diff options
Diffstat (limited to 'drivers/pci/iov.c')
| -rw-r--r-- | drivers/pci/iov.c | 762 |
1 files changed, 674 insertions, 88 deletions
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 120485d6f352..00784a60ba80 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -1,23 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * drivers/pci/iov.c - * - * Copyright (C) 2009 Intel Corporation, Yu Zhao <yu.zhao@intel.com> - * - * PCI Express I/O Virtualization (IOV) support. + * PCI Express I/O Virtualization (IOV) support * Single Root IOV 1.0 * Address Translation Service 1.0 + * + * Copyright (C) 2009 Intel Corporation, Yu Zhao <yu.zhao@intel.com> */ +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/log2.h> #include <linux/pci.h> +#include <linux/sizes.h> #include <linux/slab.h> -#include <linux/mutex.h> #include <linux/export.h> #include <linux/string.h> #include <linux/delay.h> -#include <linux/pci-ats.h> +#include <asm/div64.h> #include "pci.h" -#define VIRTFN_ID_LEN 16 +#define VIRTFN_ID_LEN 17 /* "virtfn%u\0" for 2^32 - 1 */ int pci_iov_virtfn_bus(struct pci_dev *dev, int vf_id) { @@ -34,6 +36,49 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int vf_id) return (dev->devfn + dev->sriov->offset + dev->sriov->stride * vf_id) & 0xff; } +EXPORT_SYMBOL_GPL(pci_iov_virtfn_devfn); + +int pci_iov_vf_id(struct pci_dev *dev) +{ + struct pci_dev *pf; + + if (!dev->is_virtfn) + return -EINVAL; + + pf = pci_physfn(dev); + return (pci_dev_id(dev) - (pci_dev_id(pf) + pf->sriov->offset)) / + pf->sriov->stride; +} +EXPORT_SYMBOL_GPL(pci_iov_vf_id); + +/** + * pci_iov_get_pf_drvdata - Return the drvdata of a PF + * @dev: VF pci_dev + * @pf_driver: Device driver required to own the PF + * + * This must be called from a context that ensures that a VF driver is attached. + * The value returned is invalid once the VF driver completes its remove() + * callback. + * + * Locking is achieved by the driver core. A VF driver cannot be probed until + * pci_enable_sriov() is called and pci_disable_sriov() does not return until + * all VF drivers have completed their remove(). + * + * The PF driver must call pci_disable_sriov() before it begins to destroy the + * drvdata. + */ +void *pci_iov_get_pf_drvdata(struct pci_dev *dev, struct pci_driver *pf_driver) +{ + struct pci_dev *pf_dev; + + if (!dev->is_virtfn) + return ERR_PTR(-EINVAL); + pf_dev = dev->physfn; + if (pf_dev->driver != pf_driver) + return ERR_PTR(-EINVAL); + return pci_get_drvdata(pf_dev); +} +EXPORT_SYMBOL_GPL(pci_iov_get_pf_drvdata); /* * Per SR-IOV spec sec 3.3.10 and 3.3.11, First VF Offset and VF Stride may @@ -110,76 +155,244 @@ resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno) if (!dev->is_physfn) return 0; - return dev->sriov->barsz[resno - PCI_IOV_RESOURCES]; + return dev->sriov->barsz[pci_resource_num_to_vf_bar(resno)]; } -int pci_iov_add_virtfn(struct pci_dev *dev, int id, int reset) +void pci_iov_resource_set_size(struct pci_dev *dev, int resno, int size) +{ + if (!pci_resource_is_iov(resno)) { + pci_warn(dev, "%s is not an IOV resource\n", + pci_resource_name(dev, resno)); + return; + } + + resno = pci_resource_num_to_vf_bar(resno); + dev->sriov->barsz[resno] = pci_rebar_size_to_bytes(size); +} + +bool pci_iov_is_memory_decoding_enabled(struct pci_dev *dev) +{ + u16 cmd; + + pci_read_config_word(dev, dev->sriov->pos + PCI_SRIOV_CTRL, &cmd); + + return cmd & PCI_SRIOV_CTRL_MSE; +} + +static void pci_read_vf_config_common(struct pci_dev *virtfn) +{ + struct pci_dev *physfn = virtfn->physfn; + + /* + * Some config registers are the same across all associated VFs. + * Read them once from VF0 so we can skip reading them from the + * other VFs. + * + * PCIe r4.0, sec 