[v11,24/26] virt: gunyah: Add irqfd interface
Commit Message
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.
Co-developed-by: Prakruthi Deepak Heragu <quic_pheragu@quicinc.com>
Signed-off-by: Prakruthi Deepak Heragu <quic_pheragu@quicinc.com>
Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
---
Documentation/virt/gunyah/vm-manager.rst | 2 +-
drivers/virt/gunyah/Kconfig | 9 ++
drivers/virt/gunyah/Makefile | 1 +
drivers/virt/gunyah/gunyah_irqfd.c | 164 +++++++++++++++++++++++
include/linux/gunyah.h | 5 +
include/uapi/linux/gunyah.h | 30 +++++
6 files changed, 210 insertions(+), 1 deletion(-)
create mode 100644 drivers/virt/gunyah/gunyah_irqfd.c
Comments
On 3/3/23 7:06 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.
>
> Co-developed-by: Prakruthi Deepak Heragu <quic_pheragu@quicinc.com>
> Signed-off-by: Prakruthi Deepak Heragu <quic_pheragu@quicinc.com>
> Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
I suggest a few things below, including some code simplification.
I also have a few questions (which could possibly be answered by
adding comments).
-Alex
> ---
> Documentation/virt/gunyah/vm-manager.rst | 2 +-
> drivers/virt/gunyah/Kconfig | 9 ++
> drivers/virt/gunyah/Makefile | 1 +
> drivers/virt/gunyah/gunyah_irqfd.c | 164 +++++++++++++++++++++++
> include/linux/gunyah.h | 5 +
> include/uapi/linux/gunyah.h | 30 +++++
> 6 files changed, 210 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 83d326b0d11f..a1dd70f0cbf6 100644
> --- a/Documentation/virt/gunyah/vm-manager.rst
> +++ b/Documentation/virt/gunyah/vm-manager.rst
> @@ -124,7 +124,7 @@ the VM starts.
> The possible types are documented below:
>
> .. kernel-doc:: include/uapi/linux/gunyah.h
> - :identifiers: GH_FN_VCPU gh_fn_vcpu_arg
> + :identifiers: GH_FN_VCPU gh_fn_vcpu_arg GH_FN_IRQFD gh_fn_irqfd_arg
>
> Gunyah VCPU API Descriptions
> ----------------------------
> diff --git a/drivers/virt/gunyah/Kconfig b/drivers/virt/gunyah/Kconfig
> index 4c1c6110b50e..2cde24d429d1 100644
> --- a/drivers/virt/gunyah/Kconfig
> +++ b/drivers/virt/gunyah/Kconfig
> @@ -26,3 +26,12 @@ 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 2d1b604a7b03..6cf756bfa3c2 100644
> --- a/drivers/virt/gunyah/Makefile
> +++ b/drivers/virt/gunyah/Makefile
> @@ -7,3 +7,4 @@ gunyah_rsc_mgr-y += rsc_mgr.o rsc_mgr_rpc.o vm_mgr.o vm_mgr_mm.o
> obj-$(CONFIG_GUNYAH) += gunyah_rsc_mgr.o
>
> obj-$(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 000000000000..38e5fe266b00
> --- /dev/null
> +++ b/drivers/virt/gunyah/gunyah_irqfd.c
> @@ -0,0 +1,164 @@
> +// 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);
> + u64 enable_mask = GH_BELL_NONBLOCK;
> + u64 old_flags;
> + int ret = 0;
> +
> + if (flags & EPOLLIN) {
> + if (irqfd->ghrsc) {
> + ret = gh_hypercall_bell_send(irqfd->ghrsc->capid, enable_mask, &old_flags);
I commented elsewhere that you might support passing a null
pointer as the last argument above (since you don't use the
result).
> + 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 int gh_irqfd_populate(struct gh_vm_resource_ticket *ticket, struct gh_resource *ghrsc)
> +{
> + struct gh_irqfd *irqfd = container_of(ticket, struct gh_irqfd, ticket);
> + u64 enable_mask = GH_BELL_NONBLOCK;
> + u64 ack_mask = ~0;
Why is the ACK mask ~0?
