1 files changed, 159 insertions, 97 deletions

diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
index 682fa877478f..d686488f4111 100644
--- a/drivers/pci/msi/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -10,12 +10,12 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 
 #include "../pci.h"
 #include "msi.h"
 
-int pci_msi_enable = 1;
-int pci_msi_ignore_mask;
+bool pci_msi_enable = true;
 
 /**
  * pci_msi_supported - check whether MSI may be enabled on a device
@@ -86,9 +86,11 @@ static int pcim_setup_msi_release(struct pci_dev *dev)
 		return 0;
 
 	ret = devm_add_action(&dev->dev, pcim_msi_release, dev);
-	if (!ret)
-		dev->is_msi_managed = true;
-	return ret;
+	if (ret)
+		return ret;
+
+	dev->is_msi_managed = true;
+	return 0;
 }
 
 /*
@@ -99,9 +101,10 @@ static int pci_setup_msi_context(struct pci_dev *dev)
 {
 	int ret = msi_setup_device_data(&dev->dev);
 
-	if (!ret)
-		ret = pcim_setup_msi_release(dev);
-	return ret;
+	if (ret)
+		return ret;
+
+	return pcim_setup_msi_release(dev);
 }
 
 /*
@@ -292,8 +295,7 @@ static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
 	/* Lies, damned lies, and MSIs */
 	if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING)
 		control |= PCI_MSI_FLAGS_MASKBIT;
-	/* Respect XEN's mask disabling */
-	if (pci_msi_ignore_mask)
+	if (pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY))
 		control &= ~PCI_MSI_FLAGS_MASKBIT;
 
 	desc.nvec_used			= nvec;
@@ -333,47 +335,23 @@ static int msi_verify_entries(struct pci_dev *dev)
 	return !entry ? 0 : -EIO;
 }
 
-/**
- * msi_capability_init - configure device's MSI capability structure
- * @dev: pointer to the pci_dev data structure of MSI device function
- * @nvec: number of interrupts to allocate
- * @affd: description of automatic IRQ affinity assignments (may be %NULL)
- *
- * Setup the MSI capability structure of the device with the requested
- * number of interrupts.  A return value of zero indicates the successful
- * setup of an entry with the new MSI IRQ.  A negative return value indicates
- * an error, and a positive return value indicates the number of interrupts
- * which could have been allocated.
- */
-static int msi_capability_init(struct pci_dev *dev, int nvec,
-			       struct irq_affinity *affd)
+static int __msi_capability_init(struct pci_dev *dev, int nvec, struct irq_affinity_desc *masks)
 {
-	struct irq_affinity_desc *masks = NULL;
-	struct msi_desc *entry;
-	int ret;
-
-	/* Reject multi-MSI early on irq domain enabled architectures */
-	if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY))
-		return 1;
-
-	/*
-	 * Disable MSI during setup in the hardware, but mark it enabled
-	 * so that setup code can evaluate it.
-	 */
-	pci_msi_set_enable(dev, 0);
-	dev->msi_enabled = 1;
-
-	if (affd)
-		masks = irq_create_affinity_masks(nvec, affd);
+	int ret = msi_setup_msi_desc(dev, nvec, masks);
+	struct msi_desc *entry, desc;
 
-	msi_lock_descs(&dev->dev);
-	ret = msi_setup_msi_desc(dev, nvec, masks);
 	if (ret)
-		goto fail;
+		return ret;
 
 	/* All MSIs are unmasked by default; mask them all */
 	entry = msi_first_desc(&dev->dev, MSI_DESC_ALL);
 	pci_msi_mask(entry, msi_multi_mask(entry));
+	/*
+	 * Copy the MSI descriptor for the error path because
+	 * pci_msi_setup_msi_irqs() will free it for the hierarchical
+	 * interrupt domain case.
+	 */
+	memcpy(&desc, entry, sizeof(desc));
 
 	/* Configure MSI capability structure */
 	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
@@ -385,24 +363,51 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 		goto err;
 
