diff options
Diffstat (limited to 'drivers/vfio')
| -rw-r--r-- | drivers/vfio/Kconfig | 6 | ||||
| -rw-r--r-- | drivers/vfio/Makefile | 1 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci.c | 167 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_private.h | 3 | ||||
| -rw-r--r-- | drivers/vfio/vfio_iommu_spapr_tce.c | 17 | ||||
| -rw-r--r-- | drivers/vfio/vfio_spapr_eeh.c | 100 |
6 files changed, 276 insertions, 18 deletions
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index af7b204b9215..d8c57636b9ce 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -8,11 +8,17 @@ config VFIO_IOMMU_SPAPR_TCE depends on VFIO && SPAPR_TCE_IOMMU default n +config VFIO_SPAPR_EEH + tristate + depends on EEH && VFIO_IOMMU_SPAPR_TCE + default n + menuconfig VFIO tristate "VFIO Non-Privileged userspace driver framework" depends on IOMMU_API select VFIO_IOMMU_TYPE1 if X86 select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES) + select VFIO_SPAPR_EEH if (PPC_POWERNV || PPC_PSERIES) select ANON_INODES help VFIO provides a framework for secure userspace device drivers. diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile index 72bfabc8629e..0b035b12600a 100644 --- a/drivers/vfio/Makefile +++ b/drivers/vfio/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_VFIO) += vfio.o obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o +obj-$(CONFIG_VFIO_SPAPR_EEH) += vfio_spapr_eeh.o obj-$(CONFIG_VFIO_PCI) += pci/ diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 010e0f8b8e4f..f7825332a325 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -37,6 +37,10 @@ module_param_named(nointxmask, nointxmask, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(nointxmask, "Disable support for PCI 2.3 style INTx masking. If this resolves problems for specific devices, report lspci -vvvxxx to linux-pci@vger.kernel.org so the device can be fixed automatically via the broken_intx_masking flag."); +static DEFINE_MUTEX(driver_lock); + +static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev); + static int vfio_pci_enable(struct vfio_pci_device *vdev) { struct pci_dev *pdev = vdev->pdev; @@ -44,6 +48,9 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev) u16 cmd; u8 msix_pos; + /* Don't allow our initial saved state to include busmaster */ + pci_clear_master(pdev); + ret = pci_enable_device(pdev); if (ret) return ret; @@ -99,7 +106,8 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) struct pci_dev *pdev = vdev->pdev; int bar; - pci_disable_device(pdev); + /* Stop the device from further DMA */ + pci_clear_master(pdev); vfio_pci_set_irqs_ioctl(vdev, VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, @@ -117,6 +125,8 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) vdev->barmap[bar] = NULL; } + vdev->needs_reset = true; + /* * If we have saved state, restore it. If we can reset the device, * even better. Resetting with current state seems better than @@ -128,7 +138,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) __func__, dev_name(&pdev->dev)); if (!vdev->reset_works) - return; + goto out; pci_save_state(pdev); } @@ -148,17 +158,29 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) if (ret) pr_warn("%s: Failed to reset device %s (%d)\n", __func__, dev_name(&pdev->dev), ret); + else + vdev->needs_reset = false; } pci_restore_state(pdev); +out: + pci_disable_device(pdev); + + vfio_pci_try_bus_reset(vdev); } static void vfio_pci_release(void *device_data) { struct vfio_pci_device *vdev = device_data; - if (atomic_dec_and_test(&vdev->refcnt)) + mutex_lock(&driver_lock); + + if (!