I guess I don't know details about this hypercall (do you document
them somewhere?), so it's hard to judge whether or why this is the
right thing to use. The enable_mask is just GH_BELL_NONBLOCK,
which is just BIT(32).
> + int ret = 0;
> +
> + if (irqfd->ghrsc) {
> + pr_warn("irqfd%d already got a Gunyah resource. Check if multiple resources with same label were configured.\n",
s/%d/%u/
> + irqfd->ticket.label);
> + return -1;
I would say you should return -EBUSY here instead.
However, all callers just check for a zero/nonzero result, so
you could instead have this function (and the pointer it's
assigned to) to return Boolean instead (and return true on
success).
> + }
> +
> + irqfd->ghrsc = ghrsc;
> + if (irqfd->level) {
I think I don't understand this part of the code well
enough to know this. What happens if level is false?
> + ret = gh_hypercall_bell_set_mask(irqfd->ghrsc->capid, enable_mask, ack_mask);
> + if (ret)
> + pr_warn("irq %d couldn't be set as level triggered. Might cause IRQ storm if asserted\n",
> + irqfd->ticket.label);
> + }
> +
> + return 0;
> +}
> +
> +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_LEVEL)
> + return -EINVAL;
> +
> + irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
> + if (!irqfd)
> + return -ENOMEM;
> +
> + irqfd->f = f;
> + f->data = irqfd;
> +
In the next section you get a temporary reference to the FD,
then look up the eventfd context from its file. But in
gh_ioeventfd_bind() you just call eventfd_ctx_fdget().
I *think* you can do the same here, but perhaps I'm missing
something.
> + 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;
> + }
> +
I.e., rather than the two function calls above, you could just
call:
irqfd->ctx = eventfd_ctx_fdget(args->fd);
And in that case you also wouldn't need the fdput() call in the
error path below.
> + if (args->flags & GH_IRQFD_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);
> +}
> +
> +DECLARE_GH_VM_FUNCTION_INIT(irqfd, GH_FN_IRQFD, gh_irqfd_bind, gh_irqfd_unbind);
> +MODULE_DESCRIPTION("Gunyah irqfds");
Maybe singular, and maybe "Gunyah irqfd VM function(s)".
> +MODULE_LICENSE("GPL");
> diff --git a/include/linux/gunyah.h b/include/linux/gunyah.h
> index 63395dacc1a8..0344b6988cfa 100644
> --- a/include/linux/gunyah.h
> +++ b/include/linux/gunyah.h
> @@ -33,6 +33,11 @@ struct gh_resource {
> u32 rm_label;
> };
>
> +/**
> + * Gunyah Doorbells
> + */
> +#define GH_BELL_NONBLOCK BIT(32)
> +
> /**
> * Gunyah Message Queues
> */
> diff --git a/include/uapi/linux/gunyah.h b/include/uapi/linux/gunyah.h
> index e52265fa5715..5617dadc1c7b 100644
> --- a/include/uapi/linux/gunyah.h
> +++ b/include/uapi/linux/gunyah.h
> @@ -76,6 +76,19 @@ struct gh_vm_dtb_config {
> */
> #define GH_FN_VCPU 1
>
> +/**
> + * GH_FN_IRQFD - register eventfd to assert a Gunyah doorbell
> + *
> + * gh_fn_desc is filled with gh_fn_irqfd_arg
> + *
> + * 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.
> + *
> + * Return: 0
> + */
> +#define GH_FN_IRQFD 2
> +
> #define GH_FN_MAX_ARG_SIZE 256
>
> /**
> @@ -88,6 +101,23 @@ struct gh_fn_vcpu_arg {
>
> #define GH_IRQFD_LEVEL (1UL << 0)
This is associated with the IRQFD "flags" field, so I'd name it
GH_IRQFD_FLAGS_LEVEL.
>
> +/**
> + * struct gh_fn_irqfd_arg - Arguments to create an irqfd function
> + * @fd: an eventfd which when written to will raise a doorbell
> + * @label: Label of the doorbell created on the guest VM
> + * @flags: GH_IRQFD_LEVEL configures the corresponding doorbell to behave
> + * like a level triggered interrupt.
