PCI/MSI: Provide a sane mechanism for TPH

The PCI/TPH driver fiddles with the MSI-X control word of an active
interrupt completely unserialized against concurrent operations issued
from the interrupt core. It also brings the PCI/MSI-X internal cached
control word out of sync.

Provide a function, which has the required serialization and keeps the
control word cache in sync.

Unfortunately this requires to look up and lock the interrupt descriptor,
which should be only done in the interrupt core code. But confining this
particular oddity in the PCI/MSI core is the lesser of all evil. A
interrupt core implementation would require a larger pile of infrastructure
and indirections for dubious value.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/all/20250319105506.683663807@linutronix.de

2 files changed, 56 insertions, 0 deletions

diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
index 732166a9192c..593bae2855c3 100644
--- a/drivers/pci/msi/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -913,6 +913,53 @@ void pci_free_msi_irqs(struct pci_dev *dev)
 	}
 }
 
+#ifdef CONFIG_PCIE_TPH
+/**
+ * pci_msix_write_tph_tag - Update the TPH tag for a given MSI-X vector
+ * @pdev:	The PCIe device to update
+ * @index:	The MSI-X index to update
+ * @tag:	The tag to write
+ *
+ * Returns: 0 on success, error code on failure
+ */
+int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag)
+{
+	struct msi_desc *msi_desc;
+	struct irq_desc *irq_desc;
+	unsigned int virq;
+
+	if (!pdev->msix_enabled)
+		return -ENXIO;
+
+	guard(msi_descs_lock)(&pdev->dev);
+	virq = msi_get_virq(&pdev->dev, index);
+	if (!virq)
+		return -ENXIO;
+	/*
+	 * This is a horrible hack, but short of implementing a PCI
+	 * specific interrupt chip callback and a huge pile of
+	 * infrastructure, this is the minor nuissance. It provides the
+	 * protection against concurrent operations on this entry and keeps
+	 * the control word cache in sync.
+	 */
+	irq_desc = irq_to_desc(virq);
+	if (!irq_desc)
+		return -ENXIO;
+
+	guard(raw_spinlock_irq)(&irq_desc->lock);
+	msi_desc = irq_data_get_msi_desc(&irq_desc->irq_data);
+	if (!msi_desc || msi_desc->pci.msi_attrib.is_virtual)
+		return -ENXIO;
+
+	msi_desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_ST;
+	msi_desc->pci.msix_ctrl |= FIELD_PREP(PCI_MSIX_ENTRY_CTRL_ST, tag);
+	pci_msix_write_vector_ctrl(msi_desc, msi_desc->pci.msix_ctrl);
+	/* Flush the write */
+	readl(pci_msix_desc_addr(msi_desc));
+	return 0;
+}
+#endif
+
 /* Misc. infrastructure */
 
 struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index b81e99cd4b62..39f368d2f26d 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -1064,6 +1064,15 @@ int pcim_request_region_exclusive(struct pci_dev *pdev, int bar,
 				  const char *name);
 void pcim_release_region(struct pci_dev *pdev, int bar);
 
+#ifdef CONFIG_PCI_MSI
+int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag);
+#else
+static inline int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag)
+{
+	return -ENODEV;
+}
+#endif
+
 /*
  * Config Address for PCI Configuration Mechanism #1
  *