diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index a8d01005f480..10a93696e55a 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -82,7 +82,19 @@ Most of the hard work is done for the driver in the PCI layer. It simply has to request that the PCI layer set up the MSI capability for this device. -4.2.1 pci_enable_msi_range +4.2.1 pci_enable_msi + +int pci_enable_msi(struct pci_dev *dev) + +A successful call allocates ONE interrupt to the device, regardless +of how many MSIs the device supports. The device is switched from +pin-based interrupt mode to MSI mode. The dev->irq number is changed +to a new number which represents the message signaled interrupt; +consequently, this function should be called before the driver calls +request_irq(), because an MSI is delivered via a vector that is +different from the vector of a pin-based interrupt. + +4.2.2 pci_enable_msi_range int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) @@ -147,6 +159,11 @@ static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) return pci_enable_msi_range(pdev, nvec, nvec); } +Note, unlike pci_enable_msi_exact() function, which could be also used to +enable a particular number of MSI-X interrupts, pci_enable_msi_range() +returns either a negative errno or 'nvec' (not negative errno or 0 - as +pci_enable_msi_exact() does). + 4.2.1.3 Single MSI mode The most notorious example of the request type described above is @@ -158,7 +175,27 @@ static int foo_driver_enable_single_msi(struct pci_dev *pdev) return pci_enable_msi_range(pdev, 1, 1); } -4.2.2 pci_disable_msi +Note, unlike pci_enable_msi() function, which could be also used to +enable the single MSI mode, pci_enable_msi_range() returns either a +negative errno or 1 (not negative errno or 0 - as pci_enable_msi() +does). + +4.2.3 pci_enable_msi_exact + +int pci_enable_msi_exact(struct pci_dev *dev, int nvec) + +This variation on pci_enable_msi_range() call allows a device driver to +request exactly 'nvec' MSIs. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to request any more MSI interrupts for +this device. + +By contrast with pci_enable_msi_range() function, pci_enable_msi_exact() +returns zero in case of success, which indicates MSI interrupts have been +successfully allocated. + +4.2.4 pci_disable_msi void pci_disable_msi(struct pci_dev *dev) @@ -172,7 +209,7 @@ on any interrupt for which it previously called request_irq(). Failure to do so results in a BUG_ON(), leaving the device with MSI enabled and thus leaking its vector. -4.2.3 pci_msi_vec_count +4.2.4 pci_msi_vec_count int pci_msi_vec_count(struct pci_dev *dev) @@ -257,8 +294,8 @@ possible, likely up to the limit returned by pci_msix_vec_count() function: static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) { - return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, - 1, nvec); + return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + 1, nvec); } Note the value of 'minvec' parameter is 1. As 'minvec' is inclusive, @@ -269,8 +306,8 @@ In this case the function could look like this: static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) { - return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, - FOO_DRIVER_MINIMUM_NVEC, nvec); + return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + FOO_DRIVER_MINIMUM_NVEC, nvec); } 4.3.1.2 Exact number of MSI-X interrupts @@ -282,10 +319,15 @@ parameters: static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) { - return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, - nvec, nvec); + return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + nvec, nvec); } +Note, unlike pci_enable_msix_exact() function, which could be also used to +enable a particular number of MSI-X interrupts, pci_enable_msix_range() +returns either a negative errno or 'nvec' (not negative errno or 0 - as +pci_enable_msix_exact() does). + 4.3.1.3 Specific requirements to the number of MSI-X interrupts As noted above, there could be devices that can not operate with just any @@ -332,7 +374,64 @@ Note how pci_enable_msix_range() return value is analized for a fallback - any error code other than -ENOSPC indicates a fatal error and should not be retried. -4.3.2 pci_disable_msix +4.3.2 pci_enable_msix_exact + +int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) + +This variation on pci_enable_msix_range() call allows a device driver to +request exactly 'nvec' MSI-Xs. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to allocate any more MSI-X interrupts for +this device. + +By contrast with pci_enable_msix_range() function, pci_enable_msix_exact() +returns zero in case of success, which indicates MSI-X interrupts have been +successfully allocated. + +Another version of a routine that enables MSI-X mode for a device with +specific requirements described in chapter 4.3.1.3 might look like this: + +/* + * Assume 'minvec' and 'maxvec' are non-zero + */ +static int foo_driver_enable_msix(struct foo_adapter *adapter, + int minvec, int maxvec) +{ + int rc; + + minvec = roundup_pow_of_two(minvec); + maxvec = rounddown_pow_of_two(maxvec); + + if (minvec > maxvec) + return -ERANGE; + +retry: + rc = pci_enable_msix_exact(adapter->pdev, + adapter->msix_entries, maxvec); + + /* + * -ENOSPC is the only error code allowed to be analyzed + */ + if (rc == -ENOSPC) { + if (maxvec == 1) + return -ENOSPC; + + maxvec /= 2; + + if (minvec > maxvec) + return -ENOSPC; + + goto retry; + } else if (rc < 0) { + return rc; + } + + return maxvec; +} + +4.3.3 pci_disable_msix void pci_disable_msix(struct pci_dev *dev) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index dc2756fb6f33..023710905289 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1151,13 +1151,13 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host) static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports, struct ahci_host_priv *hpriv) { - int rc, nvec; + int nvec; if (hpriv->flags & AHCI_HFLAG_NO_MSI) goto intx; - rc = pci_msi_vec_count(pdev); - if (rc < 0) + nvec = pci_msi_vec_count(pdev); + if (nvec < 0) goto intx; /* @@ -1165,19 +1165,19 @@ static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports, * Message mode could be enforced. In this case assume that advantage * of multipe MSIs is negated and use single MSI mode instead. */ - if (rc < n_ports) + if (nvec < n_ports) goto single_msi; - nvec = rc; - rc = pci_enable_msi_block(pdev, nvec); - if (rc) + nvec = pci_enable_msi_range(pdev, nvec, nvec); + if (nvec == -ENOSPC) + goto single_msi; + else if (nvec < 0) goto intx; return nvec; single_msi: - rc = pci_enable_msi(pdev); - if (rc) + if (pci_enable_msi(pdev)) goto intx; return 1; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 7a0fec6ce571..955ab7990c5b 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -545,9 +545,15 @@ static int populate_msi_sysfs(struct pci_dev *pdev) return -ENOMEM; list_for_each_entry(entry, &pdev->msi_list, list) { char *name = kmalloc(20, GFP_KERNEL); - msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL); - if (!msi_dev_attr) + if (!name) goto error_attrs; + + msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL); + if (!msi_dev_attr) { + kfree(name); + goto error_attrs; + } + sprintf(name, "%d", entry->irq); sysfs_attr_init(&msi_dev_attr->attr); msi_dev_attr->attr.name = name; @@ -589,6 +595,7 @@ error_attrs: ++count; msi_attr = msi_attrs[count]; } + kfree(msi_attrs); return ret; } @@ -959,7 +966,6 @@ EXPORT_SYMBOL(pci_disable_msi); /** * pci_msix_vec_count - return the number of device's MSI-X table entries * @dev: pointer to the pci_dev data structure of MSI-X device function - * This function returns the number of device's MSI-X table entries and * therefore the number of MSI-X vectors device is capable of sending. * It returns a negative errno if the device is not capable of sending MSI-X diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 210357691dc0..9dd49c9839ac 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -482,15 +482,19 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) for (i = 0; i < nvec; i++) vdev->msix[i].entry = i; - ret = pci_enable_msix(pdev, vdev->msix, nvec); - if (ret) { + ret = pci_enable_msix_range(pdev, vdev->msix, 1, nvec); + if (ret < nvec) { + if (ret > 0) + pci_disable_msix(pdev); kfree(vdev->msix); kfree(vdev->ctx); return ret; } } else { - ret = pci_enable_msi_block(pdev, nvec); - if (ret) { + ret = pci_enable_msi_range(pdev, 1, nvec); + if (ret < nvec) { + if (ret > 0) + pci_disable_msi(pdev); kfree(vdev->ctx); return ret; } diff --git a/include/linux/pci.h b/include/linux/pci.h index 60ab8d782f8c..1e26fc602adc 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1171,8 +1171,23 @@ void msi_remove_pci_irq_vectors(struct pci_dev *dev); void pci_restore_msi_state(struct pci_dev *dev); int pci_msi_enabled(void); int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec); +static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) +{ + int rc = pci_enable_msi_range(dev, nvec, nvec); + if (rc < 0) + return rc; + return 0; +} int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec); +static inline int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) +{ + int rc = pci_enable_msix_range(dev, entries, nvec, nvec); + if (rc < 0) + return rc; + return 0; +} #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec) @@ -1191,9 +1206,14 @@ static inline int pci_msi_enabled(void) { return 0; } static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { return -ENOSYS; } +static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) +{ return -ENOSYS; } static inline int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { return -ENOSYS; } +static inline int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) +{ return -ENOSYS; } #endif #ifdef CONFIG_PCIEPORTBUS