4 files changed, 197 insertions, 222 deletions

diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c
index be679aa5db64..818d55fbad0d 100644
--- a/drivers/pci/msi/api.c
+++ b/drivers/pci/msi/api.c
@@ -53,10 +53,9 @@ void pci_disable_msi(struct pci_dev *dev)
 	if (!pci_msi_enabled() || !dev || !dev->msi_enabled)
 		return;
 
-	msi_lock_descs(&dev->dev);
+	guard(msi_descs_lock)(&dev->dev);
 	pci_msi_shutdown(dev);
 	pci_free_msi_irqs(dev);
-	msi_unlock_descs(&dev->dev);
 }
 EXPORT_SYMBOL(pci_disable_msi);
 
@@ -162,7 +161,7 @@ struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index,
 EXPORT_SYMBOL_GPL(pci_msix_alloc_irq_at);
 
 /**
- * pci_msix_free_irq - Free an interrupt on a PCI/MSIX interrupt domain
+ * pci_msix_free_irq - Free an interrupt on a PCI/MSI-X interrupt domain
  *
  * @dev:	The PCI device to operate on
  * @map:	A struct msi_map describing the interrupt to free
@@ -196,10 +195,9 @@ void pci_disable_msix(struct pci_dev *dev)
 	if (!pci_msi_enabled() || !dev || !dev->msix_enabled)
 		return;
 
-	msi_lock_descs(&dev->dev);
+	guard(msi_descs_lock)(&dev->dev);
 	pci_msix_shutdown(dev);
 	pci_free_msi_irqs(dev);
-	msi_unlock_descs(&dev->dev);
 }
 EXPORT_SYMBOL(pci_disable_msix);
 
@@ -213,8 +211,8 @@ EXPORT_SYMBOL(pci_disable_msix);
  *            * %PCI_IRQ_MSIX      Allow trying MSI-X vector allocations
  *            * %PCI_IRQ_MSI       Allow trying MSI vector allocations
  *
- *            * %PCI_IRQ_LEGACY    Allow trying legacy INTx interrupts, if
- *              and only if @min_vecs == 1
+ *            * %PCI_IRQ_INTX      Allow trying INTx interrupts, if and
+ *              only if @min_vecs == 1
  *
  *            * %PCI_IRQ_AFFINITY  Auto-manage IRQs affinity by spreading
  *              the vectors around available CPUs
@@ -279,8 +277,8 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
 			return nvecs;
 	}
 
-	/* use legacy IRQ if allowed */
-	if (flags & PCI_IRQ_LEGACY) {
+	/* use INTx IRQ if allowed */
+	if (flags & PCI_IRQ_INTX) {
 		if (min_vecs == 1 && dev->irq) {
 			/*
 			 * Invoke the affinity spreading logic to ensure that
@@ -366,56 +364,6 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr)
 EXPORT_SYMBOL(pci_irq_get_affinity);
 
