cxl: Add support for interrupts on the Mellanox CX4

The Mellanox CX4 in cxl mode uses a hybrid interrupt model, where
interrupts are routed from the networking hardware to the XSL using the
MSIX table, and from there will be transformed back into an MSIX
interrupt using the cxl style interrupts (i.e. using IVTE entries and
ranges to map a PE and AFU interrupt number to an MSIX address).

We want to hide the implementation details of cxl interrupts as much as
possible. To this end, we use a special version of the MSI setup &
teardown routines in the PHB while in cxl mode to allocate the cxl
interrupts and configure the IVTE entries in the process element.

This function does not configure the MSIX table - the CX4 card uses a
custom format in that table and it would not be appropriate to fill that
out in generic code. The rest of the functionality is similar to the
"Full MSI-X mode" described in the CAIA, and this could be easily
extended to support other adapters that use that mode in the future.

The interrupts will be associated with the default context. If the
maximum number of interrupts per context has been limited (e.g. by the
mlx5 driver), it will automatically allocate additional kernel contexts
to associate extra interrupts as required. These contexts will be
started using the same WED that was used to start the default context.

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 108 insertions, 0 deletions

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index f02a85974e49..f3d34b941f85 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -14,6 +14,7 @@
 #include <misc/cxl.h>
 #include <linux/fs.h>
 #include <asm/pnv-pci.h>
+#include <linux/msi.h>
 
 #include "cxl.h"
 
@@ -489,3 +490,73 @@ int cxl_get_max_irqs_per_process(struct pci_dev *dev)
 	return afu->irqs_max;
 }
 EXPORT_SYMBOL_GPL(cxl_get_max_irqs_per_process);
+
+/*
+ * This is a special interrupt allocation routine called from the PHB's MSI
+ * setup function. When capi interrupts are allocated in this manner they must
+ * still be associated with a running context, but since the MSI APIs have no
+ * way to specify this we use the default context associated with the device.
+ *
+ * The Mellanox CX4 has a hardware limitation that restricts the maximum AFU
+ * interrupt number, so in order to overcome this their driver informs us of
+ * the restriction by setting the maximum interrupts per context, and we
+ * allocate additional contexts as necessary so that we can keep the AFU
+ * interrupt number within the supported range.
+ */
+int _cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct cxl_context *ctx, *new_ctx, *default_ctx;
+	int remaining;
+	int rc;
+
+	ctx = default_ctx = cxl_get_context(pdev);
+	if (WARN_ON(!default_ctx))
+		return -ENODEV;
+
+	remaining = nvec;
+	while (remaining > 0) {
+		rc = cxl_allocate_afu_irqs(ctx, min(remaining, ctx->afu->irqs_max));
+		if (rc) {
+			pr_warn("%s: Failed to find enough free MSIs\n", pci_name(pdev));
+			return rc;
+		}
+		remaining -= ctx->afu->irqs_max;
+
+		if (ctx != default_ctx && default_ctx->status == STARTED) {
+			WARN_ON(cxl_start_context(ctx,
+				be64_to_cpu(default_ctx->elem->common.wed),
+				NULL));
+		}
+
+		if (remaining > 0) {
+			new_ctx = cxl_dev_context_init(pdev);
+			if (!new_ctx) {
+				pr_warn("%s: Failed to allocate enough contexts for MSIs\n", pci_name(pdev));
+				return -ENOSPC;
+			}
+			list_add(&new_ctx->extra_irq_contexts, &ctx->extra_irq_contexts);
+			ctx = new_ctx;
+		}
+	}
+
+	return 0;
+}
+/* Exported via cxl_base */
+
+void _cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct cxl_context *ctx, *pos, *tmp;
+
+	ctx = cxl_get_context(pdev);
+	if (WARN_ON(!ctx))
+		return;
+
+	cxl_free_afu_irqs(ctx);
+	list_for_each_entry_safe(pos, tmp, &ctx->extra_irq_contexts, extra_irq_contexts) {
+		cxl_stop_context(pos);
+		cxl_free_afu_irqs(pos);
+		list_del(&pos->extra_irq_contexts);
+		cxl_release_context(pos);
+	}
+}
+/* Exported via cxl_base */
diff --git a/drivers/misc/cxl/base.c b/drivers/misc/cxl/base.c
index fe90f895bb10..cd54ce6f6230 100644
--- a/drivers/misc/cxl/base.c
+++ b/drivers/misc/cxl/base.c
@@ -158,6 +158,37 @@ int cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_
 }
 EXPORT_SYMBOL_GPL(cxl_next_msi_hwirq);
 
+int cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	int ret;
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return false;
+
+	ret = calls->cxl_cx4_setup_msi_irqs(pdev, nvec, type);
+
+	cxl_calls_put(calls);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cxl_cx4_setup_msi_irqs);
+
+void cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return;
+
+	calls->cxl_cx4_teardown_msi_irqs(pdev);
+
+	cxl_calls_put(calls);
+}
+EXPORT_SYMBOL_GPL(cxl_cx4_teardown_msi_irqs);
+
 static int __init cxl_base_init(void)
 {
 	struct device_node *np;
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 73b9a55aa35b..d50cdb137c43 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -731,12 +731,16 @@ ssize_t cxl_pci_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
 bool _cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu);
 void _cxl_pci_disable_device(struct pci_dev *dev);
 int _cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq);
+int _cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
+void _cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev);
 
 struct cxl_calls {
 	void (*cxl_slbia)(struct mm_struct *mm);
 	bool (*cxl_pci_associate_default_context)(struct pci_dev *dev, struct cxl_afu *afu);
 	void (*cxl_pci_disable_device)(struct pci_dev *dev);
 	int (*cxl_next_msi_hwirq)(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq);
+	int (*cxl_cx4_setup_msi_irqs)(struct pci_dev *pdev, int nvec, int type);
+	void (*cxl_cx4_teardown_msi_irqs)(struct pci_dev *pdev);
 
 	struct module *owner;
 };
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index 66fac713e7ad..d9be23b24aa3 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -113,6 +113,8 @@ static struct cxl_calls cxl_calls = {
 	.cxl_pci_associate_default_context = _cxl_pci_associate_default_context,
 	.cxl_pci_disable_device = _cxl_pci_disable_device,
 	.cxl_next_msi_hwirq = _cxl_next_msi_hwirq,
+	.cxl_cx4_setup_msi_irqs = _cxl_cx4_setup_msi_irqs,
+	.cxl_cx4_teardown_msi_irqs = _cxl_cx4_teardown_msi_irqs,
 	.owner = THIS_MODULE,
 };