[PATCH 2/3] vfio/ism: Implement vfio_pci driver for ISM devices

[Julian Ruess]

Add a vfio_pci variant driver for the s390-specific Internal Shared
Memory (ISM) devices used for inter-VM communication.

This enables the development of vfio-pci-based user space drivers for
ISM devices.

On s390, kernel primitives such as ioread() and iowrite() are switched
over from function handle based PCI load/stores instructions to PCI
memory-I/O (MIO) loads/stores when these are available and not
explicitly disabled. Since these instructions cannot be used with ISM
devices, ensure that classic function handle-based PCI instructions are
used instead.

The driver is still required even when MIO instructions are disabled, as
the ISM device relies on the PCI store block (PCISTB) instruction to
perform write operations.

Stores are not fragmented, therefore one ioctl corresponds to exactly
one PCISTB instruction. User space must ensure to not write more than
4096 bytes at once to an ISM BAR which is the maximum payload of the
PCISTB instruction

Export vfio_pci_config_rw() for config space accesses that do not rely
on s390 MIO instructions.

Acked-by: Alexandra Winter <wintera@xxxxxxxxxxxxx>
Signed-off-by: Julian Ruess <julianr@xxxxxxxxxxxxx>
---
 drivers/vfio/pci/Kconfig           |   2 +
 drivers/vfio/pci/Makefile          |   2 +
 drivers/vfio/pci/ism/Kconfig       |  11 ++
 drivers/vfio/pci/ism/Makefile      |   3 +
 drivers/vfio/pci/ism/main.c        | 227 +++++++++++++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_config.c |   1 +
 6 files changed, 246 insertions(+)

diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 1e82b44bda1a0a544e1add7f4b06edecf35aaf81..296bf01e185ecacc388ebc69e92706c99e47c814 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -60,6 +60,8 @@ config VFIO_PCI_DMABUF
 
 source "drivers/vfio/pci/mlx5/Kconfig"
 
+source "drivers/vfio/pci/ism/Kconfig"
+
 source "drivers/vfio/pci/hisilicon/Kconfig"
 
 source "drivers/vfio/pci/pds/Kconfig"
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index e0a0757dd1d2b0bc69b7e4d79441d5cacf4e1cd8..6138f1bf241df04e7419f196b404abdf9b194050 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -11,6 +11,8 @@ obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
 
 obj-$(CONFIG_MLX5_VFIO_PCI)           += mlx5/
 
+obj-$(CONFIG_ISM_VFIO_PCI)           += ism/
+
 obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisilicon/
 