(--vdev->refcnt)) { + vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_disable(vdev); + } + + mutex_unlock(&driver_lock); module_put(THIS_MODULE); } @@ -166,19 +188,26 @@ static void vfio_pci_release(void *device_data) static int vfio_pci_open(void *device_data) { struct vfio_pci_device *vdev = device_data; + int ret = 0; if (!try_module_get(THIS_MODULE)) return -ENODEV; - if (atomic_inc_return(&vdev->refcnt) == 1) { - int ret = vfio_pci_enable(vdev); - if (ret) { - module_put(THIS_MODULE); - return ret; - } - } + mutex_lock(&driver_lock); - return 0; + if (!vdev->refcnt) { + ret = vfio_pci_enable(vdev); + if (ret) + goto error; + + vfio_spapr_pci_eeh_open(vdev->pdev); + } + vdev->refcnt++; +error: + mutex_unlock(&driver_lock); + if (ret) + module_put(THIS_MODULE); + return ret; } static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type) @@ -833,7 +862,6 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) vdev->irq_type = VFIO_PCI_NUM_IRQS; mutex_init(&vdev->igate); spin_lock_init(&vdev->irqlock); - atomic_set(&vdev->refcnt, 0); ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) { @@ -848,12 +876,15 @@ static void vfio_pci_remove(struct pci_dev *pdev) { struct vfio_pci_device *vdev; + mutex_lock(&driver_lock); + vdev = vfio_del_group_dev(&pdev->dev); - if (!vdev) - return; + if (vdev) { + iommu_group_put(pdev->dev.iommu_group); + kfree(vdev); + } - iommu_group_put(pdev->dev.iommu_group); - kfree(vdev); + mutex_unlock(&driver_lock); } static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, @@ -896,6 +927,110 @@ static struct pci_driver vfio_pci_driver = { .err_handler = &vfio_err_handlers, }; +/* + * Test whether a reset is necessary and possible. We mark devices as + * needs_reset when they are released, but don't have a function-local reset + * available. If any of these exist in the affected devices, we want to do + * a bus/slot reset. We also need all of the affected devices to be unused, + * so we abort if any device has a non-zero refcnt. driver_lock prevents a + * device from being opened during the scan or unbound from vfio-pci. + */ +static int vfio_pci_test_bus_reset(struct pci_dev *pdev, void *data) +{ + bool *needs_reset = data; + struct pci_driver *pci_drv = ACCESS_ONCE(pdev->driver); + int ret = -EBUSY; + + if (pci_drv == &vfio_pci_driver) { + struct vfio_device *device; + struct vfio_pci_device *vdev; + + device = vfio_device_get_from_dev(&pdev->dev); + if (!device) + return ret; + + vdev = vfio_device_data(device); + if (vdev) { + if (vdev->needs_reset) + *needs_reset = true; + + if (!vdev->refcnt) + ret = 0; + } + + vfio_device_put(device); + } + + /* + * TODO: vfio-core considers groups to be viable even if some devices + * are attached to known drivers, like pci-stub or pcieport. We can't + * freeze devices from being unbound to those drivers like we can + * here though, so it would be racy to test for them. We also can't + * use device_lock() to prevent changes as that would interfere with + * PCI-core taking device_lock during bus reset. For now, we require + * devices to be bound to vfio-pci to get a bus/slot reset on release. + */ + + return ret; +} + +/* Clear needs_reset on all affected devices after successful bus/slot reset */ +static int vfio_pci_clear_needs_reset(struct pci_dev *pdev, void *data) +{ + struct pci_driver *pci_drv = ACCESS_ONCE(pdev->driver); + + if (pci_drv == &vfio_pci_driver) { + struct vfio_device *device; + struct vfio_pci_device *vdev; + + device = vfio_device_get_from_dev(&pdev->dev); + if (!device) + return 0; + + vdev = vfio_device_data(device); + if (vdev) + vdev->needs_reset = false; + + vfio_device_put(device); + } + + return 0; +} + +/* + * Attempt to do a bus/slot reset if there are devices affected by a reset for + * this device that are needs_reset and all of the affected devices are unused + * (!refcnt). Callers of this function are required to hold driver_lock such + * that devices can not be unbound from vfio-pci or opened by a user while we + * test for and perform a bus/slot reset. + */ +static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev) +{ + bool needs_reset = false, slot = false; + int ret; + + if (!pci_probe_reset_slot(vdev->pdev->slot)) + slot = true; + else if (pci_probe_reset_bus(vdev->pdev->bus)) + return; + + if (vfio_pci_for_each_slot_or_bus(vdev->pdev, + vfio_pci_test_bus_reset, + &needs_reset, slot) || !needs_reset) + return; + + if (slot) + ret = pci_try_reset_slot(vdev->pdev->slot); + else + ret = pci_try_reset_bus(vdev->pdev->bus); + + if (ret) + return; + + vfio_pci_for_each_slot_or_bus(vdev->pdev, + vfio_pci_clear_needs_reset, NULL, slot); +} + static void __exit vfio_pci_cleanup(void) { pci_unregister_driver(&vfio_pci_driver); diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 9c6d5d0f3b02..671c17a6e6d0 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -54,8 +54,9 @@ struct vfio_pci_device { bool extended_caps; bool bardirty; bool has_vga; + bool needs_reset; struct pci_saved_state *pci_saved_state; - atomic_t refcnt; + int refcnt; struct eventfd_ctx *err_trigger; }; diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index a84788ba662c..730b4ef3e0cc 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -156,7 +156,16 @@ static long tce_iommu_ioctl(void *iommu_data, switch (cmd) { case VFIO_CHECK_EXTENSION: - return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0; + switch (arg) { + case VFIO_SPAPR_TCE_IOMMU: + ret = 1; + break; + default: + ret = vfio_spapr_iommu_eeh_ioctl(NULL, cmd, arg); + break; + } + + return (ret < 0) ? 0 : ret; case VFIO_IOMMU_SPAPR_TCE_GET_INFO: { struct vfio_iommu_spapr_tce_info info; @@ -283,6 +292,12 @@ static long tce_iommu_ioctl(void *iommu_data, tce_iommu_disable(container); mutex_unlock(&container->lock); return 0; + case VFIO_EEH_PE_OP: + if (!container->tbl || !container->tbl->it_group) + return -ENODEV; + + return vfio_spapr_iommu_eeh_ioctl(container->tbl->it_group, + cmd, arg); } return -ENOTTY; diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c new file mode 100644 index 000000000000..86dfceb9201f --- /dev/null +++ b/drivers/vfio/vfio_spapr_eeh.c @@ -0,0 +1,100 @@ +/* + * EEH functionality support for VFIO devices. The feature is only + * available on sPAPR compatible platforms. + * + * Copyright Gavin Shan, IBM Corporation 2014. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/uaccess.h> +#include <linux/vfio.h> +#include <asm/eeh.h> + +#define DRIVER_VERSION "0.1" +#define DRIVER_AUTHOR "Gavin Shan, IBM Corporation" +#define DRIVER_DESC "VFIO IOMMU SPAPR EEH" + +/* We might build address mapping here for "fast" path later */ +void vfio_spapr_pci_eeh_open(struct pci_dev *pdev) +{ + eeh_dev_open(pdev); +} +EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_open); + +void vfio_spapr_pci_eeh_release(struct pci_dev *pdev) +{ + eeh_dev_release(pdev); +} +EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_release); + +long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, + unsigned int cmd, unsigned long arg) +{ + struct eeh_pe *pe; + struct vfio_eeh_pe_op op; + unsigned long minsz; + long ret = -EINVAL; + + switch (cmd) { + case VFIO_CHECK_EXTENSION: + if (arg == VFIO_EEH) + ret = eeh_enabled() ? 1 : 0; + else + ret = 0; + break; + case VFIO_EEH_PE_OP: + pe = eeh_iommu_group_to_pe(group); + if (!pe) + return -ENODEV; + + minsz = offsetofend(struct vfio_eeh_pe_op, op); + if (copy_from_user(&op, (void __user *)arg, minsz)) + return -EFAULT; + if (op.argsz < minsz || op.flags) + return -EINVAL; + + switch (op.op) { + case VFIO_EEH_PE_DISABLE: + ret = eeh_pe_set_option(pe, EEH_OPT_DISABLE); + break; + case VFIO_EEH_PE_ENABLE: + ret = eeh_pe_set_option(pe, EEH_OPT_ENABLE); + break; + case VFIO_EEH_PE_UNFREEZE_IO: + ret = eeh_pe_set_option(pe, EEH_OPT_THAW_MMIO); + break; + case VFIO_EEH_PE_UNFREEZE_DMA: + ret = eeh_pe_set_option(pe, EEH_OPT_THAW_DMA); + break; + case VFIO_EEH_PE_GET_STATE: + ret = eeh_pe_get_state(pe); + break; + case VFIO_EEH_PE_RESET_DEACTIVATE: + ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE); + break; + case VFIO_EEH_PE_RESET_HOT: + ret = eeh_pe_reset(pe, EEH_RESET_HOT); + break; + case VFIO_EEH_PE_RESET_FUNDAMENTAL: + ret = eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL); + break; + case VFIO_EEH_PE_CONFIGURE: + ret = eeh_pe_configure(pe); + break; + default: + ret = -EINVAL; + } + } + + return ret; +} +EXPORT_SYMBOL(vfio_spapr_iommu_eeh_ioctl); + +MODULE_VERSION(DRIVER_VERSION); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); |