9.3.4.1, technically doesn't require all VFs to + * have the same Revision ID and Subsystem ID, but we assume they + * do. + */ + pci_read_config_dword(virtfn, PCI_CLASS_REVISION, + &physfn->sriov->class); + pci_read_config_byte(virtfn, PCI_HEADER_TYPE, + &physfn->sriov->hdr_type); + pci_read_config_word(virtfn, PCI_SUBSYSTEM_VENDOR_ID, + &physfn->sriov->subsystem_vendor); + pci_read_config_word(virtfn, PCI_SUBSYSTEM_ID, + &physfn->sriov->subsystem_device); +} + +int pci_iov_sysfs_link(struct pci_dev *dev, + struct pci_dev *virtfn, int id) { - int i; - int rc = -ENOMEM; - u64 size; char buf[VIRTFN_ID_LEN]; - struct pci_dev *virtfn; - struct resource *res; - struct pci_sriov *iov = dev->sriov; - struct pci_bus *bus; + int rc; - bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id)); - if (!bus) + sprintf(buf, "virtfn%u", id); + rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf); + if (rc) goto failed; + rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn"); + if (rc) + goto failed1; + + kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE); + + return 0; + +failed1: + sysfs_remove_link(&dev->dev.kobj, buf); +failed: + return rc; +} + +#ifdef CONFIG_PCI_MSI +static ssize_t sriov_vf_total_msix_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + u32 vf_total_msix = 0; + + device_lock(dev); + if (!pdev->driver || !pdev->driver->sriov_get_vf_total_msix) + goto unlock; + + vf_total_msix = pdev->driver->sriov_get_vf_total_msix(pdev); +unlock: + device_unlock(dev); + return sysfs_emit(buf, "%u\n", vf_total_msix); +} +static DEVICE_ATTR_RO(sriov_vf_total_msix); + +static ssize_t sriov_vf_msix_count_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pci_dev *vf_dev = to_pci_dev(dev); + struct pci_dev *pdev = pci_physfn(vf_dev); + int val, ret = 0; + + if (kstrtoint(buf, 0, &val) < 0) + return -EINVAL; + + if (val < 0) + return -EINVAL; + + device_lock(&pdev->dev); + if (!pdev->driver || !pdev->driver->sriov_set_msix_vec_count) { + ret = -EOPNOTSUPP; + goto err_pdev; + } + + device_lock(&vf_dev->dev); + if (vf_dev->driver) { + /* + * A driver is already attached to this VF and has configured + * itself based on the current MSI-X vector count. Changing + * the vector size could mess up the driver, so block it. + */ + ret = -EBUSY; + goto err_dev; + } + + ret = pdev->driver->sriov_set_msix_vec_count(vf_dev, val); + +err_dev: + device_unlock(&vf_dev->dev); +err_pdev: + device_unlock(&pdev->dev); + return ret ? : count; +} +static DEVICE_ATTR_WO(sriov_vf_msix_count); +#endif + +static struct attribute *sriov_vf_dev_attrs[] = { +#ifdef CONFIG_PCI_MSI + &dev_attr_sriov_vf_msix_count.attr, +#endif + NULL, +}; + +static umode_t sriov_vf_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pci_dev *pdev = to_pci_dev(dev); + + if (!pdev->is_virtfn) + return 0; + + return a->mode; +} + +const struct attribute_group sriov_vf_dev_attr_group = { + .attrs = sriov_vf_dev_attrs, + .is_visible = sriov_vf_attrs_are_visible, +}; + +static struct pci_dev *pci_iov_scan_device(struct pci_dev *dev, int id, + struct pci_bus *bus) +{ + struct pci_sriov *iov = dev->sriov; + struct pci_dev *virtfn; + int rc; virtfn = pci_alloc_dev(bus); if (!virtfn) - goto failed0; + return ERR_PTR(-ENOMEM); virtfn->devfn = pci_iov_virtfn_devfn(dev, id); virtfn->vendor = dev->vendor; - pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_DID, &virtfn->device); + virtfn->device = iov->vf_device; + virtfn->is_virtfn = 1; + virtfn->physfn = pci_dev_get(dev); + virtfn->no_command_memory = 1; + + if (id == 0) + pci_read_vf_config_common(virtfn); + rc = pci_setup_device(virtfn); - if (rc) + if (rc) { + pci_dev_put(dev); + pci_bus_put(virtfn->bus); + kfree(virtfn); + return