[PATCH v5 16/18] vfio-user: handle device interrupts

From: Jagannathan Raman <jag.raman@oracle.com>
To: qemu-devel@nongnu.org
Cc: eduardo@habkost.net, elena.ufimtseva@oracle.com,
	john.g.johnson@oracle.com, berrange@redhat.com, bleal@redhat.com,
	john.levon@nutanix.com, mst@redhat.com, armbru@redhat.com,
	quintela@redhat.com, f4bug@amsat.org, marcandre.lureau@gmail.com,
	stefanha@redhat.com, thanos.makatos@nutanix.com,
	pbonzini@redhat.com, jag.raman@oracle.com, eblake@redhat.com,
	dgilbert@redhat.com
Subject: [PATCH v5 16/18] vfio-user: handle device interrupts
Date: Wed, 19 Jan 2022 16:42:05 -0500	[thread overview]
Message-ID: <bc2c2c117aa72cc5d619ecfe549a252303ae539d.1642626515.git.jag.raman@oracle.com> (raw)
In-Reply-To: <cover.1642626515.git.jag.raman@oracle.com>

Forward remote device's interrupts to the guest

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
---
 include/hw/pci/pci.h      |  6 +++
 hw/pci/msi.c              | 13 +++++-
 hw/pci/msix.c             | 12 +++++-
 hw/remote/vfio-user-obj.c | 89 +++++++++++++++++++++++++++++++++++++++
 hw/remote/trace-events    |  1 +
 5 files changed, 119 insertions(+), 2 deletions(-)

diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 8c18f10d9d..092334d2af 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -128,6 +128,8 @@ typedef uint32_t PCIConfigReadFunc(PCIDevice *pci_dev,
 typedef void PCIMapIORegionFunc(PCIDevice *pci_dev, int region_num,
                                 pcibus_t addr, pcibus_t size, int type);
 typedef void PCIUnregisterFunc(PCIDevice *pci_dev);
+typedef void PCIMSINotify(PCIDevice *pci_dev, unsigned vector);
+typedef void PCIMSIxNotify(PCIDevice *pci_dev, unsigned vector);
 
 typedef struct PCIIORegion {
     pcibus_t addr; /* current PCI mapping address. -1 means not mapped */
@@ -322,6 +324,10 @@ struct PCIDevice {
     /* Space to store MSIX table & pending bit array */
     uint8_t *msix_table;
     uint8_t *msix_pba;
+
+    PCIMSINotify *msi_notify;
+    PCIMSIxNotify *msix_notify;
+
     /* MemoryRegion container for msix exclusive BAR setup */
     MemoryRegion msix_exclusive_bar;
     /* Memory Regions for MSIX table and pending bit entries. */
diff --git a/hw/pci/msi.c b/hw/pci/msi.c
index 47d2b0f33c..93f5e400cc 100644
--- a/hw/pci/msi.c
+++ b/hw/pci/msi.c
@@ -51,6 +51,8 @@
  */
 bool msi_nonbroken;
 
+static void pci_msi_notify(PCIDevice *dev, unsigned int vector);
+
 /* If we get rid of cap allocator, we won't need this. */
 static inline uint8_t msi_cap_sizeof(uint16_t flags)
 {
@@ -225,6 +227,8 @@ int msi_init(struct PCIDevice *dev, uint8_t offset,
     dev->msi_cap = config_offset;
     dev->cap_present |= QEMU_PCI_CAP_MSI;
 
+    dev->msi_notify = pci_msi_notify;
+
     pci_set_word(dev->config + msi_flags_off(dev), flags);
     pci_set_word(dev->wmask + msi_flags_off(dev),
                  PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
@@ -307,7 +311,7 @@ bool msi_is_masked(const PCIDevice *dev, unsigned int vector)
     return mask & (1U << vector);
 }
 
-void msi_notify(PCIDevice *dev, unsigned int vector)
+static void pci_msi_notify(PCIDevice *dev, unsigned int vector)
 {
     uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
     bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
@@ -332,6 +336,13 @@ void msi_notify(PCIDevice *dev, unsigned int vector)
     msi_send_message(dev, msg);
 }
 
