PCI/MSI: Mask all unused MSI-X entries

commit 7d5ec3d upstream.

When MSI-X is enabled the ordering of calls is:

  msix_map_region();
  msix_setup_entries();
  pci_msi_setup_msi_irqs();
  msix_program_entries();

This has a few interesting issues:

 1) msix_setup_entries() allocates the MSI descriptors and initializes them
    except for the msi_desc:masked member which is left zero initialized.

 2) pci_msi_setup_msi_irqs() allocates the interrupt descriptors and sets
    up the MSI interrupts which ends up in pci_write_msi_msg() unless the
    interrupt chip provides its own irq_write_msi_msg() function.

 3) msix_program_entries() does not do what the name suggests. It solely
    updates the entries array (if not NULL) and initializes the masked
    member for each MSI descriptor by reading the hardware state and then
    masks the entry.

Obviously this has some issues:

 1) The uninitialized masked member of msi_desc prevents the enforcement
    of masking the entry in pci_write_msi_msg() depending on the cached
    masked bit. Aside of that half initialized data is a NONO in general

 2) msix_program_entries() only ensures that the actually allocated entries
    are masked. This is wrong as experimentation with crash testing and
    crash kernel kexec has shown.

    This limited testing unearthed that when the production kernel had more
    entries in use and unmasked when it crashed and the crash kernel
    allocated a smaller amount of entries, then a full scan of all entries
    found unmasked entries which were in use in the production kernel.

    This is obviously a device or emulation issue as the device reset
    should mask all MSI-X table entries, but obviously that's just part
    of the paper specification.

Cure this by:

 1) Masking all table entries in hardware
 2) Initializing msi_desc::masked in msix_setup_entries()
 3) Removing the mask dance in msix_program_entries()
 4) Renaming msix_program_entries() to msix_update_entries() to
    reflect the purpose of that function.

As the masking of unused entries has never been done the Fixes tag refers
to a commit in:
   git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git

Fixes: f036d4e ("[PATCH] ia32 Message Signalled Interrupt support")
Signed-off-by: Thomas Gleixner <[email protected]>
Tested-by: Marc Zyngier <[email protected]>
Reviewed-by: Marc Zyngier <[email protected]>
Acked-by: Bjorn Helgaas <[email protected]>
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: KAGA-KOKO

drivers/pci/msi.c

@@ -698,6 +698,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 {
 	struct irq_affinity_desc *curmsk, *masks = NULL;
 	struct msi_desc *entry;
+	void __iomem *addr;
 	int ret, i;
 	int vec_count = pci_msix_vec_count(dev);
 
@@ -718,6 +719,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 
 		entry->msi_attrib.is_msix	= 1;
 		entry->msi_attrib.is_64		= 1;
+
 		if (entries)
 			entry->msi_attrib.entry_nr = entries[i].entry;
 		else
@@ -729,6 +731,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 		entry->msi_attrib.default_irq	= dev->irq;
 		entry->mask_base		= base;
 
+		addr = pci_msix_desc_addr(entry);
+		if (addr)
+			entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
 		list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
 		if (masks)
 			curmsk++;
@@ -739,26 +745,25 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 	return ret;
 }
 
-static void msix_program_entries(struct pci_dev *dev,
-				 struct msix_entry *entries)
+static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
 {
 	struct msi_desc *entry;
-	int i = 0;
-	void __iomem *desc_addr;
 
 	for_each_pci_msi_entry(entry, dev) {
-		if (entries)
-			entries[i++].vector = entry->irq;
+		if (entries) {
+			entries->vector = entry->irq;
+			entries++;
+		}
+	}
+}
 
-		desc_addr = pci_msix_desc_addr(entry);
-		if (desc_addr)
-			entry->masked = readl(desc_addr +
-					      PCI_MSIX_ENTRY_VECTOR_CTRL);
-		else
-			entry->masked = 0;
+static void msix_mask_all(void __iomem *base, int tsize)
+{
+	u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	int i;
 
-		msix_mask_irq(entry, 1);
-	}
+	for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
+		writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
 
 /**
@@ -775,9 +780,9 @@ static void msix_program_entries(struct pci_dev *dev,
 static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 				int nvec, struct irq_affinity *affd)
 {
-	int ret;
-	u16 control;
 	void __iomem *base;
+	int ret, tsize;
+	u16 control;
 
 	/*
 	 * Some devices require MSI-X to be enabled before the MSI-X
@@ -789,12 +794,16 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 
 	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
 	/* Request & Map MSI-X table region */
-	base = msix_map_region(dev, msix_table_size(control));
+	tsize = msix_table_size(control);
+	base = msix_map_region(dev, tsize);
 	if (!base) {
 		ret = -ENOMEM;
 		goto out_disable;
 	}
 
+	/* Ensure that all table entries are masked. */
+	msix_mask_all(base, tsize);
+
 	ret = msix_setup_entries(dev, base, entries, nvec, affd);
 	if (ret)
 		goto out_disable;
@@ -808,7 +817,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 	if (ret)
 		goto out_free;
 
-	msix_program_entries(dev, entries);
+	msix_update_entries(dev, entries);
 
 	ret = populate_msi_sysfs(dev);
 	if (ret)