Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Jeffrey Hugo <quic_jhugo@quicinc.com>
To:     <kys@microsoft.com>, <haiyangz@microsoft.com>,
        <sthemmin@microsoft.com>, <wei.liu@kernel.org>,
        <decui@microsoft.com>, <lorenzo.pieralisi@arm.com>,
        <robh@kernel.org>, <kw@linux.com>, <bhelgaas@google.com>,
        <jakeo@microsoft.com>
CC:     <bjorn.andersson@linaro.org>, <linux-hyperv@vger.kernel.org>,
        <linux-pci@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        Jeffrey Hugo <quic_jhugo@quicinc.com>
Subject: [PATCH] PCI: hv: Fix multi-MSI to allow more than one MSI vector
Date:   Tue, 12 Apr 2022 08:16:31 -0600
Message-ID: <1649772991-10285-1-git-send-email-quic_jhugo@quicinc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Type: text/plain
Precedence: bulk

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().

Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs")
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
---
 drivers/pci/controller/pci-hyperv.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index d270a204..41be63e 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -614,7 +614,16 @@ static void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry,
 static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
 			  int nvec, msi_alloc_info_t *info)
 {
-	return pci_msi_prepare(domain, dev, nvec, info);
+	int ret = pci_msi_prepare(domain, dev, nvec, info);
+
+	/*
+	 * By using the interrupt remapper in the hypervisor IOMMU, contiguous
+	 * CPU vectors in not needed for multi-MSI
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	return ret;
 }
 
 /**
-- 
2.7.4