Merge tag 'for-linus-6.7-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - two small cleanup patches

 - a fix for PCI passthrough under Xen

 - a four patch series speeding up virtio under Xen with user space
   backends

* tag 'for-linus-6.7-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen-pciback: Consider INTx disabled when MSI/MSI-X is enabled
  xen: privcmd: Add support for ioeventfd
  xen: evtchn: Allow shared registration of IRQ handers
  xen: irqfd: Use _IOW instead of the internal _IOC() macro
  xen: Make struct privcmd_irqfd's layout architecture independent
  xen/xenbus: Add __counted_by for struct read_buffer and use struct_size()
  xenbus: fix error exit in xenbus_init()

drivers/xen/Kconfig

@@ -269,12 +269,12 @@ config XEN_PRIVCMD
 	  disaggregated Xen setups this driver might be needed for other
 	  domains, too.
 
-config XEN_PRIVCMD_IRQFD
-	bool "Xen irqfd support"
+config XEN_PRIVCMD_EVENTFD
+	bool "Xen Ioeventfd and irqfd support"
 	depends on XEN_PRIVCMD && XEN_VIRTIO && EVENTFD
 	help
-	  Using the irqfd mechanism a virtio backend running in a daemon can
-	  speed up interrupt injection into a guest.
+	  Using the ioeventfd / irqfd mechanism a virtio backend running in a
+	  daemon can speed up interrupt delivery from / to a guest.
 
 config XEN_ACPI_PROCESSOR
 	tristate "Xen ACPI processor"

drivers/xen/events/events_base.c

@@ -1229,7 +1229,8 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
 		bind_evtchn_to_cpu(evtchn, 0, false);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
-		WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
+		if (!WARN_ON(!info || info->type != IRQT_EVTCHN))
+			info->refcnt++;
 	}
 
 out:

drivers/xen/evtchn.c

@@ -397,7 +397,7 @@ static int evtchn_bind_to_user(struct per_user_data *u, evtchn_port_t port,
 	if (rc < 0)
 		goto err;
 
-	rc = bind_evtchn_to_irqhandler_lateeoi(port, evtchn_interrupt, 0,
+	rc = bind_evtchn_to_irqhandler_lateeoi(port, evtchn_interrupt, IRQF_SHARED,
 					       u->name, evtchn);
 	if (rc < 0)
 		goto err;

drivers/xen/xen-pciback/conf_space.c

@@ -288,12 +288,6 @@ int xen_pcibk_get_interrupt_type(struct pci_dev *dev)
 	u16 val;
 	int ret = 0;
 
-	err = pci_read_config_word(dev, PCI_COMMAND, &val);
-	if (err)
-		return err;
-	if (!(val & PCI_COMMAND_INTX_DISABLE))
-		ret |= INTERRUPT_TYPE_INTX;
-
 	/*
 	 * Do not trust dev->msi(x)_enabled here, as enabling could be done
 	 * bypassing the pci_*msi* functions, by the qemu.
@@ -316,6 +310,19 @@ int xen_pcibk_get_interrupt_type(struct pci_dev *dev)
 		if (val & PCI_MSIX_FLAGS_ENABLE)
 			ret |= INTERRUPT_TYPE_MSIX;
 	}
+
+	/*
+	 * PCIe spec says device cannot use INTx if MSI/MSI-X is enabled,
+	 * so check for INTx only when both are disabled.
+	 */
+	if (!ret) {
+		err = pci_read_config_word(dev, PCI_COMMAND, &val);
+		if (err)
+			return err;
+		if (!(val & PCI_COMMAND_INTX_DISABLE))
+			ret |= INTERRUPT_TYPE_INTX;
+	}
+
 	return ret ?: INTERRUPT_TYPE_NONE;
 }
 

drivers/xen/xen-pciback/conf_space_capability.c

@@ -236,10 +236,16 @@ static int msi_msix_flags_write(struct pci_dev *dev, int offset, u16 new_value,
 		return PCIBIOS_SET_FAILED;
 
 	if (new_value & field_config->enable_bit) {
-		/* don't allow enabling together with other interrupt types */
+		/*
+		 * Don't allow enabling together with other interrupt type, but do
+		 * allow enabling MSI(-X) while INTx is still active to please Linuxes
+		 * MSI(-X) startup sequence. It is safe to do, as according to PCI
+		 * spec, device with enabled MSI(-X) shouldn't use INTx.
+		 */
 		int int_type = xen_pcibk_get_interrupt_type(dev);
 
 		if (int_type == INTERRUPT_TYPE_NONE ||
+		    int_type == INTERRUPT_TYPE_INTX ||
 		    int_type == field_config->int_type)
 			goto write;
 		return PCIBIOS_SET_FAILED;

drivers/xen/xen-pciback/conf_space_header.c

@@ -104,24 +104,9 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
 		pci_clear_mwi(dev);
 	}
 