 obj-$(CONFIG_PDS_VFIO_PCI) += pds/
diff --git a/drivers/vfio/pci/ism/Kconfig b/drivers/vfio/pci/ism/Kconfig
new file mode 100644
index 0000000000000000000000000000000000000000..2db6c9327980827bf617afb9a82b1d1928868d42
--- /dev/null
+++ b/drivers/vfio/pci/ism/Kconfig
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+config ISM_VFIO_PCI
+	tristate "VFIO support for ISM devices"
+	depends on ISM
+	select VFIO_PCI_CORE
+	help
+	  This provides user space support for
+	  IBM Internal Shared Memory (ISM) Adapter devices
+	  using the VFIO framework.
+
+	  If you don't know what to do here, say N.
diff --git a/drivers/vfio/pci/ism/Makefile b/drivers/vfio/pci/ism/Makefile
new file mode 100644
index 0000000000000000000000000000000000000000..32cc3c66dd11395da85a2b6f05b3d97036ed8a35
--- /dev/null
+++ b/drivers/vfio/pci/ism/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ISM_VFIO_PCI) += ism-vfio-pci.o
+ism-vfio-pci-y := main.o
diff --git a/drivers/vfio/pci/ism/main.c b/drivers/vfio/pci/ism/main.c
new file mode 100644
index 0000000000000000000000000000000000000000..99f27682ec16ec855ae12ff87059dbb1bc18c586
--- /dev/null
+++ b/drivers/vfio/pci/ism/main.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * vfio-ISM driver for s390
+ *
+ * Copyright IBM Corp. 2026
+ */
+
+#include "../vfio_pci_priv.h"
+
+struct ism_vfio_pci_core_device {
+	struct vfio_pci_core_device core_device;
+};
+
+static int ism_pci_open_device(struct vfio_device *core_vdev)
+{
+	struct ism_vfio_pci_core_device *mvdev = container_of(
+		core_vdev, struct ism_vfio_pci_core_device, core_device.vdev);
+	struct vfio_pci_core_device *vdev = &mvdev->core_device;
+	int ret;
+
+	ret = vfio_pci_core_enable(vdev);
+	if (ret)
+		return ret;
+
+	vfio_pci_core_finish_enable(vdev);
+	return 0;
+}
+
+static ssize_t ism_vfio_pci_do_io_r(struct vfio_pci_core_device *vdev,
+				    char __user *buf, loff_t off, size_t count,
+				    int bar)
+{
+	struct zpci_dev *zdev = to_zpci(vdev->pdev);
+	ssize_t ret, done = 0;
+	u64 req, length, tmp;
+
+	while (count) {
+		if (count >= 8 && IS_ALIGNED(off, 8))
+			length = 8;
+		else if (count >= 4 && IS_ALIGNED(off, 4))
+			length = 4;
+		else if (count >= 2 && IS_ALIGNED(off, 2))
+			length = 2;
+		else
+			length = 1;
+		req = ZPCI_CREATE_REQ(READ_ONCE(zdev->fh), bar, length);
+		/* use pcilg to prevent using MIO instructions */
+		ret = __zpci_load(&tmp, req, off);
+		if (ret)
+			return ret;
+		if (copy_to_user(buf, &tmp, length))
+			return -EFAULT;
+		count -= length;
+		done += length;
+		off += length;
+		buf += length;
+	}
+	return done;
+}
+
+static ssize_t ism_vfio_pci_do_io_w(struct vfio_pci_core_device *vdev,
+				    char __user *buf, loff_t off, size_t count,
+				    int bar)
+{
+	struct zpci_dev *zdev = to_zpci(vdev->pdev);
+	void *data __free(kfree) = NULL;
+	ssize_t ret;
+	u64 req;
+
+	if (count > ZPCI_BOUNDARY_SIZE)
+		return -EINVAL;
+	data = kzalloc(ZPCI_BOUNDARY_SIZE, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	if (copy_from_user(data, buf, count))
+		return -EFAULT;
+	req = ZPCI_CREATE_REQ(READ_ONCE(zdev->fh), bar, count);
+	ret = __zpci_store_block(data, req, off);
+	if (ret)
+		return ret;
+	return count;
+}
+
+static ssize_t ism_vfio_pci_bar_rw(struct vfio_pci_core_device *vdev,
+				   char __user *buf, size_t count, loff_t *ppos,
+				   bool iswrite)
+{
+	int bar = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	resource_size_t end;
+	ssize_t done = 0;
+
+	if (pci_resource_start(vdev->pdev, bar))
+		end = pci_resource_len(vdev->pdev, bar);
+	else
+		return -EINVAL;
+
+	if (pos >= end)
+		return -EINVAL;
+
+	count = min(count, (size_t)(end - pos));
+
+	if (iswrite)
+		done = ism_vfio_pci_do_io_w(vdev, buf, pos, count, bar);
+	else
+		done = ism_vfio_pci_do_io_r(vdev, buf, pos, count, bar);
+
+	if (done >= 0)
+		*ppos += done;
+
+	return done;
+}
+
+static ssize_t ism_vfio_pci_rw(struct vfio_device *core_vdev, char __user *buf,
+			       size_t count, loff_t *ppos, bool iswrite)
+{
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	struct vfio_pci_core_device *vdev;
+	int ret;
+
+	vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev);
+
+	if (!count)
+		return 0;
+
+	switch (index) {
+	case VFIO_PCI_CONFIG_REGION_INDEX:
+		ret = vfio_pci_config_rw(vdev, buf, count, ppos, iswrite);
+		break;
+
+	case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
+		ret = ism_vfio_pci_bar_rw(vdev, buf, count, ppos, iswrite);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+static ssize_t ism_vfio_pci_read(struct vfio_device *core_vdev,
+				 char __user *buf, size_t count, loff_t *ppos)
+{
+	return ism_vfio_pci_rw(core_vdev, buf, count, ppos, false);
+}
+
+static ssize_t ism_vfio_pci_write(struct vfio_device *core_vdev,
+				  const char __user *buf, size_t count,
+				  loff_t *ppos)
+{
+	return ism_vfio_pci_rw(core_vdev, (char __user *)buf, count, ppos,
+			       true);
+}
+
+static const struct vfio_device_ops ism_pci_ops = {
+	.name = "ism-vfio-pci",
+	.init = vfio_pci_core_init_dev,
+	.release = vfio_pci_core_release_dev,
+	.open_device = ism_pci_open_device,
+	.close_device = vfio_pci_core_close_device,
+	.ioctl = vfio_pci_core_ioctl,
+	.get_region_info_caps = vfio_pci_ioctl_get_region_info,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = ism_vfio_pci_read,
+	.write = ism_vfio_pci_write,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+
+};
+
+static int ism_vfio_pci_probe(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	struct ism_vfio_pci_core_device *ivpcd;
+	int ret;
+
+	ivpcd = vfio_alloc_device(ism_vfio_pci_core_device, core_device.vdev,
+				  &pdev->dev, &ism_pci_ops);
+	if (IS_ERR(ivpcd))
+		return PTR_ERR(ivpcd);
+
+	dev_set_drvdata(&pdev->dev, &ivpcd->core_device);
+	ret = vfio_pci_core_register_device(&ivpcd->core_device);
+	if (ret)
+		vfio_put_device(&ivpcd->core_device.vdev);
+	return ret;
+}
+
+static void ism_vfio_pci_remove(struct pci_dev *pdev)
+{
+	struct vfio_pci_core_device *core_device;
+	struct ism_vfio_pci_core_device *ivpcd;
+
+	core_device = dev_get_drvdata(&pdev->dev);
+	ivpcd = container_of(core_device, struct ism_vfio_pci_core_device,
+			     core_device);
+
+	vfio_pci_core_unregister_device(&ivpcd->core_device);
+	vfio_put_device(&ivpcd->core_device.vdev);
+}
+
+static const struct pci_device_id ism_device_table[] = {
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_IBM,
+					  PCI_DEVICE_ID_IBM_ISM) },
+	{}
+};
+MODULE_DEVICE_TABLE(pci, ism_device_table);
+
+static struct pci_driver ism_vfio_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = ism_device_table,
+	.probe = ism_vfio_pci_probe,
+	.remove = ism_vfio_pci_remove,
+	.driver_managed_dma = true,
+};
+
+module_pci_driver(ism_vfio_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("vfio-pci variant driver for the IBM Internal Shared Memory (ISM) device");
+MODULE_AUTHOR("IBM Corporation");
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index dc4e510e6e1bf4753e1d9005e0054399a639ea12..c7341a2d072b058965135a3d225894d74379e12e 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1995,6 +1995,7 @@ ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 
 	return done;
 }
+EXPORT_SYMBOL(vfio_pci_config_rw);
 
 /**
  * vfio_pci_core_range_intersect_range() - Determine overlap between a buffer

-- 
2.51.0