ERR_PTR(rc); + } + + return virtfn; +} + +int pci_iov_add_virtfn(struct pci_dev *dev, int id) +{ + struct pci_bus *bus; + struct pci_dev *virtfn; + struct resource *res; + int rc, i; + u64 size; + + bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id)); + if (!bus) { + rc = -ENOMEM; + goto failed; + } + + virtfn = pci_iov_scan_device(dev, id, bus); + if (IS_ERR(virtfn)) { + rc = PTR_ERR(virtfn); goto failed0; + } virtfn->dev.parent = dev->dev.parent; - virtfn->physfn = pci_dev_get(dev); - virtfn->is_virtfn = 1; virtfn->multifunction = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; + int idx = pci_resource_num_from_vf_bar(i); + + res = &dev->resource[idx]; if (!res->parent) continue; virtfn->resource[i].name = pci_name(virtfn); virtfn->resource[i].flags = res->flags; - size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); - virtfn->resource[i].start = res->start + size * id; - virtfn->resource[i].end = virtfn->resource[i].start + size - 1; + size = pci_iov_resource_size(dev, idx); + resource_set_range(&virtfn->resource[i], + res->start + size * id, size); rc = request_resource(res, &virtfn->resource[i]); BUG_ON(rc); } - if (reset) - __pci_reset_function(virtfn); - pci_device_add(virtfn, virtfn->bus); - - pci_bus_add_device(virtfn); - sprintf(buf, "virtfn%u", id); - rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf); + rc = pci_iov_sysfs_link(dev, virtfn, id); if (rc) goto failed1; - rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn"); - if (rc) - goto failed2; - kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE); + pci_bus_add_device(virtfn); return 0; -failed2: - sysfs_remove_link(&dev->dev.kobj, buf); failed1: - pci_dev_put(dev); pci_stop_and_remove_bus_device(virtfn); + pci_dev_put(dev); failed0: virtfn_remove_bus(dev->bus, bus); failed: @@ -187,7 +400,7 @@ failed: return rc; } -void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset) +void pci_iov_remove_virtfn(struct pci_dev *dev, int id) { char buf[VIRTFN_ID_LEN]; struct pci_dev *virtfn; @@ -198,11 +411,6 @@ void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset) if (!virtfn) return; - if (reset) { - device_release_driver(&virtfn->dev); - __pci_reset_function(virtfn); - } - sprintf(buf, "virtfn%u", id); sysfs_remove_link(&dev->dev.kobj, buf); /* @@ -221,6 +429,188 @@ void pci_iov_remove_virtfn(struct pci_dev *dev, int id, int reset) pci_dev_put(dev); } +static ssize_t sriov_totalvfs_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return sysfs_emit(buf, "%u\n", pci_sriov_get_totalvfs(pdev)); +} + +static ssize_t sriov_numvfs_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + u16 num_vfs; + + /* Serialize vs sriov_numvfs_store() so readers see valid num_VFs */ + device_lock(&pdev->dev); + num_vfs = pdev->sriov->num_VFs; + device_unlock(&pdev->dev); + + return sysfs_emit(buf, "%u\n", num_vfs); +} + +/* + * num_vfs > 0; number of VFs to enable + * num_vfs = 0; disable all VFs + * + * Note: SRIOV spec does not allow partial VF + * disable, so it's all or none. + */ +static ssize_t sriov_numvfs_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret = 0; + u16 num_vfs; + + if (kstrtou16(buf, 0, &num_vfs) < 0) + return -EINVAL; + + if (num_vfs > pci_sriov_get_totalvfs(pdev)) + return -ERANGE; + + device_lock(&pdev->dev); + + if (num_vfs == pdev->sriov->num_VFs) + goto exit; + + /* is PF driver loaded */ + if (!pdev->driver) { + pci_info(pdev, "no driver bound to device; cannot configure SR-IOV\n"); + ret = -ENOENT; + goto exit; + } + + /* is PF driver loaded w/callback */ + if (!pdev->driver->sriov_configure) { + pci_info(pdev, "driver does not support SR-IOV configuration via sysfs\n"); + ret = -ENOENT; + goto exit; + } + + if (num_vfs == 0) { + /* disable VFs */ + ret = pdev->driver->sriov_configure(pdev, 0); + goto exit; + } + + /* enable VFs */ + if (pdev->sriov->num_VFs) { + pci_warn(pdev, "%d VFs already enabled. Disable before enabling %d VFs\n", + pdev->sriov->num_VFs, num_vfs); + ret = -EBUSY; + goto exit; + } + + ret = pdev->driver->sriov_configure(pdev, num_vfs); + if (ret < 0) + goto exit; + + if (ret != num_vfs) + pci_warn(pdev, "%d VFs requested; only %d enabled\n", + num_vfs, ret); + +exit: + device_unlock(&pdev->dev); + + if (ret < 0) + return ret; + + return count; +} + +static ssize_t sriov_offset_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return sysfs_emit(buf, "%u\n", pdev->sriov->offset); +} + +static ssize_t sriov_stride_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return sysfs_emit(buf, "%u\n", pdev->sriov->stride); +} + +static ssize_t sriov_vf_device_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return sysfs_emit(buf, "%x\n", pdev->sriov->vf_device); +} + +static ssize_t sriov_drivers_autoprobe_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return sysfs_emit(buf, "%u\n", pdev->sriov->drivers_autoprobe); +} + +static ssize_t sriov_drivers_autoprobe_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pci_dev *pdev = to_pci_dev(dev); + bool drivers_autoprobe; + + if (kstrtobool(buf, &drivers_autoprobe) < 0) + return -EINVAL; + + pdev->sriov->drivers_autoprobe = drivers_autoprobe; + + return count; +} + +static DEVICE_ATTR_RO(sriov_totalvfs); +static DEVICE_ATTR_RW(sriov_numvfs); +static DEVICE_ATTR_RO(sriov_offset); +static DEVICE_ATTR_RO(sriov_stride); +static DEVICE_ATTR_RO(sriov_vf_device); +static DEVICE_ATTR_RW(sriov_drivers_autoprobe); + +static struct attribute *sriov_pf_dev_attrs[] = { + &dev_attr_sriov_totalvfs.attr, + &dev_attr_sriov_numvfs.attr, + &dev_attr_sriov_offset.attr, + &dev_attr_sriov_stride.attr, + &dev_attr_sriov_vf_device.attr, + &dev_attr_sriov_drivers_autoprobe.attr, +#ifdef CONFIG_PCI_MSI + &dev_attr_sriov_vf_total_msix.attr, +#endif + NULL, +}; + +static umode_t sriov_pf_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + + if (!dev_is_pf(dev)) + return 0; + + return a->mode; +} + +const struct attribute_group sriov_pf_dev_attr_group = { + .attrs = sriov_pf_dev_attrs, + .is_visible = sriov_pf_attrs_are_visible, +}; + int __weak pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) { return 0; @@ -231,6 +621,30 @@ int __weak pcibios_sriov_disable(struct pci_dev *pdev) return 0; } +static int sriov_add_vfs(struct pci_dev *dev, u16 num_vfs) +{ + unsigned int i; + int rc; + + if (dev->no_vf_scan) + return 0; + + pci_lock_rescan_remove(); + for (i = 0; i < num_vfs; i++) { + rc = pci_iov_add_virtfn(dev, i); + if (rc) + goto failed; + } + pci_unlock_rescan_remove(); + return 0; +failed: + while (i--) + pci_iov_remove_virtfn(dev, i); + pci_unlock_rescan_remove(); + + return rc; +} + static int sriov_enable(struct pci_dev *dev, int nr_virtfn) { int rc; @@ -260,25 +674,30 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - bars |= (1 << (i + PCI_IOV_RESOURCES)); - res = &dev->resource[i + PCI_IOV_RESOURCES]; + int idx = pci_resource_num_from_vf_bar(i); + resource_size_t vf_bar_sz = pci_iov_resource_size(dev, idx); + + bars |= (1 << idx); + res = &dev->resource[idx]; + if (vf_bar_sz * nr_virtfn > resource_size(res)) + continue; if (res->parent) nres++; } if (nres != iov->nres) { - dev_err(&dev->dev, "not enough MMIO resources for SR-IOV\n"); + pci_err(dev, "not enough MMIO resources for SR-IOV\n"); return -ENOMEM; } bus = pci_iov_virtfn_bus(dev, nr_virtfn - 1); if (bus > dev->bus->busn_res.end) { - dev_err(&dev->dev, "can't enable %d VFs (bus %02x out of range of %pR)\n", + pci_err(dev, "can't