-	if (dev_data && dev_data->allow_interrupt_control) {
-		if ((cmd->val ^ value) & PCI_COMMAND_INTX_DISABLE) {
-			if (value & PCI_COMMAND_INTX_DISABLE) {
-				pci_intx(dev, 0);
-			} else {
-				/* Do not allow enabling INTx together with MSI or MSI-X. */
-				switch (xen_pcibk_get_interrupt_type(dev)) {
-				case INTERRUPT_TYPE_NONE:
-					pci_intx(dev, 1);
-					break;
-				case INTERRUPT_TYPE_INTX:
-					break;
-				default:
-					return PCIBIOS_SET_FAILED;
-				}
-			}
-		}
-	}
+	if (dev_data && dev_data->allow_interrupt_control &&
+	    ((cmd->val ^ value) & PCI_COMMAND_INTX_DISABLE))
+		pci_intx(dev, !(value & PCI_COMMAND_INTX_DISABLE));
 
 	cmd->val = value;
 

drivers/xen/xenbus/xenbus_dev_frontend.c

@@ -82,7 +82,7 @@ struct read_buffer {
 	struct list_head list;
 	unsigned int cons;
 	unsigned int len;
-	char msg[];
+	char msg[] __counted_by(len);
 };
 
 struct xenbus_file_priv {
@@ -195,7 +195,7 @@ static int queue_reply(struct list_head *queue, const void *data, size_t len)
 	if (len > XENSTORE_PAYLOAD_MAX)
 		return -EINVAL;
 
-	rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL);
+	rb = kmalloc(struct_size(rb, msg, len), GFP_KERNEL);
 	if (rb == NULL)
 		return -ENOMEM;
 

drivers/xen/xenbus/xenbus_probe.c

@@ -1025,7 +1025,7 @@ static int __init xenbus_init(void)
 			if (err < 0) {
 				pr_err("xenstore_late_init couldn't bind irq err=%d\n",
 				       err);
-				return err;
+				goto out_error;
 			}
 
 			xs_init_irq = err;

include/uapi/xen/privcmd.h

@@ -102,7 +102,7 @@ struct privcmd_mmap_resource {
 #define PRIVCMD_IRQFD_FLAG_DEASSIGN (1 << 0)
 
 struct privcmd_irqfd {
-	void __user *dm_op;
+	__u64 dm_op;
 	__u32 size; /* Size of structure pointed by dm_op */
 	__u32 fd;
 	__u32 flags;
@@ -110,6 +110,22 @@ struct privcmd_irqfd {
 	__u8 pad[2];
 };
 
+/* For privcmd_ioeventfd::flags */
+#define PRIVCMD_IOEVENTFD_FLAG_DEASSIGN (1 << 0)
+
+struct privcmd_ioeventfd {
+	__u64 ioreq;
+	__u64 ports;
+	__u64 addr;
+	__u32 addr_len;
+	__u32 event_fd;
+	__u32 vcpus;
+	__u32 vq;
+	__u32 flags;
+	domid_t dom;
+	__u8 pad[2];
+};
+
 /*
  * @cmd: IOCTL_PRIVCMD_HYPERCALL
  * @arg: &privcmd_hypercall_t
@@ -138,6 +154,8 @@ struct privcmd_irqfd {
 #define IOCTL_PRIVCMD_MMAP_RESOURCE				\
 	_IOC(_IOC_NONE, 'P', 7, sizeof(struct privcmd_mmap_resource))
 #define IOCTL_PRIVCMD_IRQFD					\
-	_IOC(_IOC_NONE, 'P', 8, sizeof(struct privcmd_irqfd))
+	_IOW('P', 8, struct privcmd_irqfd)
+#define IOCTL_PRIVCMD_IOEVENTFD					\
+	_IOW('P', 9, struct privcmd_ioeventfd)
 
 #endif /* __LINUX_PUBLIC_PRIVCMD_H__ */

include/xen/interface/hvm/ioreq.h

+/* SPDX-License-Identifier: MIT */
+/*
+ * ioreq.h: I/O request definitions for device models
+ * Copyright (c) 2004, Intel Corporation.
+ */
+
+#ifndef __XEN_PUBLIC_HVM_IOREQ_H__
+#define __XEN_PUBLIC_HVM_IOREQ_H__
+
+#define IOREQ_READ      1
+#define IOREQ_WRITE     0
+
+#define STATE_IOREQ_NONE        0
+#define STATE_IOREQ_READY       1
+#define STATE_IOREQ_INPROCESS   2
+#define STATE_IORESP_READY      3
+
+#define IOREQ_TYPE_PIO          0 /* pio */
+#define IOREQ_TYPE_COPY         1 /* mmio ops */
+#define IOREQ_TYPE_PCI_CONFIG   2
+#define IOREQ_TYPE_TIMEOFFSET   7
+#define IOREQ_TYPE_INVALIDATE   8 /* mapcache */
+
+/*
+ * VMExit dispatcher should cooperate with instruction decoder to
+ * prepare this structure and notify service OS and DM by sending
+ * virq.
+ *
+ * For I/O type IOREQ_TYPE_PCI_CONFIG, the physical address is formatted
+ * as follows:
+ *
+ * 63....48|47..40|39..35|34..32|31........0
+ * SEGMENT |BUS   |DEV   |FN    |OFFSET
+ */
+struct ioreq {
+	uint64_t addr;          /* physical address */
+	uint64_t data;          /* data (or paddr of data) */
+	uint32_t count;         /* for rep prefixes */
+	uint32_t size;          /* size in bytes */
+	uint32_t vp_eport;      /* evtchn for notifications to/from device model */
+	uint16_t _pad0;
+	uint8_t state:4;
+	uint8_t data_is_ptr:1;  /* if 1, data above is the guest paddr
+				 * of the real data to use. */
+	uint8_t dir:1;          /* 1=read, 0=write */
+	uint8_t df:1;
+	uint8_t _pad1:1;
+	uint8_t type;           /* I/O type */
+};
+
+#endif /* __XEN_PUBLIC_HVM_IOREQ_H__ */