PCI/MSI: Convert pci_msi_ignore_mask to per MSI domain flag

Setting pci_msi_ignore_mask inhibits the toggling of the mask bit for both
MSI and MSI-X entries globally, regardless of the IRQ chip they are using.
Only Xen sets the pci_msi_ignore_mask when routing physical interrupts over
event channels, to prevent PCI code from attempting to toggle the maskbit,
as it's Xen that controls the bit.

However, the pci_msi_ignore_mask being global will affect devices that use
MSI interrupts but are not routing those interrupts over event channels
(not using the Xen pIRQ chip).  One example is devices behind a VMD PCI
bridge.  In that scenario the VMD bridge configures MSI(-X) using the
normal IRQ chip (the pIRQ one in the Xen case), and devices behind the
bridge configure the MSI entries using indexes into the VMD bridge MSI
table.  The VMD bridge then demultiplexes such interrupts and delivers to
the destination device(s).  Having pci_msi_ignore_mask set in that scenario
prevents (un)masking of MSI entries for devices behind the VMD bridge.

Move the signaling of no entry masking into the MSI domain flags, as that
allows setting it on a per-domain basis.  Set it for the Xen MSI domain
that uses the pIRQ chip, while leaving it unset for the rest of the
cases.

Remove pci_msi_ignore_mask at once, since it was only used by Xen code, and
with Xen dropping usage the variable is unneeded.

This fixes using devices behind a VMD bridge on Xen PV hardware domains.

Albeit Devices behind a VMD bridge are not known to Xen, that doesn't mean
Linux cannot use them.  By inhibiting the usage of
VMD_FEAT_CAN_BYPASS_MSI_REMAP and the removal of the pci_msi_ignore_mask
bodge devices behind a VMD bridge do work fine when use from a Linux Xen
hardware domain.  That's the whole point of the series.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Juergen Gross <jgross@suse.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Message-ID: <20250219092059.90850-4-roger.pau@citrix.com>
Signed-off-by: Juergen Gross <jgross@suse.com>

Author: royger

arch/x86/pci/xen.c

@@ -436,7 +436,8 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = {
 };
 
 static struct msi_domain_info xen_pci_msi_domain_info = {
-	.flags			= MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS,
+	.flags			= MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS |
+				  MSI_FLAG_DEV_SYSFS | MSI_FLAG_NO_MASK,
 	.ops			= &xen_pci_msi_domain_ops,
 };
 
@@ -484,11 +485,6 @@ static __init void xen_setup_pci_msi(void)
 	 * in allocating the native domain and never use it.
 	 */
 	x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain;
-	/*
-	 * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely
-	 * controlled by the hypervisor.
-	 */
-	pci_msi_ignore_mask = 1;
 }
 
 #else /* CONFIG_PCI_MSI */

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;
 
 /**
  * pci_msi_supported - check whether MSI may be enabled on a device
@@ -285,6 +285,8 @@ static void pci_msi_set_enable(struct pci_dev *dev, int enable)
 static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
 			      struct irq_affinity_desc *masks)
 {
+	const struct irq_domain *d = dev_get_msi_domain(&dev->dev);
+	const struct msi_domain_info *info = d->host_data;
 	struct msi_desc desc;
 	u16 control;
 
@@ -295,8 +297,7 @@ 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 (info->flags & MSI_FLAG_NO_MASK)
 		control &= ~PCI_MSI_FLAGS_MASKBIT;
 
 	desc.nvec_used			= nvec;
@@ -604,12 +605,15 @@ static void __iomem *msix_map_region(struct pci_dev *dev,
  */
 void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
 {
+	const struct irq_domain *d = dev_get_msi_domain(&dev->dev);
+	const struct msi_domain_info *info = d->host_data;
+
 	desc->nvec_used				= 1;
 	desc->pci.msi_attrib.is_msix		= 1;
 	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.can_mask		= !(info->flags & MSI_FLAG_NO_MASK) &&
 						  !desc->pci.msi_attrib.is_virtual;
 
 	if (desc->pci.msi_attrib.can_mask) {
@@ -659,9 +663,6 @@ 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);
 }
@@ -714,6 +715,8 @@ static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries
 static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 				int nvec, struct irq_affinity *affd)
 {
+	const struct irq_domain *d = dev_get_msi_domain(&dev->dev);
+	const struct msi_domain_info *info = d->host_data;
 	int ret, tsize;
 	u16 control;
 
@@ -744,15 +747,17 @@ 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 (!(info->flags & MSI_FLAG_NO_MASK)) {
+		/*
+		 * 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);

include/linux/msi.h

@@ -73,7 +73,6 @@ struct msi_msg {
 	};
 };
 
-extern int pci_msi_ignore_mask;
 /* Helper functions */
 struct msi_desc;
 struct pci_dev;
@@ -556,6 +555,8 @@ enum {
 	MSI_FLAG_PCI_MSIX_ALLOC_DYN	= (1 << 20),
 	/* PCI MSIs cannot be steered separately to CPU cores */
 	MSI_FLAG_NO_AFFINITY		= (1 << 21),
+	/* Inhibit usage of entry masking */
+	MSI_FLAG_NO_MASK		= (1 << 22),
 };
 
 /**

kernel/irq/msi.c

@@ -1143,7 +1143,7 @@ static bool msi_check_reservation_mode(struct irq_domain *domain,
 	if (!(info->flags & MSI_FLAG_MUST_REACTIVATE))
 		return false;
 
-	if (IS_ENABLED(CONFIG_PCI_MSI) && pci_msi_ignore_mask)
+	if (info->flags & MSI_FLAG_NO_MASK)
 		return false;
 
 	/*