> + * @padding: padding bytes
> + */
> +struct gh_fn_irqfd_arg {
> + __u32 fd;
Should the "fd" field be signed? Should it be an int? (Perhaps
you're trying to define a fixed kernel API, so __s32 if signed would
be better.)
> + __u32 label;
> + __u32 flags;
> + __u32 padding;
> +};
> +
> +#define GH_IOEVENTFD_DATAMATCH (1UL << 0)
> +
> /**
> * struct gh_fn_desc - Arguments to create a VM function
> * @type: Type of the function. See GH_FN_* macro for supported types
On 3/31/2023 7:27 AM, Alex Elder wrote:
> On 3/3/23 7:06 PM, Elliot Berman wrote:
[snip]
>> +
>> +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);
>> + u64 enable_mask = GH_BELL_NONBLOCK;
>> + u64 old_flags;
>> + int ret = 0;
>> +
>> + if (flags & EPOLLIN) {
>> + if (irqfd->ghrsc) {
>> + ret = gh_hypercall_bell_send(irqfd->ghrsc->capid,
>> enable_mask, &old_flags);
>
> I commented elsewhere that you might support passing a null
> pointer as the last argument above (since you don't use the
> result).
>
>> + 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 int gh_irqfd_populate(struct gh_vm_resource_ticket *ticket,
>> struct gh_resource *ghrsc)
>> +{
>> + struct gh_irqfd *irqfd = container_of(ticket, struct gh_irqfd,
>> ticket);
>> + u64 enable_mask = GH_BELL_NONBLOCK;
>> + u64 ack_mask = ~0;
>
> Why is the ACK mask ~0?
>
> I guess I don't know details about this hypercall (do you document
> them somewhere?), so it's hard to judge whether or why this is the
> right thing to use. The enable_mask is just GH_BELL_NONBLOCK,
> which is just BIT(32).
>
I talked to our hypervisor folks and they mentioned we can simplify
this. In v12, enable_mask and ack_mask can just be "1" (BIT(0)). We had
chosen bit 32 arbitrarily.
[snip]
>
>> + }
>> +
>> + irqfd->ghrsc = ghrsc;
>> + if (irqfd->level) {
>
> I think I don't understand this part of the code well
> enough to know this. What happens if level is false?
>
If level is false, then guest is assumed to set up IRQ on its side as
edge-triggered. In that case, we don't need to configure the enable
mask/ack mask because the doorbell flags aren't polled.
[snip]
>> +/**
>> + * struct gh_fn_irqfd_arg - Arguments to create an irqfd function
>> + * @fd: an eventfd which when written to will raise a doorbell
>> + * @label: Label of the doorbell created on the guest VM
>> + * @flags: GH_IRQFD_LEVEL configures the corresponding doorbell to
>> behave
>> + * like a level triggered interrupt.
>> + * @padding: padding bytes
>> + */
>> +struct gh_fn_irqfd_arg {
>> + __u32 fd;
>
> Should the "fd" field be signed? Should it be an int? (Perhaps
> you're trying to define a fixed kernel API, so __s32 if signed would
> be better.)
>
It looked to me like some interfaces use __u32 and some use __s32. Is
one technically correct?
On 4/17/23 5:55 PM, Elliot Berman wrote:
>>>
>>> +struct gh_fn_irqfd_arg {
>>> + __u32 fd;
>>
>> Should the "fd" field be signed? Should it be an int? (Perhaps
>> you're trying to define a fixed kernel API, so __s32 if signed would
>> be better.)
>>
>
> It looked to me like some interfaces use __u32 and some use __s32. Is
> one technically correct?
Good question. It depends on how you use it.
It's a file descriptor, so it should be an int, and it appears
that's always a 32-bit signed (for 32 and 64 bit machines).
So the size seems to be right.
Whether it's signed or not I think depends on whether you
ever save an error value in this field. I doubt you do,
but if you do, it should be signed. Otherwise, the largest
value will never exceed INT_MAX/S32_MAX; and in that case
either is fine.
Will Gunyah ever run on a 32-bit machine?