 /**
- * pci_ims_alloc_irq - Allocate an interrupt on a PCI/IMS interrupt domain
- * @dev:	The PCI device to operate on
- * @icookie:	Pointer to an IMS implementation specific cookie for this
- *		IMS instance (PASID, queue ID, pointer...).
- *		The cookie content is copied into the MSI descriptor for the
- *		interrupt chip callbacks or domain specific setup functions.
- * @affdesc:	Optional pointer to an interrupt affinity descriptor
- *
- * There is no index for IMS allocations as IMS is an implementation
- * specific storage and does not have any direct associations between
- * index, which might be a pure software construct, and device
- * functionality. This association is established by the driver either via
- * the index - if there is a hardware table - or in case of purely software
- * managed IMS implementation the association happens via the
- * irq_write_msi_msg() callback of the implementation specific interrupt
- * chip, which utilizes the provided @icookie to store the MSI message in
- * the appropriate place.
- *
- * Return: A struct msi_map
- *
- *	On success msi_map::index contains the allocated index (>= 0) and
- *	msi_map::virq the allocated Linux interrupt number (> 0).
- *
- *	On fail msi_map::index contains the error code and msi_map::virq
- *	is set to 0.
- */
-struct msi_map pci_ims_alloc_irq(struct pci_dev *dev, union msi_instance_cookie *icookie,
-				 const struct irq_affinity_desc *affdesc)
-{
-	return msi_domain_alloc_irq_at(&dev->dev, MSI_SECONDARY_DOMAIN, MSI_ANY_INDEX,
-				       affdesc, icookie);
-}
-EXPORT_SYMBOL_GPL(pci_ims_alloc_irq);
-
-/**
- * pci_ims_free_irq - Allocate an interrupt on a PCI/IMS interrupt domain
- *		      which was allocated via pci_ims_alloc_irq()
- * @dev:	The PCI device to operate on
- * @map:	A struct msi_map describing the interrupt to free as
- *		returned from pci_ims_alloc_irq()
- */
-void pci_ims_free_irq(struct pci_dev *dev, struct msi_map map)
-{
-	if (WARN_ON_ONCE(map.index < 0 || map.virq <= 0))
-		return;
-	msi_domain_free_irqs_range(&dev->dev, MSI_SECONDARY_DOMAIN, map.index, map.index);
-}
-EXPORT_SYMBOL_GPL(pci_ims_free_irq);
-
-/**
  * pci_free_irq_vectors() - Free previously allocated IRQs for a device
  * @dev: the PCI device to operate on
  *
@@ -451,7 +399,7 @@ EXPORT_SYMBOL_GPL(pci_restore_msi_state);
  * Return: true if MSI has not been globally disabled through ACPI FADT,
  * PCI bridge quirks, or the "pci=nomsi" kernel command-line option.
  */
-int pci_msi_enabled(void)
+bool pci_msi_enabled(void)
 {
 	return pci_msi_enable;
 }
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index cfd84a899c82..c05152733993 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -148,17 +148,35 @@ static void pci_device_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *d
 	arg->hwirq = desc->msi_index;
 }
 
+static __always_inline void cond_mask_parent(struct irq_data *data)
+{
+	struct msi_domain_info *info = data->domain->host_data;
+
+	if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT))
+		irq_chip_mask_parent(data);
+}
+
+static __always_inline void cond_unmask_parent(struct irq_data *data)
+{
+	struct msi_domain_info *info = data->domain->host_data;
+
+	if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT))
+		irq_chip_unmask_parent(data);
+}
+
 static void pci_irq_mask_msi(struct irq_data *data)
 {
 	struct msi_desc *desc = irq_data_get_msi_desc(data);
 
 	pci_msi_mask(desc, BIT(data->irq - desc->irq));
+	cond_mask_parent(data);
 }
 
 static void pci_irq_unmask_msi(struct irq_data *data)
 {
 	struct msi_desc *desc = irq_data_get_msi_desc(data);
 
+	cond_unmask_parent(data);
 	pci_msi_unmask(desc, BIT(data->irq - desc->irq));
 }
 
@@ -195,10 +213,12 @@ static const struct msi_domain_template pci_msi_template = {
 static void pci_irq_mask_msix(struct irq_data *data)
 {
 	pci_msix_mask(irq_data_get_msi_desc(data));
+	cond_mask_parent(data);
 }
 
 static void pci_irq_unmask_msix(struct irq_data *data)
 {
+	cond_unmask_parent(data);
 	pci_msix_unmask(irq_data_get_msi_desc(data));
 }
 
@@ -251,6 +271,7 @@ static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_doma
 /**
  * pci_setup_msi_device_domain - Setup a device MSI interrupt domain
  * @pdev:	The PCI device to create the domain on
+ * @hwsize:	The maximum number of MSI vectors
  *
  * Return:
  *  True when:
@@ -267,7 +288,7 @@ static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_doma
  *	- The device is removed
  *	- MSI is disabled and a MSI-X domain is created
  */
-bool pci_setup_msi_device_domain(struct pci_dev *pdev)
+bool pci_setup_msi_device_domain(struct pci_dev *pdev, unsigned int hwsize)
 {
 	if (WARN_ON_ONCE(pdev->msix_enabled))
 		return false;
@@ -277,7 +298,7 @@ bool pci_setup_msi_device_domain(struct pci_dev *pdev)
 	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX))
 		msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN);
 
-	return pci_create_device_domain(pdev, &pci_msi_template, 1);
+	return pci_create_device_domain(pdev, &pci_msi_template, hwsize);
 }
 