+void msi_notify(PCIDevice *dev, unsigned int vector)
+{
+    if (dev->msi_notify) {
+        dev->msi_notify(dev, vector);
+    }
+}
+
 void msi_send_message(PCIDevice *dev, MSIMessage msg)
 {
     MemTxAttrs attrs = {};
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
index ae9331cd0b..1c71e67f53 100644
--- a/hw/pci/msix.c
+++ b/hw/pci/msix.c
@@ -31,6 +31,8 @@
 #define MSIX_ENABLE_MASK (PCI_MSIX_FLAGS_ENABLE >> 8)
 #define MSIX_MASKALL_MASK (PCI_MSIX_FLAGS_MASKALL >> 8)
 
+static void pci_msix_notify(PCIDevice *dev, unsigned vector);
+
 MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)
 {
     uint8_t *table_entry = dev->msix_table + vector * PCI_MSIX_ENTRY_SIZE;
@@ -334,6 +336,7 @@ int msix_init(struct PCIDevice *dev, unsigned short nentries,
     dev->msix_table = g_malloc0(table_size);
     dev->msix_pba = g_malloc0(pba_size);
     dev->msix_entry_used = g_malloc0(nentries * sizeof *dev->msix_entry_used);
+    dev->msix_notify = pci_msix_notify;
 
     msix_mask_all(dev, nentries);
 
@@ -485,7 +488,7 @@ int msix_enabled(PCIDevice *dev)
 }
 
 /* Send an MSI-X message */
-void msix_notify(PCIDevice *dev, unsigned vector)
+static void pci_msix_notify(PCIDevice *dev, unsigned vector)
 {
     MSIMessage msg;
 
@@ -503,6 +506,13 @@ void msix_notify(PCIDevice *dev, unsigned vector)
     msi_send_message(dev, msg);
 }
 
+void msix_notify(PCIDevice *dev, unsigned vector)
+{
+    if (dev->msix_notify) {
+        dev->msix_notify(dev, vector);
+    }
+}
+
 void msix_reset(PCIDevice *dev)
 {
     if (!msix_present(dev)) {
diff --git a/hw/remote/vfio-user-obj.c b/hw/remote/vfio-user-obj.c
index bf88eac8f1..1771dba1bf 100644
--- a/hw/remote/vfio-user-obj.c
+++ b/hw/remote/vfio-user-obj.c
@@ -53,6 +53,8 @@
 #include "hw/qdev-core.h"
 #include "hw/pci/pci.h"
 #include "qemu/timer.h"
+#include "hw/pci/msi.h"
+#include "hw/pci/msix.h"
 
 #define TYPE_VFU_OBJECT "x-vfio-user-server"
 OBJECT_DECLARE_TYPE(VfuObject, VfuObjectClass, VFU_OBJECT)
@@ -106,6 +108,8 @@ struct VfuObject {
     int vfu_poll_fd;
 };
 
+static GHashTable *vfu_object_dev_to_ctx_table;
+
 static void vfu_object_init_ctx(VfuObject *o, Error **errp);
 
 static void vfu_object_set_socket(Object *obj, Visitor *v, const char *name,
@@ -381,6 +385,72 @@ static void vfu_object_register_bars(vfu_ctx_t *vfu_ctx, PCIDevice *pdev)
     }
 }
 
