("irq %d couldn't be set as level triggered. Might cause IRQ storm if asserted\n",
> +				irqfd->ticket.label);
> +	}
> +
> +	return true;
> +}
> +
> +static void gh_irqfd_unpopulate(struct gh_vm_resource_ticket *ticket, struct gh_resource *ghrsc)
> +{
> +	struct gh_irqfd *irqfd = container_of(ticket, struct gh_irqfd, ticket);
> +	u64 cnt;
> +
> +	eventfd_ctx_remove_wait_queue(irqfd->ctx, &irqfd->wait, &cnt);
> +}
> +
> +static long gh_irqfd_bind(struct gh_vm_function_instance *f)
> +{
> +	struct gh_fn_irqfd_arg *args = f->argp;
> +	struct gh_irqfd *irqfd;
> +	__poll_t events;
> +	struct fd fd;
> +	long r;
> +
> +	if (f->arg_size != sizeof(*args))
> +		return -EINVAL;
> +
> +	/* All other flag bits are reserved for future use */
> +	if (args->flags & ~GH_IRQFD_FLAGS_LEVEL)
> +		return -EINVAL;
> +
> +	irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
> +	if (!irqfd)
> +		return -ENOMEM;
> +
> +	irqfd->f = f;
> +	f->data = irqfd;
> +
> +	fd = fdget(args->fd);
> +	if (!fd.file) {
> +		kfree(irqfd);
> +		return -EBADF;
> +	}
> +
> +	irqfd->ctx = eventfd_ctx_fileget(fd.file);
> +	if (IS_ERR(irqfd->ctx)) {
> +		r = PTR_ERR(irqfd->ctx);
> +		goto err_fdput;
> +	}
> +
> +	if (args->flags & GH_IRQFD_FLAGS_LEVEL)
> +		irqfd->level = true;
> +
> +	init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
> +	init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);
> +
> +	irqfd->ticket.resource_type = GH_RESOURCE_TYPE_BELL_TX;
> +	irqfd->ticket.label = args->label;
> +	irqfd->ticket.owner = THIS_MODULE;
> +	irqfd->ticket.populate = gh_irqfd_populate;
> +	irqfd->ticket.unpopulate = gh_irqfd_unpopulate;
> +
> +	r = gh_vm_add_resource_ticket(f->ghvm, &irqfd->ticket);
> +	if (r)
> +		goto err_ctx;
> +
> +	events = vfs_poll(fd.file, &irqfd->pt);
> +	if (events & EPOLLIN)
> +		pr_warn("Premature injection of interrupt\n");
> +	fdput(fd);
> +
> +	return 0;
> +err_ctx:
> +	eventfd_ctx_put(irqfd->ctx);
> +err_fdput:
> +	fdput(fd);
> +	kfree(irqfd);
> +	return r;
> +}
> +
> +static void gh_irqfd_unbind(struct gh_vm_function_instance *f)
> +{
> +	struct gh_irqfd *irqfd = f->data;
> +
> +	gh_vm_remove_resource_ticket(irqfd->f->ghvm, &irqfd->ticket);
> +	eventfd_ctx_put(irqfd->ctx);
> +	kfree(irqfd);
> +}
> +
> +static bool gh_irqfd_compare(const struct gh_vm_function_instance *f,
> +				const void *arg, size_t size)
> +{
> +	const struct gh_fn_irqfd_arg *instance = f->argp,
> +					 *other = arg;
> +
> +	if (sizeof(*other) != size)
> +		return false;
> +
> +	return instance->label == other->label;
> +}
> +
> +DECLARE_GH_VM_FUNCTION_INIT(irqfd, GH_FN_IRQFD, 2, gh_irqfd_bind, gh_irqfd_unbind,
> +				gh_irqfd_compare);
> +MODULE_DESCRIPTION("Gunyah irqfd VM Function");
> +MODULE_LICENSE("GPL");
> diff --git a/include/uapi/linux/gunyah.h b/include/uapi/linux/gunyah.h
> index 434ffa8ffc783..0c480c622686a 100644
> --- a/include/uapi/linux/gunyah.h
> +++ b/include/uapi/linux/gunyah.h
> @@ -77,9 +77,12 @@ struct gh_vm_dtb_config {
>    * @GH_FN_VCPU: create a vCPU instance to control a vCPU
>    *              &struct gh_fn_desc.arg is a pointer to &struct gh_fn_vcpu_arg
>    *              Return: file descriptor to manipulate the vcpu.
> + * @GH_FN_IRQFD: register eventfd to assert a Gunyah doorbell
> + *               &struct gh_fn_desc.arg is a pointer to &struct gh_fn_irqfd_arg
>    */
>   enum gh_fn_type {
>   	GH_FN_VCPU = 1,
> +	GH_FN_IRQFD,
>   };
>   
>   #define GH_FN_MAX_ARG_SIZE		256
> @@ -99,6 +102,38 @@ struct gh_fn_vcpu_arg {
>   	__u32 id;
>   };
>   
> +/**
> + * enum gh_irqfd_flags - flags for use in gh_fn_irqfd_arg
> + * @GH_IRQFD_FLAGS_LEVEL: make the interrupt operate like a level triggered
> + *                        interrupt on guest side. Triggering IRQFD before
> + *                        guest handles the interrupt causes interrupt to
> + *                        stay asserted.
> + */
> +enum gh_irqfd_flags {
> +	GH_IRQFD_FLAGS_LEVEL		= 1UL << 0,
> +};
> +
> +/**
> + * struct gh_fn_irqfd_arg - Arguments to create an irqfd function.
> + *
> + * Create this function with &GH_VM_ADD_FUNCTION using type &GH_FN_IRQFD.
> + *
> + * Allows setting an eventfd to directly trigger a guest interrupt.
> + * irqfd.fd specifies the file descriptor to use as the eventfd.
> + * irqfd.label corresponds to the doorbell label used in the guest VM's devicetree.
> + *
> + * @fd: an eventfd which when written to will raise a doorbell
> + * @label: Label of the doorbell created on the guest VM
> + * @flags: see &enum gh_irqfd_flags
> + * @padding: padding bytes
> + */
> +struct gh_fn_irqfd_arg {
> +	__u32 fd;
> +	__u32 label;
> +	__u32 flags;
> +	__u32 padding;
> +};
> +
>   /**
>    * struct gh_fn_desc - Arguments to create a VM function
>    * @type: Type of the function. See &enum gh_fn_type.