[PATCH RFC v15 28/30] virt: gunyah: Add irqfd interface

[Elliot Berman]

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>
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>
---
 drivers/virt/gunyah/Kconfig        |   9 ++
 drivers/virt/gunyah/Makefile       |   1 +
 drivers/virt/gunyah/gunyah_irqfd.c | 191 +++++++++++++++++++++++++++++++++++++
 include/uapi/linux/gunyah.h        |  35 +++++++
 4 files changed, 236 insertions(+)

diff --git a/drivers/virt/gunyah/Kconfig b/drivers/virt/gunyah/Kconfig
index fe2823dc48ba..1685b75fb77a 100644
--- a/drivers/virt/gunyah/Kconfig
+++ b/drivers/virt/gunyah/Kconfig
@@ -27,3 +27,12 @@ config GUNYAH_QCOM_PLATFORM
 	  extra platform-specific support.
 
 	  Say Y/M here to use Gunyah on Qualcomm platforms.
+
+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 c4505fce177d..b41b02792921 100644
--- a/drivers/virt/gunyah/Makefile
+++ b/drivers/virt/gunyah/Makefile
@@ -5,3 +5,4 @@ gunyah_rsc_mgr-y += rsc_mgr.o rsc_mgr_rpc.o vm_mgr.o vm_mgr_mem.o guest_memfd.o
 obj-$(CONFIG_GUNYAH) += gunyah.o gunyah_rsc_mgr.o gunyah_vcpu.o
 obj-$(CONFIG_GUNYAH_PLATFORM_HOOKS) += gunyah_platform_hooks.o
 obj-$(CONFIG_GUNYAH_QCOM_PLATFORM) += gunyah_qcom.o
+obj-$(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..0e377ead3213
--- /dev/null
+++ b/drivers/virt/gunyah/gunyah_irqfd.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/eventfd.h>
+#include <linux/device/driver.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 gunyah_irqfd {
+	struct gunyah_resource *ghrsc;
+	struct gunyah_vm_resource_ticket ticket;
+	struct gunyah_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 gunyah_irqfd *irqfd =
+		container_of(wait, struct gunyah_irqfd, wait);
+	__poll_t flags = key_to_poll(key);
+	int ret = 0;
+
+	if (flags & EPOLLIN) {
+		if (irqfd->ghrsc) {
+			ret = gunyah_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 gunyah_irqfd *irq_ctx =
+		container_of(pt, struct gunyah_irqfd, pt);
+
+	add_wait_queue(wqh, &irq_ctx->wait);
+}
+
+static bool gunyah_irqfd_populate(struct gunyah_vm_resource_ticket *ticket,
+				  struct gunyah_resource *ghrsc)
+{
+	struct gunyah_irqfd *irqfd =
+		container_of(ticket, struct gunyah_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 gunyah_hypercall_bell_send
+		 */
+		ret = gunyah_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 gunyah_irqfd_unpopulate(struct gunyah_vm_resource_ticket *ticket,
+				    struct gunyah_resource *ghrsc)
+{
+	struct gunyah_irqfd *irqfd =
+		container_of(ticket, struct gunyah_irqfd, ticket);
+	u64 cnt;
+
+	eventfd_ctx_remove_wait_queue(irqfd->ctx, &irqfd->wait, &cnt);
+}
+
+static long gunyah_irqfd_bind(struct gunyah_vm_function_instance *f)
+{
+	struct gunyah_fn_irqfd_arg *args = f->argp;
+	struct gunyah_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 & ~GUNYAH_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 & GUNYAH_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 = GUNYAH_RESOURCE_TYPE_BELL_TX;
+	irqfd->ticket.label = args->label;
+	irqfd->ticket.owner = THIS_MODULE;
+	irqfd->ticket.populate = gunyah_irqfd_populate;
+	irqfd->ticket.unpopulate = gunyah_irqfd_unpopulate;
+
+	r = gunyah_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 gunyah_irqfd_unbind(struct gunyah_vm_function_instance *f)
+{
+	struct gunyah_irqfd *irqfd = f->data;
+
+	gunyah_vm_remove_resource_ticket(irqfd->f->ghvm, &irqfd->ticket);
+	eventfd_ctx_put(irqfd->ctx);
+	kfree(irqfd);
+}
+
+static bool gunyah_irqfd_compare(const struct gunyah_vm_function_instance *f,
+				 const void *arg, size_t size)
+{
+	const struct gunyah_fn_irqfd_arg *instance = f->argp, *other = arg;
+
+	if (sizeof(*other) != size)
+		return false;
+
+	return instance->label == other->label;
+}
+
+DECLARE_GUNYAH_VM_FUNCTION_INIT(irqfd, GUNYAH_FN_IRQFD, 2, gunyah_irqfd_bind,
+				gunyah_irqfd_unbind, gunyah_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 574116f54472..cb7b0bb9bef3 100644
--- a/include/uapi/linux/gunyah.h
+++ b/include/uapi/linux/gunyah.h
@@ -63,9 +63,12 @@ struct gunyah_vm_dtb_config {
  * @GUNYAH_FN_VCPU: create a vCPU instance to control a vCPU
  *              &struct gunyah_fn_desc.arg is a pointer to &struct gunyah_fn_vcpu_arg
  *              Return: file descriptor to manipulate the vcpu.
+ * @GUNYAH_FN_IRQFD: register eventfd to assert a Gunyah doorbell
+ *               &struct gunyah_fn_desc.arg is a pointer to &struct gunyah_fn_irqfd_arg
  */
 enum gunyah_fn_type {
 	GUNYAH_FN_VCPU = 1,
+	GUNYAH_FN_IRQFD,
 };
 
 #define GUNYAH_FN_MAX_ARG_SIZE		256
@@ -85,6 +88,38 @@ struct gunyah_fn_vcpu_arg {
 	__u32 id;
 };
 
+/**
+ * enum gunyah_irqfd_flags - flags for use in gunyah_fn_irqfd_arg
+ * @GUNYAH_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 gunyah_irqfd_flags {
+	GUNYAH_IRQFD_FLAGS_LEVEL		= 1UL << 0,
+};
+
+/**
+ * struct gunyah_fn_irqfd_arg - Arguments to create an irqfd function.
+ *
+ * Create this function with &GUNYAH_VM_ADD_FUNCTION using type &GUNYAH_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 gunyah_irqfd_flags
+ * @padding: padding bytes
+ */
+struct gunyah_fn_irqfd_arg {
+	__u32 fd;
+	__u32 label;
+	__u32 flags;
+	__u32 padding;
+};
+
 /**
  * struct gunyah_fn_desc - Arguments to create a VM function
  * @type: Type of the function. See &enum gunyah_fn_type.

-- 
2.43.0