From: Thomas Gleixner tglx@linutronix.de
stable inclusion from linux-4.19.205 commit 3b570884c868c12e3184627ce4b4a167e9d6f018
--------------------------------
commit 7d5ec3d3612396dc6d4b76366d20ab9fc06f399f 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: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support") Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Marc Zyngier maz@kernel.org Reviewed-by: Marc Zyngier maz@kernel.org Acked-by: Bjorn Helgaas bhelgaas@google.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210729222542.403833459@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/pci/msi.c | 40 ++++++++++++++++++++++++++++------------ 1 file changed, 28 insertions(+), 12 deletions(-)
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 14dc5c1495836..4d00f03d76dd8 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -686,6 +686,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, { struct cpumask *curmsk, *masks = NULL; struct msi_desc *entry; + void __iomem *addr; int ret, i;
if (affd) @@ -705,6 +706,7 @@ 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 @@ -712,6 +714,10 @@ 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++; @@ -722,21 +728,27 @@ 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;
for_each_pci_msi_entry(entry, dev) { - if (entries) - entries[i++].vector = entry->irq; - entry->masked = readl(pci_msix_desc_addr(entry) + - PCI_MSIX_ENTRY_VECTOR_CTRL); - msix_mask_irq(entry, 1); + if (entries) { + entries->vector = entry->irq; + entries++; + } } }
+static void msix_mask_all(void __iomem *base, int tsize) +{ + u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT; + int i; + + for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE) + writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); +} + /** * msix_capability_init - configure device's MSI-X capability * @dev: pointer to the pci_dev data structure of MSI-X device function @@ -751,9 +763,9 @@ static void msix_program_entries(struct pci_dev *dev, static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec, const 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 @@ -765,12 +777,16 @@ 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; @@ -784,7 +800,7 @@ 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)