 /**
@@ -330,8 +351,11 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask,
 
 	domain = dev_get_msi_domain(&pdev->dev);
 
-	if (!domain || !irq_domain_is_hierarchy(domain))
-		return mode == ALLOW_LEGACY;
+	if (!domain || !irq_domain_is_hierarchy(domain)) {
+		if (IS_ENABLED(CONFIG_PCI_MSI_ARCH_FALLBACKS))
+			return mode == ALLOW_LEGACY;
+		return false;
+	}
 
 	if (!irq_domain_is_msi_parent(domain)) {
 		/*
@@ -355,65 +379,6 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask,
 	return (supported & feature_mask) == feature_mask;
 }
 
-/**
- * pci_create_ims_domain - Create a secondary IMS domain for a PCI device
- * @pdev:	The PCI device to operate on
- * @template:	The MSI info template which describes the domain
- * @hwsize:	The size of the hardware entry table or 0 if the domain
- *		is purely software managed
- * @data:	Optional pointer to domain specific data to be stored
- *		in msi_domain_info::data
- *
- * Return: True on success, false otherwise
- *
- * An IMS domain is expected to have the following constraints:
- *	- The index space is managed by the core code
- *
- *	- There is no requirement for consecutive index ranges
- *
- *	- The interrupt chip must provide the following callbacks:
- *		- irq_mask()
- *		- irq_unmask()
- *		- irq_write_msi_msg()
- *
- *	- The interrupt chip must provide the following optional callbacks
- *	  when the irq_mask(), irq_unmask() and irq_write_msi_msg() callbacks
- *	  cannot operate directly on hardware, e.g. in the case that the
- *	  interrupt message store is in queue memory:
- *		- irq_bus_lock()
- *		- irq_bus_unlock()
- *
- *	  These callbacks are invoked from preemptible task context and are
- *	  allowed to sleep. In this case the mandatory callbacks above just
- *	  store the information. The irq_bus_unlock() callback is supposed
- *	  to make the change effective before returning.
- *
- *	- Interrupt affinity setting is handled by the underlying parent
- *	  interrupt domain and communicated to the IMS domain via
- *	  irq_write_msi_msg().
- *
- * The domain is automatically destroyed when the PCI device is removed.
- */
-bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template,
-			   unsigned int hwsize, void *data)
-{
-	struct irq_domain *domain = dev_get_msi_domain(&pdev->dev);
-
-	if (!domain || !irq_domain_is_msi_parent(domain))
-		return false;
-
-	if (template->info.bus_token != DOMAIN_BUS_PCI_DEVICE_IMS ||
-	    !(template->info.flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS) ||
-	    !(template->info.flags & MSI_FLAG_FREE_MSI_DESCS) ||
-	    !template->chip.irq_mask || !template->chip.irq_unmask ||
-	    !template->chip.irq_write_msi_msg || template->chip.irq_set_affinity)
-		return false;
-
-	return msi_create_device_irq_domain(&pdev->dev, MSI_SECONDARY_DOMAIN, template,
-					    hwsize, data, NULL);
-}
-EXPORT_SYMBOL_GPL(pci_create_ims_domain);
-
 /*
  * Users of the generic MSI infrastructure expect a device to have a single ID,
  * so with DMA aliases we have to pick the least-worst compromise. Devices with
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;
 }
diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h
index ee53cf079f4e..0b420b319f50 100644
--- a/drivers/pci/msi/msi.h
+++ b/drivers/pci/msi/msi.h
@@ -87,7 +87,7 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc)
 void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc);
 
 /* Subsystem variables */
-extern int pci_msi_enable;
+extern bool pci_msi_enable;
 
 /* MSI internal functions invoked from the public APIs */
 void pci_msi_shutdown(struct pci_dev *dev);
@@ -107,7 +107,7 @@ enum support_mode {
 };
 
 bool pci_msi_domain_supports(struct pci_dev *dev, unsigned int feature_mask, enum support_mode mode);
-bool pci_setup_msi_device_domain(struct pci_dev *pdev);
+bool pci_setup_msi_device_domain(struct pci_dev *pdev, unsigned int hwsize);
 bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize);
 
 /* Legacy (!IRQDOMAIN) fallbacks */