@@ -2425,6 +2425,14 @@ F: drivers/net/wan/pc300too.c
F: drivers/net/wan/pci200syn.c
F: drivers/net/wan/wanxl*
+GENERIC UIO DRIVER FOR PCI DEVICES
+P: Michael S. Tsirkin
+M: mst@redhat.com
+L: kvm@vger.kernel.org
+L: linux-kernel@vger.kernel.org
+S: Supported
+F: drivers/uio/uio_pci_generic.c
+
GFS2 FILE SYSTEM
P: Steven Whitehouse
M: swhiteho@redhat.com
@@ -89,4 +89,14 @@ config UIO_SERCOS3
If you compile this as a module, it will be called uio_sercos3.
+config UIO_PCI_GENERIC
+ tristate "Generic driver for PCI 2.3 and PCI Express cards"
+ depends on PCI
+ default n
+ help
+ Generic driver that you can bind, dynamically, to any
+ PCI 2.3 compliant and PCI Express card. It is useful,
+ primarily, for virtualization scenarios.
+ If you compile this as a module, it will be called uio_pci_generic.
+
endif
@@ -5,3 +5,4 @@ obj-$(CONFIG_UIO_PDRV_GENIRQ) += uio_pdrv_genirq.o
obj-$(CONFIG_UIO_SMX) += uio_smx.o
obj-$(CONFIG_UIO_AEC) += uio_aec.o
obj-$(CONFIG_UIO_SERCOS3) += uio_sercos3.o
+obj-$(CONFIG_UIO_PCI_GENERIC) += uio_pci_generic.o
new file mode 100644
@@ -0,0 +1,206 @@
+/* uio_pci_generic - generic UIO driver for PCI 2.3 devices
+ *
+ * Copyright (C) 2009 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Since the driver does not declare any device ids, you must allocate
+ * id and bind the device to the driver yourself. For example:
+ *
+ * # echo "8086 10f5" > /sys/bus/pci/drivers/uio_pci_generic/new_id
+ * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/e1000e/unbind
+ * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/uio_pci_generic/bind
+ * # ls -l /sys/bus/pci/devices/0000:00:19.0/driver
+ * .../0000:00:19.0/driver -> ../../../bus/pci/drivers/uio_pci_generic
+ *
+ * Driver won't bind to devices which do not support the Interrupt Disable Bit
+ * in the command register. All devices compliant to PCI 2.3 (circa 2002) and
+ * all compliant PCI Express devices should support this bit.
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/uio_driver.h>
+#include <linux/spinlock.h>
+
+#define DRIVER_VERSION "0.01.0"
+#define DRIVER_AUTHOR "Michael S. Tsirkin <mst@redhat.com>"
+#define DRIVER_DESC "Generic UIO driver for PCI 2.3 devices"
+
+struct uio_pci_generic_dev {
+ struct uio_info info;
+ struct pci_dev *pdev;
+ spinlock_t lock; /* guards command register accesses */
+};
+
+static inline struct uio_pci_generic_dev *
+to_uio_pci_generic_dev(struct uio_info *info)
+{
+ return container_of(info, struct uio_pci_generic_dev, info);
+}
+
+/* Interrupt handler. Read/modify/write the command register to disable
+ * the interrupt. */
+static irqreturn_t irqhandler(int irq, struct uio_info *info)
+{
+ struct uio_pci_generic_dev *gdev = to_uio_pci_generic_dev(info);
+ struct pci_dev *pdev = gdev->pdev;
+ irqreturn_t ret = IRQ_NONE;
+ u32 cmd_status_dword;
+ u16 origcmd, newcmd, status;
+
+ /* We do a single dword read to retrieve both command and status.
+ * Document assumptions that make this possible. */
+ BUILD_BUG_ON(PCI_COMMAND % 4);
+ BUILD_BUG_ON(PCI_COMMAND + 2 != PCI_STATUS);
+
+ spin_lock_irq(&gdev->lock);
+ pci_block_user_cfg_access(pdev);
+
+ /* Read both command and status registers in a single 32-bit operation.