 	/* Set MSI enabled bits	*/
+	dev->msi_enabled = 1;
 	pci_intx_for_msi(dev, 0);
 	pci_msi_set_enable(dev, 1);
 
 	pcibios_free_irq(dev);
 	dev->irq = entry->irq;
-	goto unlock;
-
+	return 0;
 err:
-	pci_msi_unmask(entry, msi_multi_mask(entry));
+	pci_msi_unmask(&desc, msi_multi_mask(&desc));
 	pci_free_msi_irqs(dev);
-fail:
-	dev->msi_enabled = 0;
-unlock:
-	msi_unlock_descs(&dev->dev);
-	kfree(masks);
 	return ret;
 }
 
+/**
+ * msi_capability_init - configure device's MSI capability structure
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: number of interrupts to allocate
+ * @affd: description of automatic IRQ affinity assignments (may be %NULL)
+ *
+ * Setup the MSI capability structure of the device with the requested
+ * number of interrupts.  A return value of zero indicates the successful
+ * setup of an entry with the new MSI IRQ.  A negative return value indicates
+ * an error, and a positive return value indicates the number of interrupts
+ * which could have been allocated.
+ */
+static int msi_capability_init(struct pci_dev *dev, int nvec,
+			       struct irq_affinity *affd)
+{
+	/* Reject multi-MSI early on irq domain enabled architectures */
+	if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY))
+		return 1;
+
+	/*
+	 * Disable MSI during setup in the hardware, but mark it enabled
+	 * so that setup code can evaluate it.
+	 */
+	pci_msi_set_enable(dev, 0);
+
+	struct irq_affinity_desc *masks __free(kfree) =
+		affd ? irq_create_affinity_masks(nvec, affd) : NULL;
+
+	guard(msi_descs_lock)(&dev->dev);
+	return __msi_capability_init(dev, nvec, masks);
+}
+
 int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 			   struct irq_affinity *affd)
 {
@@ -424,22 +429,26 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 	if (WARN_ON_ONCE(dev->msi_enabled))
 		return -EINVAL;
 
+	/* Test for the availability of MSI support */
+	if (!pci_msi_domain_supports(dev, 0, ALLOW_LEGACY))
+		return -ENOTSUPP;
+
 	nvec = pci_msi_vec_count(dev);
 	if (nvec < 0)
 		return nvec;
 	if (nvec < minvec)
 		return -ENOSPC;
 
-	if (nvec > maxvec)
-		nvec = maxvec;
-
 	rc = pci_setup_msi_context(dev);
 	if (rc)
 		return rc;
 
-	if (!pci_setup_msi_device_domain(dev))
+	if (!pci_setup_msi_device_domain(dev, nvec))
 		return -ENODEV;
 
+	if (nvec > maxvec)
+		nvec = maxvec;
+
 	for (;;) {
 		if (affd) {
 			nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
@@ -596,12 +605,16 @@ void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
 	desc->pci.msi_attrib.is_64		= 1;
 	desc->pci.msi_attrib.default_irq	= dev->irq;
 	desc->pci.mask_base			= dev->msix_base;
-	desc->pci.msi_attrib.can_mask		= !pci_msi_ignore_mask &&
-						  !desc->pci.msi_attrib.is_virtual;
 
-	if (desc->pci.msi_attrib.can_mask) {
+
+	if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY) &&
+	    !desc->pci.msi_attrib.is_virtual) {
 		void __iomem *addr = pci_msix_desc_addr(desc);
 
+		desc->pci.msi_attrib.can_mask = 1;
+		/* Workaround for SUN NIU insanity, which requires write before read */
+		if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST)
+			writel(0, addr + PCI_MSIX_ENTRY_DATA);
 		desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 	}
 }
@@ -646,45 +659,43 @@ static void msix_mask_all(void __iomem *base, int tsize)
 	u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	int i;
 
-	if (pci_msi_ignore_mask)
-		return;
-
 	for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
 		writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
 