-Alex
@@ -124,7 +124,7 @@ the VM starts.
The possible types are documented below:
.. kernel-doc:: include/uapi/linux/gunyah.h
- :identifiers: GH_FN_VCPU gh_fn_vcpu_arg
+ :identifiers: GH_FN_VCPU gh_fn_vcpu_arg GH_FN_IRQFD gh_fn_irqfd_arg
Gunyah VCPU API Descriptions
----------------------------
@@ -26,3 +26,12 @@ 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.
@@ -7,3 +7,4 @@ gunyah_rsc_mgr-y += rsc_mgr.o rsc_mgr_rpc.o vm_mgr.o vm_mgr_mm.o
obj-$(CONFIG_GUNYAH) += gunyah_rsc_mgr.o
obj-$(CONFIG_GUNYAH_VCPU) += gunyah_vcpu.o
+obj-$(CONFIG_GUNYAH_IRQFD) += gunyah_irqfd.o
new file mode 100644
@@ -0,0 +1,164 @@
+// 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);
+ u64 enable_mask = GH_BELL_NONBLOCK;
+ u64 old_flags;
+ int ret = 0;
+
+ if (flags & EPOLLIN) {
+ if (irqfd->ghrsc) {
+ ret = gh_hypercall_bell_send(irqfd->ghrsc->capid, enable_mask, &old_flags);
+ 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 int gh_irqfd_populate(struct gh_vm_resource_ticket *ticket, struct gh_resource *ghrsc)
+{
+ struct gh_irqfd *irqfd = container_of(ticket, struct gh_irqfd, ticket);
+ u64 enable_mask = GH_BELL_NONBLOCK;
+ u64 ack_mask = ~0;
+ int ret = 0;
+
+ 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 -1;
+ }
+
+ irqfd->ghrsc = ghrsc;
+ if (irqfd->level) {
+ ret = gh_hypercall_bell_set_mask(irqfd->ghrsc->capid, enable_mask, ack_mask);
+ if (ret)
+ pr_warn("irq %d couldn't be set as level triggered. Might cause IRQ storm if asserted\n",
+ irqfd->ticket.label);
+ }
+
+ return 0;
+}
+
+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_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_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);
+}
+
+DECLARE_GH_VM_FUNCTION_INIT(irqfd, GH_FN_IRQFD, gh_irqfd_bind, gh_irqfd_unbind);
+MODULE_DESCRIPTION("Gunyah irqfds");
+MODULE_LICENSE("GPL");
@@ -33,6 +33,11 @@ struct gh_resource {
u32 rm_label;
};
+/**
+ * Gunyah Doorbells
+ */
+#define GH_BELL_NONBLOCK BIT(32)
+
/**
* Gunyah Message Queues
*/
@@ -76,6 +76,19 @@ struct gh_vm_dtb_config {
*/
#define GH_FN_VCPU 1
+/**
+ * GH_FN_IRQFD - register eventfd to assert a Gunyah doorbell
+ *
+ * gh_fn_desc is filled with gh_fn_irqfd_arg
+ *
+ * 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.
+ *
+ * Return: 0
+ */
+#define GH_FN_IRQFD 2
+
#define GH_FN_MAX_ARG_SIZE 256
/**
@@ -88,6 +101,23 @@ struct gh_fn_vcpu_arg {
#define GH_IRQFD_LEVEL (1UL << 0)
+/**
+ * struct gh_fn_irqfd_arg - Arguments to create an irqfd function
+ * @fd: an eventfd which when written to will raise a doorbell
+ * @label: Label of the doorbell created on the guest VM
+ * @flags: GH_IRQFD_LEVEL configures the corresponding doorbell to behave
+ * like a level triggered interrupt.
+ * @padding: padding bytes
+ */
+struct gh_fn_irqfd_arg {
+ __u32 fd;
+ __u32 label;
+ __u32 flags;
+ __u32 padding;
+};
+
+#define GH_IOEVENTFD_DATAMATCH (1UL << 0)
+
/**
* struct gh_fn_desc - Arguments to create a VM function
* @type: Type of the function. See GH_FN_* macro for supported types