+ * Note: we could cache the value for command and move the status read
+ * out of the lock if there was a way to get notified of user changes
+ * to command register through sysfs. Should be good for shared irqs. */
+ pci_read_config_dword(pdev, PCI_COMMAND, &cmd_status_dword);
+ origcmd = cmd_status_dword;
+ status = cmd_status_dword >> 16;
+
+ /* Check interrupt status register to see whether our device
+ * triggered the interrupt. */
+ if (!(status & PCI_STATUS_INTERRUPT))
+ goto done;
+
+ /* We triggered the interrupt, disable it. */
+ newcmd = origcmd | PCI_COMMAND_INTX_DISABLE;
+ if (newcmd != origcmd)
+ pci_write_config_word(pdev, PCI_COMMAND, newcmd);
+
+ /* UIO core will signal the user process. */
+ ret = IRQ_HANDLED;
+done:
+
+ pci_unblock_user_cfg_access(pdev);
+ spin_unlock_irq(&gdev->lock);
+ return ret;
+}
+
+/* Verify that the device supports Interrupt Disable bit in command register,
+ * per PCI 2.3, by flipping this bit and reading it back: this bit was readonly
+ * in PCI 2.2. */
+static int __devinit verify_pci_2_3(struct pci_dev *pdev)
+{
+ u16 orig, new;
+ int err = 0;
+
+ pci_block_user_cfg_access(pdev);
+ pci_read_config_word(pdev, PCI_COMMAND, &orig);
+ pci_write_config_word(pdev, PCI_COMMAND,
+ orig ^ PCI_COMMAND_INTX_DISABLE);
+ pci_read_config_word(pdev, PCI_COMMAND, &new);
+ /* There's no way to protect against
+ * hardware bugs or detect them reliably, but as long as we know
+ * what the value should be, let's go ahead and check it. */
+ if ((new ^ orig) & ~PCI_COMMAND_INTX_DISABLE) {
+ err = -EBUSY;
+ dev_err(&pdev->dev, "Command changed from 0x%x to 0x%x: "
+ "driver or HW bug?\n", orig, new);
+ goto err;
+ }
+ if (!((new ^ orig) & PCI_COMMAND_INTX_DISABLE)) {
+ dev_warn(&pdev->dev, "Device does not support "
+ "disabling interrupts: unable to bind.\n");
+ err = -ENODEV;
+ goto err;
+ }
+ /* Now restore the original value. */
+ pci_write_config_word(pdev, PCI_COMMAND, orig);
+err:
+ pci_unblock_user_cfg_access(pdev);
+ return err;
+}
+
+static int __devinit probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ struct uio_pci_generic_dev *gdev;
+ int err;
+
+ if (!pdev->irq) {
+ dev_warn(&pdev->dev, "No IRQ assigned to device: "
+ "no support for interrupts?\n");
+ return -ENODEV;
+ }
+
+ err = pci_enable_device(pdev);
+ if (err) {
+ dev_err(&pdev->dev, "%s: pci_enable_device failed: %d\n",
+ __func__, err);
+ return err;
+ }
+
+ err = verify_pci_2_3(pdev);
+ if (err)
+ goto err_verify;
+
+ gdev = kzalloc(sizeof(struct uio_pci_generic_dev), GFP_KERNEL);
+ if (!gdev) {
+ err = -ENOMEM;
+ goto err_alloc;
+ }
+
+ gdev->info.name = "uio_pci_generic";
+ gdev->info.version = "0.01";
+ gdev->info.irq = pdev->irq;
+ gdev->info.irq_flags = IRQF_SHARED;
+ gdev->info.handler = irqhandler;
+ gdev->pdev = pdev;
+ spin_lock_init(&gdev->lock);
+
+ if (uio_register_device(&pdev->dev, &gdev->info))
+ goto err_register;
+ pci_set_drvdata(pdev, gdev);
+
+ return 0;
+err_register:
+ kfree(gdev);
+err_verify:
+ pci_disable_device(pdev);
+ return err;
+}
+
+static void remove(struct pci_dev *pdev)
+{
+ struct uio_pci_generic_dev *gdev = pci_get_drvdata(pdev);
+
+ uio_unregister_device(&gdev->info);
+ pci_disable_device(pdev);
+ kfree(gdev);
+}
+
+static struct pci_driver driver = {
+ .name = "uio_pci_generic",
+ .id_table = NULL, /* only dynamic id's */
+ .probe = probe,
+ .remove = remove,
+};
+
+static int __init init(void)
+{
+ info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+ return pci_register_driver(&driver);
+}
+
+static void __exit cleanup(void)
+{
+ pci_unregister_driver(&driver);
+}
+
+module_init(init);
+module_exit(cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
@@ -42,6 +42,7 @@
#define PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */
#define PCI_STATUS 0x06 /* 16 bits */
+#define PCI_STATUS_INTERRUPT 0x08 /* Interrupt status */
#define PCI_STATUS_CAP_LIST 0x10 /* Support Capability List */
#define PCI_STATUS_66MHZ 0x20 /* Support 66 Mhz PCI 2.1 bus */
#define PCI_STATUS_UDF 0x40 /* Support User Definable Features [obsolete] */
This adds a generic uio driver that can bind to any PCI device. First user will be virtualization where a qemu userspace process needs to give guest OS access to the device. Interrupts are handled using the Interrupt Disable bit in the PCI command register and Interrupt Status bit in the PCI status register. All devices compliant to PCI 2.3 (circa 2002) and all compliant PCI Express devices should support these bits. Driver detects this support, and won't bind to devices which do not support the Interrupt Disable Bit in the command register. It's expected that more features of interest to virtualization will be added to this driver in the future. Possibilities are: mmap for device resources, MSI/MSI-X, eventfd (to interface with kvm), iommu. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> --- This is intended to solve the problem that shared interrupts do not work with assigned devices. Please take a look before this goes out to lkml. Changes since v1: - some naming changes - do a single read to get both command and status register - remove irqcontrol: user can enable interrupts by writing command register directly - don't claim resources as we don't support mmap yet, but note the intent to do so in the commit log MAINTAINERS | 8 ++ drivers/uio/Kconfig | 10 ++ drivers/uio/Makefile | 1 + drivers/uio/uio_pci_generic.c | 206 +++++++++++++++++++++++++++++++++++++++++ include/linux/pci_regs.h | 1 + 5 files changed, 226 insertions(+), 0 deletions(-) create mode 100644 drivers/uio/uio_pci_generic.c