-static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries,
-				 int nvec, struct irq_affinity *affd)
-{
-	struct irq_affinity_desc *masks = NULL;
-	int ret;
+DEFINE_FREE(free_msi_irqs, struct pci_dev *, if (_T) pci_free_msi_irqs(_T));
 
-	if (affd)
-		masks = irq_create_affinity_masks(nvec, affd);
+static int __msix_setup_interrupts(struct pci_dev *__dev, struct msix_entry *entries,
+				   int nvec, struct irq_affinity_desc *masks)
+{
+	struct pci_dev *dev __free(free_msi_irqs) = __dev;
 
-	msi_lock_descs(&dev->dev);
-	ret = msix_setup_msi_descs(dev, entries, nvec, masks);
+	int ret = msix_setup_msi_descs(dev, entries, nvec, masks);
 	if (ret)
-		goto out_free;
+		return ret;
 
 	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
 	if (ret)
-		goto out_free;
+		return ret;
 
 	/* Check if all MSI entries honor device restrictions */
 	ret = msi_verify_entries(dev);
 	if (ret)
-		goto out_free;
+		return ret;
 
 	msix_update_entries(dev, entries);
-	goto out_unlock;
+	retain_and_null_ptr(dev);
+	return 0;
+}
 
-out_free:
-	pci_free_msi_irqs(dev);
-out_unlock:
-	msi_unlock_descs(&dev->dev);
-	kfree(masks);
-	return ret;
+static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries,
+				 int nvec, struct irq_affinity *affd)
+{
+	struct irq_affinity_desc *masks __free(kfree) =
+		affd ? irq_create_affinity_masks(nvec, affd) : NULL;
+
+	guard(msi_descs_lock)(&dev->dev);
+	return __msix_setup_interrupts(dev, entries, nvec, masks);
 }
 
 /**
@@ -731,15 +742,17 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 	/* Disable INTX */
 	pci_intx_for_msi(dev, 0);
 
-	/*
-	 * Ensure that all table entries are masked to prevent
-	 * stale entries from firing in a crash kernel.
-	 *
-	 * Done late to deal with a broken Marvell NVME device
-	 * which takes the MSI-X mask bits into account even
-	 * when MSI-X is disabled, which prevents MSI delivery.
-	 */
-	msix_mask_all(dev->msix_base, tsize);
+	if (!pci_msi_domain_supports(dev, MSI_FLAG_NO_MASK, DENY_LEGACY)) {
+		/*
+		 * Ensure that all table entries are masked to prevent
+		 * stale entries from firing in a crash kernel.
+		 *
+		 * Done late to deal with a broken Marvell NVME device
+		 * which takes the MSI-X mask bits into account even
+		 * when MSI-X is disabled, which prevents MSI delivery.
+		 */
+		msix_mask_all(dev->msix_base, tsize);
+	}
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 
 	pcibios_free_irq(dev);
@@ -858,13 +871,13 @@ void __pci_restore_msix_state(struct pci_dev *dev)
 
 	write_msg = arch_restore_msi_irqs(dev);
 
-	msi_lock_descs(&dev->dev);
-	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
-		if (write_msg)
-			__pci_write_msi_msg(entry, &entry->msg);
-		pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl);
+	scoped_guard (msi_descs_lock, &dev->dev) {
+		msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
+			if (write_msg)
+				__pci_write_msi_msg(entry, &entry->msg);
+			pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl);
+		}
 	}
-	msi_unlock_descs(&dev->dev);
 
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 }
@@ -903,6 +916,55 @@ 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;
+
+	virq = msi_get_virq(&pdev->dev, index);
+	if (!virq)
+		return -ENXIO;
+
+	guard(msi_descs_lock)(&pdev->dev);
+
+	/*
+	 * 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)
@@ -913,5 +975,5 @@ EXPORT_SYMBOL(msi_desc_to_pci_dev);
 
 void pci_no_msi(void)
 {
-	pci_msi_enable = 0;
+	pci_msi_enable = false;
 }