enable %d VFs (bus %02x out of range of %pR)\n", nr_virtfn, bus, &dev->bus->busn_res); return -ENOMEM; } if (pci_enable_resources(dev, bars)) { - dev_err(&dev->dev, "SR-IOV: IOV BARS not allocated\n"); + pci_err(dev, "SR-IOV: IOV BARS not allocated\n"); return -ENOMEM; } @@ -305,7 +724,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) rc = pcibios_sriov_enable(dev, initial); if (rc) { - dev_err(&dev->dev, "failure %d from pcibios_sriov_enable()\n", rc); + pci_err(dev, "failure %d from pcibios_sriov_enable()\n", rc); goto err_pcibios; } @@ -316,22 +735,15 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) msleep(100); pci_cfg_access_unlock(dev); - for (i = 0; i < initial; i++) { - rc = pci_iov_add_virtfn(dev, i, 0); - if (rc) - goto failed; - } + rc = sriov_add_vfs(dev, initial); + if (rc) + goto err_pcibios; kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE); iov->num_VFs = nr_virtfn; return 0; -failed: - while (i--) - pci_iov_remove_virtfn(dev, i, 0); - - pcibios_sriov_disable(dev); err_pcibios: iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE); pci_cfg_access_lock(dev); @@ -339,6 +751,8 @@ err_pcibios: ssleep(1); pci_cfg_access_unlock(dev); + pcibios_sriov_disable(dev); + if (iov->link != dev->devfn) sysfs_remove_link(&dev->dev.kobj, "dep_link"); @@ -346,25 +760,33 @@ err_pcibios: return rc; } -static void sriov_disable(struct pci_dev *dev) +static void sriov_del_vfs(struct pci_dev *dev) { + struct pci_sriov *iov = dev->sriov; int i; + + pci_lock_rescan_remove(); + for (i = 0; i < iov->num_VFs; i++) + pci_iov_remove_virtfn(dev, i); + pci_unlock_rescan_remove(); +} + +static void sriov_disable(struct pci_dev *dev) +{ struct pci_sriov *iov = dev->sriov; if (!iov->num_VFs) return; - for (i = 0; i < iov->num_VFs; i++) - pci_iov_remove_virtfn(dev, i, 0); - - pcibios_sriov_disable(dev); - + sriov_del_vfs(dev); iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE); pci_cfg_access_lock(dev); pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl); ssleep(1); pci_cfg_access_unlock(dev); + pcibios_sriov_disable(dev); + if (iov->link != dev->devfn) sysfs_remove_link(&dev->dev.kobj, "dep_link"); @@ -381,7 +803,9 @@ static int sriov_init(struct pci_dev *dev, int pos) u16 ctrl, total; struct pci_sriov *iov; struct resource *res; + const char *res_name; struct pci_dev *pdev; + u32 sriovbars[PCI_SRIOV_NUM_BARS]; pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl); if (ctrl & PCI_SRIOV_CTRL_VFE) { @@ -418,9 +842,17 @@ found: if (!iov) return -ENOMEM; + /* Sizing SR-IOV BARs with VF Enable cleared - no decode */ + __pci_size_stdbars(dev, PCI_SRIOV_NUM_BARS, + pos + PCI_SRIOV_BAR, sriovbars); + nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; + int idx = pci_resource_num_from_vf_bar(i); + + res = &dev->resource[idx]; + res_name = pci_resource_name(dev, idx); + /* * If it is already FIXED, don't change it, something * (perhaps EA or header fixups) wants it this way. @@ -429,7 +861,8 @@ found: bar64 = (res->flags & IORESOURCE_MEM_64) ? 1 : 0; else bar64 = __pci_read_base(dev, pci_bar_unknown, res, - pos + PCI_SRIOV_BAR + i * 4); + pos + PCI_SRIOV_BAR + i * 4, + &sriovbars[i]); if (!res->flags) continue; if (resource_size(res) & (PAGE_SIZE - 1)) { @@ -437,9 +870,9 @@ found: goto failed; } iov->barsz[i] = resource_size(res); - res->end = res->start + resource_size(res) * total - 1; - dev_info(&dev->dev, "VF(n) BAR%d space: %pR (contains BAR%d for %d VFs)\n", - i, res, i, total); + resource_set_size(res, resource_size(res) * total); + pci_info(dev, "%s %pR: contains BAR %d for %d VFs\n", + res_name, res, i, total); i += bar64; nres++; } @@ -448,6 +881,8 @@ found: iov->nres = nres; iov->ctrl = ctrl; iov->total_VFs = total; + iov->driver_max_VFs = total; + pci_read_config_word(dev, pos + PCI_SRIOV_VF_DID, &iov->vf_device); iov->pgsz = pgsz; iov->self = dev; iov->drivers_autoprobe = true; @@ -455,6 +890,7 @@ found: pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link); if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) iov->link = PCI_DEVFN(PCI_SLOT(dev->devfn), iov->link); + iov->vf_rebar_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_VF_REBAR); if (pdev) iov->dev = pci_dev_get(pdev); @@ -474,7 +910,7 @@ fail_max_buses: dev->is_physfn = 0; failed: for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; + res = &dev->resource[pci_resource_num_from_vf_bar(i)]; res->flags = 0; } @@ -493,6 +929,30 @@ static void sriov_release(struct pci_dev *dev) dev->sriov = NULL; } +static void sriov_restore_vf_rebar_state(struct pci_dev *dev) +{ + unsigned int pos, nbars, i; + u32 ctrl; + + pos = pci_iov_vf_rebar_cap(dev); + if (!pos) + return; + + pci_read_config_dword(dev, pos + PCI_VF_REBAR_CTRL, &ctrl); + nbars = FIELD_GET(PCI_VF_REBAR_CTRL_NBAR_MASK, ctrl); + + for (i = 0; i < nbars; i++, pos += 8) { + int bar_idx, size; + + pci_read_config_dword(dev, pos + PCI_VF_REBAR_CTRL, &ctrl); + bar_idx = FIELD_GET(PCI_VF_REBAR_CTRL_BAR_IDX, ctrl); + size = pci_rebar_bytes_to_size(dev->sriov->barsz[bar_idx]); + ctrl &= ~PCI_VF_REBAR_CTRL_BAR_SIZE; + ctrl |= FIELD_PREP(PCI_VF_REBAR_CTRL_BAR_SIZE, size); + pci_write_config_dword(dev, pos + PCI_VF_REBAR_CTRL, ctrl); + } +} + static void sriov_restore_state(struct pci_dev *dev) { int i; @@ -503,8 +963,16 @@ static void sriov_restore_state(struct pci_dev *dev) if (ctrl & PCI_SRIOV_CTRL_VFE) return; - for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++) - pci_update_resource(dev, i); + /* + * Restore PCI_SRIOV_CTRL_ARI before pci_iov_set_numvfs() because + * it reads offset & stride, which depend on PCI_SRIOV_CTRL_ARI. + */ + ctrl &= ~PCI_SRIOV_CTRL_ARI; + ctrl |= iov->ctrl & PCI_SRIOV_CTRL_ARI; + pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, ctrl); + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) + pci_update_resource(dev, pci_resource_num_from_vf_bar(i)); pci_write_config_dword(dev, iov->pos + PCI_SRIOV_SYS_PGSIZE, iov->pgsz); pci_iov_set_numvfs(dev, iov->num_VFs); @@ -544,6 +1012,22 @@ void pci_iov_release(struct pci_dev *dev) } /** + * pci_iov_remove - clean up SR-IOV state after PF driver is detached + * @dev: the PCI device + */ +void pci_iov_remove(struct pci_dev *dev) +{ + struct pci_sriov *iov = dev->sriov; + + if (!dev->is_physfn) + return; + + iov->driver_max_VFs = iov->total_VFs; + if (iov->num_VFs) + pci_warn(dev, "driver left SR-IOV enabled after remove\n"); +} + +/** * pci_iov_update_resource - update a VF BAR * @dev: the PCI device * @resno: the resource number @@ -553,8 +1037,8 @@ void pci_iov_release(struct pci_dev *dev) void pci_iov_update_resource(struct pci_dev *dev, int resno) { struct pci_sriov *iov = dev->is_physfn ? dev->sriov : NULL; - struct resource *res = dev->resource + resno; - int vf_bar = resno - PCI_IOV_RESOURCES; + struct resource *res = pci_resource_n(dev, resno); + int vf_bar = pci_resource_num_to_vf_bar(resno); struct pci_bus_region region; u16 cmd; u32 new; @@ -628,8 +1112,21 @@ resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno) */ void pci_restore_iov_state(struct pci_dev *dev) { - if (dev->is_physfn) + if (dev->is_physfn) { + sriov_restore_vf_rebar_state(dev); sriov_restore_state(dev); + } +} + +/** + * pci_vf_drivers_autoprobe - set PF property drivers_autoprobe for VFs + * @dev: the PCI device + * @auto_probe: set VF drivers auto probe flag + */ +void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool auto_probe) +{ + if (dev->is_physfn) + dev->sriov->drivers_autoprobe = auto_probe; } /** @@ -723,7 +1220,7 @@ int pci_vfs_assigned(struct pci_dev *dev) * determine the device ID for the VFs, the vendor ID will be the * same as the PF so there is no need to check for that one */ - pci_read_config_word(dev, dev->sriov->pos + PCI_SRIOV_VF_DID, &dev_id); + dev_id = dev->sriov->vf_device; /* loop through all the VFs to see if we own any that are assigned */ vfdev = pci_get_device(dev->vendor, dev_id, NULL); @@ -760,15 +1257,15 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs) { if (!dev->is_physfn) return -ENOSYS; + if (numvfs > dev->sriov->total_VFs) return -EINVAL; /* Shouldn't change if VFs already enabled */ if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE) return -EBUSY; - else - dev->sriov->driver_max_VFs = numvfs; + dev->sriov->driver_max_VFs = numvfs; return 0; } EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs); @@ -786,9 +1283,98 @@ int pci_sriov_get_totalvfs(struct pci_dev *dev) if (!dev->is_physfn) return 0; - if (dev->sriov->driver_max_VFs) - return dev->sriov->driver_max_VFs; - - return dev->sriov->total_VFs; + return dev->sriov->driver_max_VFs; } EXPORT_SYMBOL_GPL(pci_sriov_get_totalvfs); + +/** + * pci_sriov_configure_simple - helper to configure SR-IOV + * @dev: the PCI device + * @nr_virtfn: number of virtual functions to enable, 0 to disable + * + * Enable or disable SR-IOV for devices that don't require any PF setup + * before enabling SR-IOV. Return value is negative on error, or number of + * VFs allocated on success. + */ +int pci_sriov_configure_simple(struct pci_dev *dev, int nr_virtfn) +{ + int rc; + + might_sleep(); + + if (!dev->is_physfn) + return -ENODEV; + + if (pci_vfs_assigned(dev)) { + pci_warn(dev, "Cannot modify SR-IOV while VFs are assigned\n"); + return -EPERM; + } + + if (nr_virtfn == 0) { + sriov_disable(dev); + return 0; + } + + rc = sriov_enable(dev, nr_virtfn); + if (rc < 0) + return rc; + + return nr_virtfn; +} +EXPORT_SYMBOL_GPL(pci_sriov_configure_simple); + +/** + * pci_iov_vf_bar_set_size - set a new size for a VF BAR + * @dev: the PCI device + * @resno: the resource number + * @size: new size as defined in the spec (0=1MB, 31=128TB) + * + * Set the new size of a VF BAR that supports VF resizable BAR capability. + * Unlike pci_resize_resource(), this does not cause the resource that + * reserves the MMIO space (originally up to total_VFs) to be resized, which + * means that following calls to pci_enable_sriov() can fail if the resources + * no longer fit. + * + * Return: 0 on success, or negative on failure. + */ +int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size) +{ + if (!pci_resource_is_iov(resno)) + return -EINVAL; + + if (pci_iov_is_memory_decoding_enabled(dev)) + return -EBUSY; + + if (!pci_rebar_size_supported(dev, resno, size)) + return -EINVAL; + + return pci_rebar_set_size(dev, resno, size); +} +EXPORT_SYMBOL_GPL(pci_iov_vf_bar_set_size); + +/** + * pci_iov_vf_bar_get_sizes - get VF BAR sizes allowing to create up to num_vfs + * @dev: the PCI device + * @resno: the resource number + * @num_vfs: number of VFs + * + * Get the sizes of a VF resizable BAR that can accommodate @num_vfs within + * the currently assigned size of the resource @resno. + * + * Return: A bitmask of sizes in format defined in the spec (bit 0=1MB, + * bit 31=128TB). + */ +u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs) +{ + u64 vf_len = pci_resource_len(dev, resno); + u64 sizes; + + if (!num_vfs) + return 0; + + do_div(vf_len, num_vfs); + sizes = (roundup_pow_of_two(vf_len + 1) - 1) >> ilog2(SZ_1M); + + return sizes & pci_rebar_get_possible_sizes(dev, resno); +} +EXPORT_SYMBOL_GPL(pci_iov_vf_bar_get_sizes); |