+static int vfu_object_map_irq(PCIDevice *pci_dev, int intx)
+{
+    /*
+     * We only register one INTx interrupt with the server. map_irq
+     * callback is required for PCIBus.
+     */
+    return 0;
+}
+
+static void vfu_object_set_irq(void *opaque, int pirq, int level)
+{
+    vfu_ctx_t *vfu_ctx = opaque;
+
+    if (vfu_ctx && level) {
+        vfu_irq_trigger(vfu_ctx, 0);
+    }
+}
+
+static void vfu_object_msi_notify(PCIDevice *pci_dev, unsigned vector)
+{
+    vfu_ctx_t *vfu_ctx = NULL;
+
+    if (!vfu_object_dev_to_ctx_table) {
+        return;
+    }
+
+    vfu_ctx = g_hash_table_lookup(vfu_object_dev_to_ctx_table, pci_dev);
+
+    if (vfu_ctx) {
+        vfu_irq_trigger(vfu_ctx, vector);
+    }
+}
+
+static int vfu_object_setup_irqs(VfuObject *o, PCIDevice *pci_dev)
+{
+    vfu_ctx_t *vfu_ctx = o->vfu_ctx;
+    int ret;
+
+    ret = vfu_setup_device_nr_irqs(vfu_ctx, VFU_DEV_INTX_IRQ, 1);
+    if (ret < 0) {
+        return ret;
+    }
+
+    pci_bus_irqs(pci_get_bus(o->pci_dev), vfu_object_set_irq,
+                 vfu_object_map_irq, o->vfu_ctx, 1);
+
+    ret = 0;
+    if (msix_nr_vectors_allocated(pci_dev)) {
+        ret = vfu_setup_device_nr_irqs(vfu_ctx, VFU_DEV_MSIX_IRQ,
+                                       msix_nr_vectors_allocated(pci_dev));
+
+        pci_dev->msix_notify = vfu_object_msi_notify;
+    } else if (msi_nr_vectors_allocated(pci_dev)) {
+        ret = vfu_setup_device_nr_irqs(vfu_ctx, VFU_DEV_MSI_IRQ,
+                                       msi_nr_vectors_allocated(pci_dev));
+
+        pci_dev->msi_notify = vfu_object_msi_notify;
+    }
+
+    if (ret < 0) {
+        return ret;
+    }
+
+    return 0;
+}
+
 /*
  * TYPE_VFU_OBJECT depends on the availability of the 'socket' and 'device'
  * properties. It also depends on devices instantiated in QEMU. These
@@ -478,6 +548,13 @@ static void vfu_object_init_ctx(VfuObject *o, Error **errp)
 
     vfu_object_register_bars(o->vfu_ctx, o->pci_dev);
 
+    ret = vfu_object_setup_irqs(o, o->pci_dev);
+    if (ret < 0) {
+        error_setg(errp, "vfu: Failed to setup interrupts for %s",
+                   o->device);
+        goto fail;
+    }
+
     ret = vfu_realize_ctx(o->vfu_ctx);
     if (ret < 0) {
         error_setg(errp, "vfu: Failed to realize device %s- %s",
@@ -491,6 +568,8 @@ static void vfu_object_init_ctx(VfuObject *o, Error **errp)
         goto fail;
     }
 
+    g_hash_table_insert(vfu_object_dev_to_ctx_table, o->pci_dev, o->vfu_ctx);
+
     qemu_set_fd_handler(o->vfu_poll_fd, vfu_object_attach_ctx, NULL, o);
 
     return;
@@ -552,9 +631,15 @@ static void vfu_object_finalize(Object *obj)
         o->unplug_blocker = NULL;
     }
 
+    if (o->pci_dev) {
+        g_hash_table_remove(vfu_object_dev_to_ctx_table, o->pci_dev);
+    }
+
     o->pci_dev = NULL;
 
     if (!k->nr_devs && k->auto_shutdown) {
+        g_hash_table_destroy(vfu_object_dev_to_ctx_table);
+        vfu_object_dev_to_ctx_table = NULL;
         qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
     }
 
@@ -572,6 +657,10 @@ static void vfu_object_class_init(ObjectClass *klass, void *data)
 
     k->auto_shutdown = true;
 
+    msi_nonbroken = true;
+
+    vfu_object_dev_to_ctx_table = g_hash_table_new_full(NULL, NULL, NULL, NULL);
+
     object_class_property_add(klass, "socket", "SocketAddress", NULL,
                               vfu_object_set_socket, NULL, NULL);
     object_class_property_set_description(klass, "socket",
diff --git a/hw/remote/trace-events b/hw/remote/trace-events
index 847d50d88f..c167b3c7a5 100644
--- a/hw/remote/trace-events
+++ b/hw/remote/trace-events
@@ -12,3 +12,4 @@ vfu_dma_unregister(uint64_t gpa) "vfu: unregistering GPA 0x%"PRIx64""
 vfu_bar_register(int i, uint64_t addr, uint64_t size) "vfu: BAR %d: addr 0x%"PRIx64" size 0x%"PRIx64""
 vfu_bar_rw_enter(const char *op, uint64_t addr) "vfu: %s request for BAR address 0x%"PRIx64""
 vfu_bar_rw_exit(const char *op, uint64_t addr) "vfu: Finished %s of BAR address 0x%"PRIx64""
+vfu_interrupt(int pirq) "vfu: sending interrupt to device - PIRQ %d"
-- 
2.20.1


