This is a note to let you know that I've just added the patch titled
PCI: hv: Fix multi-MSI to allow more than one MSI vector
to the 4.19-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
pci-hv-fix-multi-msi-to-allow-more-than-one-msi-vector.patch
and it can be found in the queue-4.19 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From foo@baz Wed Jul 27 12:32:32 PM CEST 2022
From: Carl Vanderlip <quic_carlv@xxxxxxxxxxx>
Date: Mon, 25 Jul 2022 16:32:37 +0000
Subject: PCI: hv: Fix multi-MSI to allow more than one MSI vector
To: <stable@xxxxxxxxxxxxxxx>
Cc: Jeffrey Hugo <quic_jhugo@xxxxxxxxxxx>, <kys@xxxxxxxxxxxxx>, <haiyangz@xxxxxxxxxxxxx>, <sthemmin@xxxxxxxxxxxxx>, <wei.liu@xxxxxxxxxxxxx>, <decui@xxxxxxxxxxxxx>, <lorenzo.pieralisi@xxxxxxx>, <robh@xxxxxxxxxx>, <kw@xxxxxxxxx>, <bhelgaas@xxxxxxxxxx>, Wei Liu <wei.liu@xxxxxxxxxx>, "Carl Vanderlip" <quic_carlv@xxxxxxxxxxx>
Message-ID: <20220725163240.13001-2-quic_carlv@xxxxxxxxxxx>
From: Jeffrey Hugo <quic_jhugo@xxxxxxxxxxx>
commit 08e61e861a0e47e5e1a3fb78406afd6b0cea6b6d upstream.
If the allocation of multiple MSI vectors for multi-MSI fails in the core
PCI framework, the framework will retry the allocation as a single MSI
vector, assuming that meets the min_vecs specified by the requesting
driver.
Hyper-V advertises that multi-MSI is supported, but reuses the VECTOR
domain to implement that for x86. The VECTOR domain does not support
multi-MSI, so the alloc will always fail and fallback to a single MSI
allocation.
In short, Hyper-V advertises a capability it does not implement.
Hyper-V can support multi-MSI because it coordinates with the hypervisor
to map the MSIs in the IOMMU's interrupt remapper, which is something the
VECTOR domain does not have. Therefore the fix is simple - copy what the
x86 IOMMU drivers (AMD/Intel-IR) do by removing
X86_IRQ_ALLOC_CONTIGUOUS_VECTORS after calling the VECTOR domain's
pci_msi_prepare().
4.19 backport - adds the hv_msi_prepare wrapper function.
X86_IRQ_ALLOC_TYPE_PCI_MSI changed to X86_IRQ_ALLOC_TYPE_MSI
(same value).
Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs")
Signed-off-by: Jeffrey Hugo <quic_jhugo@xxxxxxxxxxx>
Reviewed-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/1649856981-14649-1-git-send-email-quic_jhugo@xxxxxxxxxxx
Signed-off-by: Wei Liu <wei.liu@xxxxxxxxxx>
Signed-off-by: Carl Vanderlip <quic_carlv@xxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/pci/controller/pci-hyperv.c | 17 ++++++++++++++++-
1 file changed, 16 insertions(+), 1 deletion(-)
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -893,6 +893,21 @@ static void hv_irq_mask(struct irq_data
pci_msi_mask_irq(data);
}
+static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
+ int nvec, msi_alloc_info_t *info)
+{
+ int ret = pci_msi_prepare(domain, dev, nvec, info);
+
+ /*
+ * By using the interrupt remapper in the hypervisor IOMMU, contiguous
+ * CPU vectors is not needed for multi-MSI
+ */
+ if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+ info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+ return ret;
+}
+
/**
* hv_irq_unmask() - "Unmask" the IRQ by setting its current
* affinity.
@@ -1240,7 +1255,7 @@ static irq_hw_number_t hv_msi_domain_ops
static struct msi_domain_ops hv_msi_ops = {
.get_hwirq = hv_msi_domain_ops_get_hwirq,
- .msi_prepare = pci_msi_prepare,
+ .msi_prepare = hv_msi_prepare,
.set_desc = pci_msi_set_desc,
.msi_free = hv_msi_free,
};
Patches currently in stable-queue which might be from quic_carlv@xxxxxxxxxxx are
queue-4.19/pci-hv-fix-interrupt-mapping-for-multi-msi.patch
queue-4.19/pci-hv-fix-multi-msi-to-allow-more-than-one-msi-vector.patch
queue-4.19/pci-hv-reuse-existing-irte-allocation-in-compose_msi_msg.patch
queue-4.19/pci-hv-fix-hv_arch_irq_unmask-for-multi-msi.patch
