PCI/MSI: Add pci_enable_msi_exact() and pci_enable_msix_exact()

The new functions are special cases for pci_enable_msi_range() and
pci_enable_msix_range() when a particular number of MSI or MSI-X
is needed.

By contrast with pci_enable_msi_range() and pci_enable_msix_range()
functions, pci_enable_msi_exact() and pci_enable_msix_exact()
return zero in case of success, which indicates MSI or MSI-X
interrupts have been successfully allocated.

Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

2 files changed, 104 insertions, 2 deletions

diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index 96ee5eb9d4d4..10a93696e55a 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -159,6 +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
@@ -175,7 +180,22 @@ 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_disable_msi
+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)
 
@@ -303,6 +323,11 @@ static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
 				     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
@@ -349,7 +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/include/linux/pci.h b/include/linux/pci.h
index fb57c892b214..33aa2caf0f0c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1169,8 +1169,23 @@ 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)
@@ -1189,9 +1204,14 @@ 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